知识热榜

62 个榜单

arXiv · cs.LG

10天前更新
  • 01
    A Zeroth-Order Paradigm for LLM Preference Alignment
    Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency. However, likelihood displacement motivates alternative ways to extract information from preference pairs with small likelihood margins. In this paper, we propose and analyze Comparison-based Preference Optimization (ComPO), a zeroth-order alignment method based on comparison oracles. ComPO extracts directional information from thesPeter Chen
  • 02
    Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
    Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on history. For every horizon $H \ge 3$, we construct two POMDPs with at most two latent states per stage, three actions, and a common logger with three memory states. Action coverage, belief coverage, and two behavior-marginal outcome-revealing conditions all have constants independent of $H$. Nevertheless, evaluating a knowPranaya Jajoo
  • 03
    Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
    Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective inteJoão Meneses dos Santos
  • 04
    How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents
    Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to exponential improvements in performance with increases in computation. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing theZixi Chen
  • 05
    Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
    As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model representations? This work analyzes how reward hacking is represented internally in frontier open source LLMs, and how those representations can be used to understand and discover the range of hacking behaviors a model displays. In particular, we find that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and QwenLeon Bergen
  • 06
    Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory
    Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present Andromeda 2, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. Using a miniaturized automated laboratory at a matched budget, we benchmark it against Andromeda 1, a probaMichael M. Craig
  • 07
    A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings
    Kernel methods, and Gaussian Processes (GPs) in particular, require a Hilbertian distance measure---one whose square is conditionally negative definite (CND)---to guarantee positive semi-definiteness (PSD) of the kernel matrix; a condition that fails for many natural input spaces, including smooth manifolds and spaces of probability distributions. We propose the Sparse Landmark Embedding (SLE) kernel, which eliminates this requirement entirely. Each input is embedded into a sparse feature vectorMarcus M. Noack
  • 08
    Probabilistic Linear Explanations
    Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by involving too many features, while probabilistic relaxations have remained largely limited to categorical classification. We present a unified framework for probabilistic explainability based on sparse, anchored linear models, applicable to both binary classification and continuous regression. By mapping instances to the BooleanFrederic Koriche
  • 09
    Double descent is the principle of least action
    The test error of a model plotted against its number of parameters $d$ falls, peaks when the model can just fit the training data, and falls again, exhibiting the double descent phenomenon. We explain the phenomenon with statistical mechanics. The training trajectory of a stochastic gradient-based method is a particle wandering over the energy landscape of the training loss at an induced temperature $T$, and a run that has equilibrated visits every parameter vector of a given training loss equalCongzhou M Sha
  • 10
    RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control
    Reinforcement learning (RL) is an exciting concept as well as a remarkable success story worth sharing. However, RL builds on rather complex interactions between different objects that play out over several cycles. Such dynamics are often best explained with an easily accessible implementation. We present RLLBC-Lib, a carefully crafted code library with the goal of lowering the entry barrier for students and other learners of RL in the context of learning-based control. At its heart, RLLBC-Lib cBernd Frauenknecht
  • 11
    Social Laws for Multi-agent Coordination in Stochastic Environments
    In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous research on social laws for multi-agent systems has primarily focused on deterministic, goal-based settings. This paper extends the concept of social laws to stochastic, reward-based environments, proposing a formalism for defining and verifying their robustness under various conditions. We introduce the notion of $α$-robustness, a measure of the guaRolando Fernandez
  • 12
    Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
    In particle collider experiments, event reconstruction is the task of inferring the kinematics of short-lived particles produced in the hard scatter from the stable final states recorded by detectors. We decompose event reconstruction into two primary tasks: assigning measured jets and charged leptons to parent particles, and predicting unmeasured neutrino kinematics. We present VyPER, a novel geometric learning framework that represents collider events as hypergraphs with a physics-inspired topLining Mao
  • 13
    Higher-order pruning of experts in mixture-of-experts language models
    Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for reducing this parameter count, yet existing methods make pruning decisions for each expert independently, and assume experts' contributions are purely additive. In reality, expert usage in MoEs is inherently cooperative. We derive HOPE (Higher-Order Pruning of Experts), a second-order pruning objective which provably minimizes aAlex M. Tseng
  • 14
    Fast Learning Rates for Physics-Informed Kernel Methods
    In physics-informed machine learning, a target function $u^*$ is learned from noisy value observations $y_i=u^*(x_i)+ \varepsilon_i$, together with differential information, given either by noisy observations $d_j=(Du^*)(z_j)+ξ_j$ or by a known physical constraint $Du^*=v$. We consider the setting where $D$ is a linear differential operator and analyze a physics-informed kernel estimator $\hat u$ combining $n$ value observations and $m$ differential observations. In this context, we ask how muchLuc Brogat-Motte
  • 15
    Learning Lyapunov Operators for Nonlinear Systems
    Constructing Lyapunov functions for nonlinear dynamical systems is a central problem in stability analysis, yet remains challenging. Lyapunov functions are commonly characterized as solutions to first-order partial differential equations (PDEs), but these solutions are typically obtained for single systems, limiting their reuse across systems. In this paper, we study the Lyapunov solution operator that maps a vector field to the corresponding Lyapunov function defined by a dissipation-based LyapAmartya Mukherjee
  • 16
    Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data
    Large Language Models (LLMs) are now routinely trained using synthetic data, since high-quality human data has been exhausted by the ever increasing needs of larger and larger models. However, recursive training on synthetic data frequently induces model collapse, a degenerative feedback loop where models progressively forget the true underlying data distribution. Training on a mixture of synthetic and fresh human data is a logical countermeasure and can prevent model collapse. However, it is anMatteo Marchi
  • 17
    Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
    Reliable prediction of crystallographic texture in laser powder bed fusion is critical for linking process conditions with anisotropic response and for qualification. However, black-box models may fail under shift and cannot distinguish weak data support from loss of physical validity. This study develops a two-stage physics-based model for <001> || BD (build direction) texture in Inconel 718. Stage 1 maps process variables to melting mode and melt pool geometry. Stage 2 predicts texture by combYisheng Lu
  • 18
    Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
    When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represented evidence to its output. We distinguish these cases in Gemma-3 and Qwen3.5 using sparse autoencoders, role-conditioned probes, causal interventions, and recovery experiments across six harmful content benchmarks, with additional Spanish and Hindi-English code-mixed evaluations. Sparse readouts outperform native prediction on all six primary binaryGirish A. Koushik
  • 19
    Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data
    The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures have ridden these laws to remarkable results, activating only a fraction of an enormous stored parameter bank for each token. That success is built on static pretraining data. A deployed model faces a different world, where much of the data that would make it more useful is not in its training set but in the live interaction it is currently handliJinli Hu
  • 20
    Interpretable Multi-Instance Learning Enables Early Prediction of Key Molecular Alterations from Routine Flow Cytometry in Acute Myeloid Leukemia
    Background: Molecular testing for NPM1 and FLT3-ITD mutations guides critical early treatment decisions in acute myeloid leukemia (AML), but results can take weeks, long after these decisions must be made. Flow cytometry, already performed within hours of admission as part of routine care, may carry enough signal to predict these mutations directly, without added cost or delay. Methods: We developed an interpretable multi-instance learning classifier based on a decision tree, in which each patieJonathan Legrand
  • 21
    WaveTLM: Reliable Time-Series Language Modeling through Task Compilation
    Time-series language models provide a shared natural-language interface across temporal tasks, but plausible text does not guarantee reliable task outputs. Responses may appear reasonable while hallucinating the required object: numerical sequences can violate shape, scale, channel order, or temporal alignment, and textual decisions can fall outside the legal label space. We formulate reliable time-series language modeling, separating task-object reliability from predictive quality. We introduceJiahui Chen
  • 22
    A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds
    We establish convergence bounds for deep $V$-learning with horizon $H$. The algorithm fits a scalar value function to targets from executed transitions and selects actions using a predictive model and the value function. For current observed-successor targets with fresh true-kernel outcomes, the conditional mean is $\mathcal{T}^βV$, which averages over behavior-policy actions. The Bellman optimality update is $\mathcal{T} V$. We decompose the update error into six residuals: fitting, transitionYury Kolomeytsev
  • 23
    CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
    Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond to evolving agent capabilities. This disconnect prevents routing strategies from adapting to evolving agent capabilities during post-training and prevents agents from achieving synergistic data-driven specialization. To resolve this, we introduce CERA-MoA (Co-Evolving Router with continually learning Agents for Mixture-of-Agents), an iterative reiJiaxuan Jiang
  • 24
    Stable Filters for Generative Modeling of Graph Signals
    Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While recent graph-aware Schrödinger bridge models incorporate topology information directly into their reference dynamics, it is unclear how perturbations of the graph propagate through these dynamics and affect the resulting generated distributions. In this paper, we analyze the structural stability of graph-aware continuous-time generative models whoseMartin Schmidt
  • 25
    When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows
    Antibody lead optimization calls for a small, bounded set of edits to an existing candidate: substitutions, but also insertions and deletions. Edit-based generative models are the only ones that allocate such an edit budget without fixing the edit positions, the edit count, or the output length in advance. However, the existing approaches Edit Flows and EvoFlows did not release code or complete training specifications. Here, we show that both methods follow the same underlying process -- edits fGabriel Bénédict
  • 26
    Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning
    We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large Language Model (LLM) decoding framework that frames candidate token selection as ensemble pruning. Existing selection strategies rely predominantly on scalar probabilities, ignoring geometric semantic relationships and causing candidate redundancy. Meanwhile, current geometry-aware methods often require complex optimization or directly reweighting the original token probabilities, leading to significant computational overheaDunyao Xue
  • 27
    Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
    In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated from multiple Monte Carlo continuations, change sharply across intermediate states while critic predictions remain comparatively flat. We further observe this phenomenon in a controlled FrozenLake enviroYizhuo Li
  • 28
    Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study
    Modern networks must support changing topologies, configurations, and performance objectives, motivating fast and reliable performance estimation. Network digital twins (NDTs) enable what-if analysis for performance estimation in such network scenarios, however, existing machine learning-based NDT approaches often rely on entire topology representations, which are inherently monolithic and lack reusability under topological or traffic changes in the network. This paper introduces a composable NDShenjia Ding
  • 29
    Rank and computation of the pathlifting Jacobian of a DAG ReLU network
    This paper provides a self-contained proof of the rank of the pathlifting Jacobian of a DAG ReLU network by performing an induction on the network's number of hidden nodes. In fact, the induction is elementary, and the key recipe is to consider the skeleton matrix of the network, a sparse matrix encoding the network paths, and transform the representation of one of its hidden neurons into an output node. The proof relies on intermediate propositions which link the pathlifting, its Jacobian, theManon Verbockhaven
  • 30
    The Uneven Impact of Generative AI on Student Learning: Examining the Roles of Reliance, Evaluation Literacy, and Course Policy in AI-related Courses
    Generative artificial intelligence (GenAI) is changing how students learn, yet the roles of course context, cognitive reliance, evaluation literacy, and early reliance remain underexplored. Using survey responses from 118 students across 12 AI-related courses at our institution, we examined differences in GenAI use and perceived learning experiences. We identified four user clusters: high-use students reporting many benefits, light users reporting less reliance and fewer benefits, and two moderaLydia Manikonda
  • 31
    VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge
    Billion-parameter vision--language--action (VLA) policies demand substantial onboard power, while communication delays in remote inference hinder timely responses. We propose VLA-ULAP, which interleaves remote VLA calls with an Ultra-Lightweight Local Action Predictor (ULAP). With approximately 7.4M parameters including the frozen vision encoder, ULAP combines current views, proprioception, and executed action history to predict chunks in one pass. Trained independently, it requires no VLA hiddeDeyu Cao
  • 32
    Revisiting Distributed Sign-Based Variance Reduction
    Sign-based methods reduce communication costs in distributed environments, but aggregating local signs can introduce bias when data are heterogeneous. As a result, existing sign-based variance reduction methods fail to obtain the optimal convergence rates. In this paper, we solve this problem and obtain optimal rates for both nonconvex stochastic and finite-sum optimization. We first give a counterexample showing that majority voting can fail to approach stationary points even with exact local gWei Jiang
  • 33
    Learning to Program Adaptive Non-Local Observables for Machine Learning
    Quantum neural networks (QNNs) are typically built from variational quantum circuits (VQCs), which are limited by local measurements. Adaptive non-local observables (ANO) address this by jointly optimizing circuit parameters and multi-qubit measurements. However, existing ANO-based VQCs learn only a single static observable that remains invariant across all inputs. We propose QFWP-ANO, a novel architecture which employs a classical hypernetwork to dynamically program VQC parameters and/or non-loYu-Ting Lee
  • 34
    Fallacy Benchmarks Measure Scheme Recognition, Not Fallacy Detection
    Fallacy-detection benchmarks pair fallacy classes with a single "valid" or "none" class that takes everything data collection did not label as a fallacy. This construction is misleading: a classifier can learn cues that do well on this class without learning to tell a fallacy from a correct argument. We show that the low false-positive rates benchmarks report are an artifact of how the class is built, not evidence of detection ability. The most informative negative for a fallacy is a correct argNavyansh Singh
  • 35
    CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning
    Emergency management assistance programs, such as relief distribution, are essential for delivering necessary supplies to affected communities. However, these programs operate in a decentralized network of local centers that face uncertain local demand and supply dynamics, resulting in inconsistent avail- ability of local services. Redistribution of supplies among these local centers reduces these imbalances, but the centers often make decisions independently, with limited information and disrupNaimur Rahman Chowdhury
  • 36
    How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction
    Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differently. We quantify this requirement for the area under the generalized risk-coverage curve (AUGRC). A prelabel lower bound rules out insufficient budgets. With all labels known, a covering linear program bounds the minimum number of labels sufficient to fix the winner (the certificate size) within $K-1$ labels for $K$ candidates. For fixed $K$, indepTetsuji Kuboyama
  • 37
    Learning Array Signal Topologies as Conditional Neural Manifolds
    Subspace methods such as multiple signal classification (MUSIC) achieve super-resolution direction of arrival (DoA) estimation by exploiting the orthogonality between the array manifold and the noise subspace of the measurements. Their accuracy therefore depends on the assumed manifold and degrades under model mismatch, while parameters not identifiable from the spatial manifold cannot be recovered. In this work, we propose the conditional neural manifold (CNM), which replaces the fixed manifoldJulian P. Merkofer
  • 38
    Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence
    We analyze the learned input-output behavior of GLU-based neurons in large language models (LLMs). We propose a simple analysis method: For each neuron, we compute the cosine similarities between its input (reading) and output (writing) weight vectors. In this scheme, a strong negative cosine similarity indicates the neuron weakens the direction it detects in the residual stream, so we call this a weakening neuron. This allows us to gain a number of novel insights. First, we show that nine diffeSebastian Gerstner
  • 39
    A Geometric Theory of Decision Boundaries in Structured Markov Decision Processes
    Classical dynamic programming represents optimal sequential decisions through value functions and policies. While this functional representation is natural for computing optimal decisions, it does not directly identify the mathematical object governing policy reconstruction, representation complexity, or oracle-query complexity once an optimal policy is fixed. This paper addresses this question by developing a geometric theory of structured optimal policies in which the decision-boundary geometrFredy Pokou
  • 40
    PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
    As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such as hiring, healthcare, and finance. In these contexts, compliance with rules specified in an agent's system context is a first-order legal concern. Currently, no evaluation framework systematically measures which LLM models tend to violate compliance rules, especially under pressure from a persistent user, a hurried manager, or circumstances where violation is convenient or attMika Okamoto
  • 41
    Online Robust Reinforcement Learning Through Monte-Carlo Planning
    Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real-world dynamics are identical. Although this assumption helps achieve the success of MCTS in games like Chess, Go, and Shogi, the real-world scenarios incur ambiguity due to their modeling mismatches in low-fidelity simulators. In this work, we present a new robust variant of MCTS that mitigates dynamical model ambiguities. OurTuan Dam
  • 42
    Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection
    Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily rely on supervised GNN-based models, which require substantial labeled data and exhibit limited generalization. Although large language models (LLMs) exhibit strong reasoning capabilities, directly feeding them raw propagation graphs creates a significant modality mismatch and severe information overload, making structure-aware reasoning unreliable in zero-shot and few-shot settings. To briZiyi Zhou
  • 43
    ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networks
    Logic resynthesis preserves circuit functionality while changing gate vocabulary, topology, and structural statistics, creating domain shift for circuit graph neural networks (GNNs) without changing task labels. To study this setting, we introduce ReDIL-GNN, a resynthesis domain-incremental learning framework that adapts a fixed prediction or representation head as new synthesis styles arrive and evaluates retention on all previously observed domains. Because not every shift should be adapted blRupesh Raj Karn
  • 44
    Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels
    For distribution system operators, short-term load forecasting (STLF) supports congestion management, voltage control, and asset protection. Most existing approaches focus on overall accuracy across all time steps and neglect performance during high-demand (HD) periods, where larger forecast errors can increase the risk of congestion and voltage violations. In this paper, we study peak-aware STLF across three operator-relevant distribution grid aggregation levels, area codes (AC), secondary subsSouhardya Chattopadhyay
  • 45
    Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
    Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters. This raises a natural question: can effective test-time adaptation emerge when both the reward signal and the optimization space are severely restricted? We answer this question with label-free bias-only TTRL, which uses majority-vote pseudo-labels as rewards and optimizes only approximatelNaveen Vakada
  • 46
    TTM-Bench: A Framework for Text-to-Music System Performance Benchmarking
    Text-to-music (TTM) systems are increasingly used to generate musical audio from natural-language descriptions. Robust evaluation is therefore essential, yet reliable performance comparison remains challenging. This difficulty stems from differences in system architecture, supported conditioning information, and access mode, as well as heterogeneous and fragmented metrics that cannot be applied uniformly across systems. To address these challenges, we introduce TTM-Bench, a framework that defineGiorgia Adorni
  • 47
    Accurate Trace Estimation with Fewer Random Bits via Recursive TensorSketch
    We consider the problem of estimating the trace of an implicit matrix $\mathbf{A} \in \mathbb{R}^{d^p\times d^p}$ that can only be accessed through matrix-vector products queries. The \textit{Hutchinson trace estimator}% ~\cite{Girard1987algorithme, article-hutchinson} is a classical sketching method for this problem. Their estimator, $H_{m}(\mathbf{A}) = \frac{1}{m} \sum_{i=1}^{m} {\mathbf{z}^{(i)}}^T \mathbf{A} \mathbf{z}^{(i)}, \quad \text{where } \ {\mathbf{z}^{(i)}}\in \mathbb{R}^{d^p}$, anMohammad Azhar Khan
  • 48
    Deep learning emergent spacetime from fermionic spectral functions in holography
    We present a physics-informed machine learning framework based on Neural Ordinary Differential Equations that solves the holographic inverse problem: reconstructing the bulk spacetime and gauge field of a charged AdS black hole directly from boundary fermionic spectral functions. Encoding the UV asymptotics, horizon regularity, and zero temperature extremality as hard constraints in the neural network architecture, our framework reliably reconstructs the extremal Reissner-Nordström AdS geometryKoji Hashimoto
  • 49
    Variational Quantum Transformer Architecture for Synthetic Language Generation
    We propose a compact NISQ-compatible quantum transformer architecture for synthetic QNLP sequence modelling. The model preserves the autoregressive next-token interface of a classical transformer, but replaces attention and feed-forward sublayers with variational quantum encoder blocks, connector circuits, decoder blocks and a direct two-qubit measurement readout. Token contexts are angle-encoded into small quantum registers, processed by parallel variational heads and encoder integration circuiJulian Hager
  • 50
    The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations
    Some aspects of AI development resemble a population process in which models are specialised, retrained on the output of peers, or combined by averaging weights. These practices lead to generations of models, in the biological sense studied by population genetics. Here, I develop this parallelism and interpret multigenerational model populations in terms of sexual and asexual reproduction, formally recombining the two fields. I test these analogies in an exact inheritance model, in trained netwoGiorgio F. Gilestro
  • 51
    Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations
    Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble member. We ask how well deep learning surrogates can reproduce these simulations at a fraction of this cost, training them on 10,584 fire spread simulations at 2m resolution for the Rectoret region in Catalonia, Spain. Four architectures are compared: a patch-based U-Net, a transfer-learned ResNet-50, a physics-informed network constMarcin Lawenda
共 100 条热搜查看完整榜单
共 20 条热搜查看完整榜单
  • 01201
    Training Object Permanence in World Models
    Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show emerged reasoning abilities, making them ideal candidates for building human-like physical intelligence. Do video models have emerged object permanence in them? If not, could we train them with a core-cognition inspired dataset? We introduce WROP (World Reasoning with Object Permanence), a data infrastructure of 150 hand-designed cognitive science inspired tasks, divided into six cognitive categories. We build Blender generators that randomize speed, lighting, camera angle, and other nuisance parameters while preserving each task's cognitive structure, yielding 10,000+ samples per task. We release a 1.5M-sample training corpus and a 300-question exam. On this exam we evaluate 14 video models: 3 reference-to-video, 7 edit, and 4 continuation, among which PWM-WROP, our 16B world model. In a blind pairwise Elo study, PWM-WROP ranks first among continuation models and third overall, behind only a statistical tie between two reference-to-video models. We release the data, exam, model answers, scores, weights, and PWM, our native-PyTorch training stack on AWS Trainium2.Haotian Zhang, Fengyuan Yu, Dezhi Luo et al.
  • 0271
    Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
    While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the Superposition Linearity Hypothesis. We provide evidence that superposition is an intrinsic property of the Transformer architecture rather than an emergent consequence of training; in fact, we observe that it tends to diminish as pretraining progresses. However, we demonstrate that linearity can be substantially restored through lightweight fine-tuning, significantly reducing the divergence between the predicted next-token distribution and the average of the individual next-token distributions. Finally, we introduce a guided decoding procedure that disentangles superposed outputs, enabling the simultaneous generation of two coherent continuations from a single forward pass.Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk et al.
  • 0339
    The Past Frames the Future: Memory for Autoregressive Video Generation
    Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generated sequence expands, practical models must operate under strictly bounded context windows, storage, and computational limits. Consequently, critical historical information, e.g., entity identities, dynamic states, and intervention-induced causal changes, often leaves the active context long before its relevance diminishes. Overcoming this limitation and maintaining temporal persistence constitutes a fundamental memory problem. We present a systematic and comprehensive review of memory mechanisms in AR video generation. We formulate memory operationally as persistent historical information maintained across outer AR steps, capable of influencing future generation even after the originating evidence is no longer locally accessible. Building upon this unified framework, we organize the literature through five complementary perspectives: (I) Forms, the representational carriers of history; (II) Functions, the specific semantic and physical information requiring preservation; (III) Operations, the lifecycle of writing, reading, updating, managing, and integrating memory; (IV) Learning, the optimization of memory behaviors under closed-loop rollouts; and (V) Evaluation, the paradigms for diagnosing genuine memory capabilities. We conclude by synthesizing open challenges, including composable and resource-aware memory architectures, trustworthy state updating, self-rollout learning, and standardized evaluation. By bridging representations, mechanisms, and learning paradigms, this paper establishes a structured foundation for developing reliable, memory-conditioned video generation systems.Harold Haodong Chen, Rongjin Guo, Disen Lan et al.
  • 0434
    WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
    Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfold across multi-shot sequences. In this paper, we present WanPE, a 397B-parameter prompt enhancement model trained on 1.05M real-world videos to master director-level cinematic planning. WanPE formulates shot-level cinematic plans via video-grounded reverse construction and employs Semantic-Consistency GRPO (SC-GRPO) to faithfully preserve user requirements across shots and over time. To benchmark this capability, we curate WanPEval, a human-annotated testbed covering durations from 5 to 30 seconds across varying intent granularities, supported by approximately 11K blind pairwise assessments. When powering Wan3.0's video generator, WanPE-397B boosts human preference over raw user prompts by 10.66-18.84 points at 5-15 seconds and by a dramatic 50.86 points in the 30-second arena. Ablation studies show that reverse construction demonstrates clear superiority over forward rewriting, while SC-GRPO robustly preserves semantic fidelity across model scales. Ultimately, WanPE leads all evaluated commercial offerings at 5-15 seconds and remains competitive with Seedance 2.5 at 30 seconds.Yubo Zhu, Yawen Shao, Ziyun Dai et al.
  • 0517
    Agent-Editing World Model: Rethinking World Modeling for LLM Agents
    Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existing language world models typically predict environment observations, yet reconstructing high-entropy, execution-dependent tool responses offers limited value when real feedback is available. Meanwhile, agents suffer from task-state contamination, where unsupported assumptions and outdated plans persist in history and distort subsequent decisions. We propose the Agent-Editing World Model (AEWM), which models how reasoning and actions shape future task progress rather than simulating tool responses. AEWM combines Action Judge to distinguish Critical, Exploratory, and Noisy decisions with State Revision to edit noisy reasoning--action continuations from the same observed history. EditAct integrates these capabilities with real execution, directly changing the state underlying subsequent decisions rather than merely providing critiques. We train AEWM across Search, Terminal, and Software Engineering through mid-training and supervised fine-tuning. AEWM achieves 70.5\% macro-F1 on our Action Judge benchmark, exceeding the strongest frontier baseline by 10.6 points. Across six benchmarks and three agent backbones, EditAct improves average scores by 3.2--6.7 points over the strongest baseline. Furthermore, rejection sampling fine-tuning on verified EditAct trajectories, termed AEWM-RFT, improves over Self-RFT by 2.2--2.6 points across three domains without online AEWM guidance.Shuang Sun, Guoxin Chen, Fanzhe Meng et al.
  • 0616
    Foundations of Large Language Models
    This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technologies. The book is structured into six main chapters, each exploring a key area: pre-training, generative models, prompting, alignment, inference, and reasoning. It is intended for college students, professionals, and practitioners in natural language processing and related fields, and can serve as a reference for anyone interested in large language models.Tong Xiao, Jingbo Zhu
  • 0715
    Rufus-Air: An Open LLM Post-Training Recipe
    Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge-based signals. Training builds on open-source components and public data, much of it used as released, without new human annotation or an in-house distillation teacher. Our main findings are that (i) diverse, high-quality SFT establishes a strong capability floor; (ii) difficulty filtering keeps RL prompts within a productive learning range; (iii) reward reliability provides a practical principle for ordering stages; and (iv) infrastructure and engineering choices are part of the recipe, not just an implementation detail. Rufus-Air improves over the official GLM-4.5-Air post-trained release and is competitive with similarly sized open models.Chia-Yuan Chang, Renyuan Cheng, Rui Feng et al.
  • 0810
    Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
    The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI systems? We explore this question by building Qwen-Planner-Agent within a closed-loop AI-for-AI framework for scalable development and iterative improvement. Mobile planning offers a demanding test of this approach: complex, long-horizon tasks challenge agent reliability, while costly real-device interaction limits development scalability. The framework connects data production, model training, and deployment through a shared action-feedback-verification contract. (i) AI for Data builds a human-gated agentic data flywheel in which specialized agents construct tasks, collect interaction trajectories, curate and balance training data, and use training feedback to guide subsequent data generation. (ii) AI for Training combines a supervised planning cold start with hybrid-environment online agentic reinforcement learning, where we introduce Competence-Aware Reward-and-Advantage Engineering (CARE) to reduce reasoning and tool-use costs while preserving task performance. (iii) AI drives model--harness co-evolution through an execution-evidence-driven loop that orchestrates memory, skills, and tools at runtime and feeds structured action feedback and preserved failure traces back into coordinated model and harness adaptation. Qwen-Planner-Agent achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use, memory, skills, and sub-agent coordination. Further evaluations of our model show improvements across non-mobile agentic benchmarks while largely preserving general capabilities.Tingyu Qu, Weigao Sun, Yuecheng Liu et al.
  • 0910
    Parts-of-Speech as Emergent Categories in SAE Latent Space
    Sparse AutoEncoders (SAEs) offer a promising way to inspect language model representations, but it is still unclear what kind of linguistic structure their latents expose. We use part-of-speech (PoS) categories as a controlled test case to study whether morpho-syntactic information is encoded by individual latents or by structured groups of features. We find that PoS distinctions are highly recoverable from SAE activations, but do not align with one-to-one latent / category mappings. This recoverability is not reducible to lexical memorisation, and Open and Closed PoS classes differ substantially. Categories are supported by compact groups of sparse latents, with substantial variation across tags. These groups remain stable on held-out data, while also showing overlap between related categories. Our results show that SAEs localise morpho-syntactic information in a distributed and category-dependent form rather than through atomic grammatical features.Alessandro Bondielli, Lucia Passaro, Serena Auriemma et al.
  • 109
    Coding Agents for Generalized Task and Motion Planning Problems
    Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses this difficulty by exploiting regularities across problem instances to reduce planning effort on new instances. However, existing methods require substantial TAMP-specific engineering. We investigate whether coding agents can automate this process by synthesizing programs that generalize across instances. Given a task description and simulator access, each agent chooses how to interact with the environment while developing a program within a fixed synthesis budget. The program is then frozen and evaluated on unseen instances. We evaluate Claude Code (Opus 5) and Codex (GPT-5.6 Sol and GPT-6 Astra) on 28 simulated environments from KinDER and PDDLStream, with object counts beyond those evaluated in the original benchmark. Across all program synthesis methods, we evaluate 980 generated programs on 100 held-out instances each, 98,000 evaluation episodes in total. Overall, we find that coding agents are surprisingly effective at generalized TAMP: all three agent configurations outperform hand-engineered planners, one-shot generation, and an LLM-based generalized planning baseline in mean success (56% to 95% versus 47% for the planners, on the 16 environments where a planner is available). As object counts grow, the agents' programs maintain higher success than the planner, using an order of magnitude less computation per instance on average. Logs show agents using interaction to calibrate physical models, test edge cases, and refine strategies. We release all code, including the full prompts given to the agents. These findings suggest that coding agents are a strong baseline for generalized TAMP.Matteo Merler, Bowen Li, Josh Roy et al.
  • 119
    ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
    Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the results. However, evaluating this ability is difficult: (1) how to verify whether a genuinely new hypothesis holds, and (2) how to determine whether a system has discovered it through exploration or merely recalled related knowledge from pre-training data. To this end, we introduce ExplorationBench, which turns the wicked problem of evaluating scientific exploration into a concrete and tractable framework built on verifiable Alien Worlds: their rules are executable, so every answer can be checked exactly, and they conflict with familiar knowledge, so recall alone cannot solve the tasks. The benchmark contains two sandboxes, AlienCode (31 discovery targets, 70 tasks) and AlienLogic (24 discovery targets, 70 tasks). Each sandbox provides a flawed manual, task-specific environmental feedback, and a dedicated tool-call schema. Systems use these resources to explore the sandbox, then solve held-out tasks. We evaluate 10 AI systems and find that the strongest systems can acquire and apply unfamiliar rules, while performance varies substantially across trajectories and continued exploration can stall or reverse earlier gains. ExplorationBench represents a step towards AI systems that can acquire and apply genuinely new knowledge through exploration in unknown environments.Ming Zhang, Zhenghao Xiang, Peizhong Gao et al.
  • 129
    IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
    Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based paradigm that alternates between a Planner for identifying information needs and a Synthesizer for integrating evidence into an evolving summary state. This design separates planning from synthesis while using the summary as the persistent state of search, reducing both capability coupling and context noise. To train IterSynth effectively, we further introduce Role-Decoupled Policy Optimization (RDPO) for reinforcement learning, which combines terminal outcome rewards with turn-level rubric evaluations and computes role-specific advantages for more precise credit assignment. Experiments on five long-horizon deep-search benchmarks such as BrowseComp and Xbench-DS show that IterSynth-8B achieves an average score of 50.7, surpassing the strongest prior leq8B agent by +4.2\%. Moreover, IterSynth serves as a model-agnostic prompting paradigm, delivering substantial zero-shot gains over ReAct and similar prompting paradigms on frontier proprietary models.Xingyu Wu, Yuchen Yan, Zhengxi Lu et al.
  • 138
    Learning to Discover Interesting Mathematics
    Recently, Large Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the door to expansion of mathematical knowledge at unprecedented scale. Yet, while LLMs may be able to conjecture and prove more and more theorems, it remains open whether this new mathematical knowledge is interesting or useful. We define intrinsic interestingness of a theorem as the ratio between the length of its proof and the length of its statement. We show that this correlates strongly with an extrinsic measure of the downstream utility of a theorem. We identify the difficulty of a proof conditioned on a set of premises as a useful primitive for computing these metrics, and train a 27B model that predicts proof difficulty more accurately than frontier general-purpose models. Optimizing for our metric creates a model capable of producing more interesting theorems, while also reducing substantial or full overlap with Mathlib from 91.9% to 30.6%, showcasing the creation of more out-of-distribution math. We show that our system can generate candidate theorems, select the most interesting among them, and iteratively build on a self-expanding mathematical library. These metrics provide a practical and quantifiable signal for ranking conjectures and guiding proof search within formal mathematical libraries. Our framework provides a path towards self-expanding, machine-verified mathematical libraries that can choose worthwhile statements without relying on human-supplied targets.Niket Patel, Ahmad Rammal, Amaury Hayat et al.
  • 147
    RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation
    In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassing abundant categories and high-quality annotations. RGBD20K possesses several attractive properties: (1) Expanded Semantic Space. In particular, it covers 160 fine-grained categories, largely surpassing the category diversity of existing popular RGB-D benchmarks (e.g., NYUv2 with 40 classes and SUN RGB-D with 37 classes). With such enriched semantic coverage, we expect to promote the learning of more generalizable segmentation models. (2) Larger Scale. Compared with current benchmarks, RGBD20K offers 20,000 RGB-D image pairs, providing a substantially larger training resource that benefits the development of more powerful deep models. (3) High-Fidelity Annotation. We perform rigorous re-evaluation and correction of existing labels to resolve long-standing annotation noise, resulting in a clean and reliable ground-truth foundation. Furthermore, we propose a novel score-purified fusion (SPF) method, which achieves state-of-the-art performance across all evaluated benchmarks, demonstrating the effectiveness of our approach in leveraging high-quality multimodal information for RGB-D semantic segmentation. The dataset is here: https://github.com/ShaohuaDong2021/RGBD20K/.Shaohua Dong, Zexuan Meng, Haiyan Sun et al.
  • 156
    World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
    General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predict constraints or write programs, or give them a view of the scene rather than a world in which to act. We present World Action Agent (WAA), a multi-agent harness through which VLMs pilot robots with basic tools, making every decision within a visual action workspace. The workspace has three properties. Contact views, selected automatically from the scene geometry, present the scene around the current interaction. Action rehearsal turns each action into an editable proposal that the agent, alone or through an Imagination Agent, previews and revises against planning feedback before execution. In-view correction closes the loop between observation, rehearsal, and low-level execution, letting the agent remove residual offsets in the view where it observes them. Through the same workspace, WAA acquires embodied procedural knowledge in two ways: it evolves multimodal skills from expert videos and human teaching under evidence-based review and consults them through a Skill Agent, and its interaction traces train smaller VLMs to pilot the same harness. On LIBERO-Pro, WAA with skills evolved only from LIBERO-90 reaches a state-of-the-art 75.6% average success, outperforming end-to-end VLAs, code-as-policy agents, and a visual-harness baseline with the same backbone; the same skills remain effective on robosuite without further learning. Fine-tuning Qwen3.5-9B on harness traces raises its out-of-domain success from 1.7% to 43.3%.Yehang Zhang, Haojian Huang, Yifan Chang et al.
  • 166
    On the Diffusibility of High-Dimensional Latents
    Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders. However, many off-the-shelf encoders are not optimized for faithful reconstruction, discarding fine-grained visual details. As expected, finetuning these encoders for image reconstruction recovers such details. However, perhaps counterintuitively, this procedure reduces the effective dimensionality of the resulting representation, and the altered geometry has downstream effects on generation. Specifically, we show that using the standard velocity prediction in flow matching in this high-dimensional space requires the model to fit orthogonal noise directions outside the low-dimensional signal manifold, making optimization inefficient. This motivates using the clean data parameterization (x_{0}-prediction) instead, which focuses learning on the underlying signal manifold. Across experiments with multiple strong-reconstruction encoders, we show that x_{0}-prediction consistently improves text-to-image generation performance.Chao Feng, Zhiyang Xu, Bowei Chen et al.
  • 175
    PUBG Ally: A Conversational Embodied Agent as an AI Teammate
    We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.Beomsoo Kim, Byeongju Kim, Dohyun Kim et al.
  • 185
    Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
    Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement learning for calibrated decisions (RLCD), answers many typed questions about one input with calibrated probabilities in a single call. Whether it detects alignment failures has not been measured. We present RLCDAlignBench, which benchmarks Jev on ten alignment failures: sycophancy, jailbreaks, deception, prompt injection, hallucination, privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking. It spans 44 benchmarks and five target models, labelled by each benchmark's scorer and, on two, by humans. Many of these failures are relational, defined against a reference, such as the user's belief or an injected instruction, that the response alone does not reveal. Our key idea is therefore to vary what Jev is asked separately from what it sees: the question's wording and answer type on one side, the fields of the input on the other. A single generic question reaches a median AUROC of 0.886 zero-shot and beats supervised baselines on most benchmarks. Question wording matters little, while context matters more, mostly through fields that encode the label. Jev matches the reference scorer's agreement with human labels, surfaces label defects in existing benchmarks, and costs 63x less than LLM-judge scorers. Code and data: https://github.com/sumleo/RLCDAlignBench.Ruoqi Guo, Yi Liu, Gelei Deng et al.
  • 194
    AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation
    Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audio-video generation is challenging. Heterogeneous multimodal rewards entangle learning signals and complicate credit assignment. Joint optimization of two modality towers is computationally expensive given their divergent dynamics. Moreover, synchronization evaluation difficulty depends on paired samples, preventing fair reward comparisons. We propose AV-GRPO, a modality-anchored online diffusion RL framework, and 5DAV, a decoupled, difficulty-controllable training dataset. AV-GRPO includes three key modules: (1) modality-anchored rollouts to disentangle learning signals and stabilize difficulty; (2) trajectory-locked frozen-tower optimization to reduce cost and reassign credit; (3) adaptive objectives and perturbation strengths tailored to modality-specific dynamics. This converts coupled multimodal preference learning into unimodal subproblems for precise reward attribution and better synchronization. Our 5DAV dataset decouples samples across five dimensions for systematic training. Experiments on JavisBench and VABench demonstrate AV-GRPO outperforms LTX-2.3 in generation quality, semantic alignment and cross-modal synchronization under LoRA and full fine-tuning. Ablations confirm our designs. Code and data: https://github.com/zhiyuxu03/AV-GRPOZhiyu Xu, Weilong Yan, Yufei Shi et al.
  • 203
    ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
    Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both a large pretrained teacher and an online critic to estimate distributional discrepancies through diffusion scores. In this work, we ask whether this resource-intensive teacher--critic stack can be eliminated by post-training only the generator against a precomputed target distribution. Drawing inspiration from representation distribution matching (RDM) for one-step image generation, we systematically study its transfer to few-step causal video generation and identify three key barriers: a memory-intractable gradient path, a distinct video optimization regime, and representation distributions that underconstrain temporal dynamics. We introduce ViRDM, a teacher- and critic-free video post-training recipe that addresses these barriers sequentially. By coupling RDM with stochastically truncated clean-exit supervision, a lightweight VAE decoder, and staged vector--Jacobian products, ViRDM makes representation distribution matching memory-feasible for multi-step causal video rollouts. We further establish effective generated-population and initialization regimes for video RDM, and introduce lightweight dynamics regularization to compensate for the underconstrained temporal dynamics. ViRDM turns three-network distillation into generator-only post-training, reducing GPU memory use and training time while improving video quality. With only 20 generator updates, the recipe reaches 84.87 on the official VBench evaluation, outperforming the previous best few-step causal baseline by 0.36, while requiring 16 A100 GPU-hours. We additionally report exploratory results demonstrating the potential of the same recipe for lower causal sampling budget and for one-, two-, and four-step bidirectional generation.Zichong Meng, Chongjian Ge, Chun-Hao P. Huang et al.
  • 213
    DeltaWAM: Delta World Action Models for Bimanual Manipulation
    World-action models (WAMs) transfer visual and motion priors from pretrained video generators to robot control by jointly modeling visual dynamics and actions. Existing WAMs, however, predict dense future frames during training, repeatedly modeling largely unchanged content and coupling action-conditioned dynamics to nuisance appearance variations. At inference, processing each complete observation with the heavy video expert bottlenecks few-step action generation. Accordingly, we propose DeltaWAM, which jointly predicts visual deltas and actions using dense-anchor, sparse-delta, and action streams, with three architectures that differ in representation and computation sharing. We further develop Streaming Delta Memory (SDM), which updates cached anchor context with compact observed deltas, reducing heavy video-expert processing. On RoboTwin, DeltaWAM with SDM improves average success over Fast-WAM from 81.3% to 85.4% in the clean setting and from 75.8% to 83.9% under visual randomization. The three architectures reduce training FLOPs by 17.78-23.77%, while SDM reduces one-step inference latency and FLOPs by 36.57% and 31.55%, respectively; real-world evaluations further show the highest overall success rate and normalized progress among the evaluated policies. Code: https://github.com/AIGeeksGroup/DeltaWAM. Website: https://aigeeksgroup.github.io/DeltaWAM.Han Yan, Zishang Xiang, Haokai Jiang et al.
  • 223
    StudentBench: AI and human tutoring yield equivalent GRE learning gains
    Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations and a public platform that enables large-scale data collection with over 175,000 student-AI messages to study whether large language models (LLMs) produce learning gains equivalent to human tutoring. Using StudentBench, we measured learning gains on Quantitative and Verbal GRE questions across 2,383 human participants receiving AI tutoring, human tutoring, or no tutoring. We establish that AI tutoring is statistically equivalent to expert human tutoring for GRE learning gains (p = .015), and in five of the seven GRE domains, the best performing AI tutor surpassed the human tutor, on average. In a second study, expert human tutors compared LLM-generated lesson plans and practice problems through 2,028 pairwise rubric evaluations. Together, the two studies clearly separate AI tutors across: (1) lesson planning, (2) practice-problem creation, (3) conversational pedagogy, (4) cost, and (5) engagement. Surprisingly, one AI tutor achieved learning gains equivalent to human tutoring (p = .044) at 918 times lower cost (USD 0.0052 for AI versus USD 4.81 for human, per percentage point gained). For Quantitative GRE sessions, faster AI replies correlated with more student messages, more messages with more correct practice, and more correct practice with larger learning gains (all p < .002). The StudentBench platform is freely available at https://studentbench.org.Curtis Northcutt, Inaara Hasmani, Kevin Feng et al.
  • 232
    Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates
    Block-based video codecs select coding parameters based on the input by optimizing a rate-distortion trade-off. The conventional distortion choice, the sum of squared errors (SSE), simplifies parameter selection: the SSE is the sum of block-wise SSEs, so rate-distortion optimization (RDO) can treat blocks independently. Alternatively, full-reference image quality assessment (FR-IQA) metrics such as MS-SSIM or LPIPS often align better with the human visual system than SSE, but they cannot be used in-loop: they do not decompose block-wise and typically require the fully decoded image as input. Building on existing results in metric quadratization, we approximate a broad class of FR-IQA metrics by an input-dependent quadratic distortion (IDQD), whose quadratic form matrix is derived from the Hessian of the metric evaluated at the source video. To make the distortion computable block-wise, we propose two approximations of the Hessian matrix: 1) keeping the block-diagonal, and 2) keeping only its diagonal. We propose estimators for both that require only matrix-vector products with the Hessian obtained by automatic differentiation. Across five metrics for Kodak and CLIC in VVC, IDQD-RDO achieves 14.2-36.7 % BD-rate savings under the target metric with no decoder changes and incurs 10-30 % encoding complexity overhead.Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega
  • 242
    LastOPD: Taming Collapse in Latent On-Policy Distillation
    On-policy distillation (OPD) corrects a student on the responses it writes, but its signal is the teacher's next-token distribution: it tells the student what the teacher says but misses how it thinks. Latent supervision promises the missing part by aligning the student's latent states to the teacher's. Recent methods such as OPRD bring this signal into on-policy distillation. However, we observe two failures of this recipe when distilling Qwen3-4B and Qwen3-8B into Qwen3-1.7B-Base. Early gain, late collapse: latent supervision alone lifts MATH-500 accuracy from 25 to 46 in 10 steps, but subsequent training degrades performance down to 11 with no recovery. Better alignment, worse behavior: although the alignment metric steadily improves throughout this collapse, the most aligned model turns out to be the worst performing. Further analysis suggests a mismatch in how the latent signal is applied: layers paired by depth play different roles in the two models, so continued alignment may pull the student toward teacher states it cannot understand. To address this, we propose LastOPD, which applies the latent signal only at the last-layer state, the common interface both LM heads read, and only during a 10-step crossfade into token-level OPD. This keeps the useful part of the latent signal and hands the student to token-level supervision before the collapse sets in. Extensive experiments show that LastOPD improves MATH-500 over token-only OPD by 5.55 and 4.02 points with the 4B and 8B teachers, leads on most held-out datasets, and reaches the final score of token-only OPD in about half the steps. Code is available at https://github.com/Muyiiiii/LastOPD.Jie Yang, Zhengyu Fang, Zelin Xu et al.
  • 251
    Rolling-WAM: World Action Models with Rolling Imagination
    World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness. We present Rolling-WAM, a formulation that distributes joint denoising across successive replanning cycles. Our method maintains a sliding window of video-action chunks at staggered noise levels. At each step, a rolling noise schedule fully denoises the imminent action chunk for execution, while partially refining farther-future chunks. As the window advances with new camera observations, the retained future chunks continue their denoising process. This distributes the computational cost over time while carrying an evolving visual-action context across chunk boundaries. Evaluations on LIBERO, RoboTwin, and a real-world Unitree G1 humanoid show that Rolling-WAM achieves competitive manipulation performance. By removing the need to denoise the entire prediction horizon from scratch, it delivers a 4.5x steady-state replanning speedup over standard joint WAMs.Yinghua Zhou, Junjie Ye, Yiqi Zhao et al.
  • 261
    HEXIS: Compiling Skills into Extended Finite State Machines
    Agent skills provide reusable knowledge and instructions, yet agents must repeatedly infer how to apply them and which operation should follow. This couples task reasoning with control decisions, allowing prescribed steps to be omitted or applied incorrectly. We introduce HEXIS, which compiles agent skills into extended finite state machines that separate knowledge from control flow. Skill knowledge is incorporated into local instructions that guide reasoning and generation within states. The machine records execution progress and intermediate results, while explicit transition conditions determine subsequent operations. Our incremental compiler first maps skill clauses and tool interfaces to state operations, local instructions, data bindings, and transitions. It then aligns development traces with existing states to identify missing operations and dependencies. These are incorporated by adding or reusing states and refining their connections. Updates are accepted only after static checks and replay of the current and all previously accepted traces. Across four benchmarks and four executors, HEXIS improves success over Skill + ReAct by 16.1 percentage points on average. Qwen3.8-27B reduces execution tokens by 38.4-88.9% across benchmarks.Minghao LI
  • 271
    FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates
    Looped Transformers have attracted substantial attention as a parameter-efficient approach to increasing computational depth through repeated application of shared Transformer blocks. However, their practical advantages over conventional Transformers remain under debate: each additional loop incurs another Transformer pass and requires caching another set of KV states, causing inference FLOPs and KV-cache memory to grow continuously with loop depth. This overhead becomes particularly severe at large loop counts and long context, preventing the parameter efficiency of Looped Transformers from translating into practical inference efficiency. In this paper, we find that much of the additional computation and storage introduced by looping is redundant. As recurrence proceeds, state changes become increasingly concentrated on a small subset of tokens; attention-output differences are dominated by a sparse and stable subset of key columns; and KV residuals between adjacent loops become progressively more amenable to low-bit quantization. Building on these observations, we introduce FlashLoop, a training-free inference framework that reduces cross-loop redundancy through token-sparse updates, sparse attention, and KV-residual quantization. Across several Looped Transformers models, FlashLoop delivers lossless accuracy while achieving up to 1.64times end-to-end speedup and up to 6times KV-cache memory reduction, substantially improving the practicality of scaling Looped Transformers to greater computational depths and longer context.Wanqi Yang, Shiwei Liu
  • 281
    IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking
    Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final response misses important errors. An assistant may ask for information it already has, rely on stale context, select the wrong account, or write an invalid value after stating the correct one. We introduce IndicBankBench, a 799-case benchmark for Indian retail banking spanning five operational domains, a capability/refusal domain, and twenty primary axes. Cases are evaluated at four stages: safety, action and tool use, response adequacy, and advisory quality. Tool use and most safety checks are deterministic. A narrow resolver handles only ambiguous confirmation-before-write cases, while a separate LLM judge evaluates semantic response adequacy. We run every case three times and report strict pass^3, which requires success on all trials. Across the eleven evaluated models, strict reliability ranges from 43.7% to 58.2%, whereas at-least-once success ranges from 60% to 74%. This gap shows that at-least-once success can overstate dependable banking behavior. The case-level diagnostics also distinguish systems that ask unnecessary questions from those that act but fail to reconcile customer context or fully resolve the request. We release the cases, mock environment, and evaluation harness.Suvradip Paul, Chandra Bhushan, Harsh Sharma et al.
  • 291
    SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
    Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries. This output heterogeneity presents a structural failure mode in standard on-policy Reinforcement Learning (RL): algorithms like GRPO indiscriminately broadcast a homogeneous trajectory-level scalar advantage to all tokens. Consequently, gradient noise from summary generation leaks into tool-decision tokens, causing cross-segment credit misattribution and brittle optimization. In this work, we propose SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA). To enable scalable exploration without costly real APIs and stable training, we first construct the Schema-Guided LLM Simulator (SGLS) as foundational training infrastructure. Building on this, SLCA decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states. Supported by Hierarchical Rewards (HierR), SLCA routes execution advantages to tool tokens and preference advantages to summary tokens, eliminating advantage contamination (the dominant cross-segment credit misattribution channel) within each policy update. On a 7B backbone, SLCA-GRPO accelerates convergence and outperforms standard GRPO, ToolPO, and RLTR by +2.53 pp on in-domain evaluation, +1.36 pp on the Berkeley Function-Calling Leaderboard (BFCL), and +9.15 pp on τ^2-Bench under the same training budgets, achieving higher accuracy with reduced tool redundancy and costs.Yan Zhan, Shaobo Liu, Qiunan Liu et al.
  • 301
    OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding
    Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, existing methods are restricted to single-sensor domains, i.e., either optical or synthetic aperture radar (SAR), limiting their real-world applicability. In this paper, we introduce the Cross-Domain RSVG (CD-RSVG) task and construct OptSAR-RSVG, the first large-scale benchmark dataset for this setting. To tackle the challenges of cross-domain feature modeling, computational inefficiency, and fine-grained semantic discrimination, we propose OptiSAR-Net++. Our framework features a patch-level Low-Rank Adaptation Mixture of Experts (PL-MoE) for efficient cross-domain feature decoupling. To mitigate the substantial computational overhead of Transformer decoding frameworks, we adopt a CLIP-based contrastive paradigm and further incorporate dynamic adversarial negative sampling, thereby transforming generative regression into an efficient cross-modal matching process. Additionally, a text-guided dual-gate fusion module (TGDF-SSA) and a region-aware auxiliary head are introduced to enhance semantic-visual alignment and spatial modeling. Extensive experiments demonstrate that OptiSAR-Net++ achieves SOTA performance on both OptSAR-RSVG and DIOR-RSVG benchmarks, offering significant advantages in localization accuracy and efficiency. The model and dataset have been made publicly available at https://github.com/JunDong-dev/OptiSAR-Net-PlusPlus.Xiaoyu Tang, Jun Dong, Jintao Cheng et al.
  • 311
    Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following
    Fine-tuning large language models on parallel data improves translation quality but can cause catastrophic forgetting. Mitigation methods are generally evaluated by retention on general benchmarks. We ask whether these findings transfer to machine translation (MT) fine-tuning and to MT-specific instruction following (MT-IF): instructions that modify a translation, such as formality, grammatical gender, and length control. We compare methods anchored to auxiliary data, to model outputs, and to the base model parameters, first in a screening study with Llama 3.2 1B Instruct, then on Llama 3.1 8B Instruct fine-tuned on bidirectional Arabic-English or Spanish-English data. Elastic Weight Consolidation preserves general capabilities best in both stages; on the 8B Spanish model the average score on general benchmarks drops 1.7 points versus 11.0 for standard fine-tuning, yet its scores for formality and grammatical gender control remain close to standard fine-tuning. Only data mixing with control-task examples preserves these controls, but its gains do not transfer to unseen prompts for the same task.Niklas Scholz, David Thulke, Abdallah Nasir et al.
  • 32
    LLM Agents Can Easily Tamper With Their Own Traces
    Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary. All tested harnesses, except Muse Code, allowed agents to delete their traces when asked, without triggering monitor guardrails. We also validate that external attackers can exploit this gap to induce trace deletion. Finally, we show that trace tampering behavior emerges naturally in frontier models, when agents try to improve their rewards. We advise practitioners to ensure trace logging happens through an independent interception mechanism outside of the agent's control, preserving trace integrity even in cases of full host compromise. Overall, our findings identify a concrete failure of trace integrity in agent infrastructure which can be used to conceal misaligned behaviors like scheming or sabotage.Jeremy Qin, David Schmotz, Derck Prinzhorn et al.
  • 33
    SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
    Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure Analysis (SCA) as a theoretical lens characterizing how branching structures and sparse rewards induce these biases in long-horizon reasoning with local admissibility, and as a design principle for structural priors in less formal reasoning tasks. Motivated by this analysis, we propose SAGE (Structural Admissibility-Guided Exploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horizon reasoning. SAGE combines two complementary structural guidance: algebraic sparsification, which projects locally admissible candidates onto operator-indexed algebraic subspaces to suppress spurious branching and mitigate exploration bias, and hyperbolic structural guidance, which embeds reasoning states into a negatively curved space to provide dense depth-wise signals and mitigate compounding bias. Across 12 benchmarks and 7 model families, SAGE outperforms competitive baselines. In particular, SAGE achieves up to an 8-fold improvement on the Andrews-Curtis problem, an open real-world long-horizon task. Code is available at: https://github.com/Susan571/SAGE-NeurIPS2026.Xinyue Zeng, Jiawei Zhang, Yujun Yan et al.
  • 34
    Ego-Exo4D Human Meshes Dataset: 4D Human Motion Reconstruction for Ego-Exo Captures
    Ego-Exo4D is a large-scale dataset providing synchronized egocentric and multi-view exocentric video, a rich resource for skill learning and assessment, procedural activity understanding, and embodied AI. However, the dataset ships with only sparse 3D human pose annotations, and reconstructing dense human motion from its multi-view captures is nontrivial. To this end, we present Ego-Exo4D-HM, a large-scale dataset of 4D human motion reconstructions for Ego-Exo4D's captures, and release the accompanying reconstruction pipeline. The code, dataset, and documentation can be found at https://abhiram824.github.io/egoexo4d_human_meshes.Abhiram Maddukuri, Georgios Pavlakos
  • 35
    TEMA: Evidence-Grounded Temporal Question Answering in Multi-Turn Multi-Audio Dialogs
    Multi-turn, multi-audio temporal question answering requires models to track target events across follow-up questions, recording switches, and historical references, recovering complete instances and their boundaries for temporal calculation and comparison. We propose TEMA, which connects event perception with evidence-based answering through Route, specifying the audio scope, and Span, describing all relevant intervals as conditional audio captions. We construct TEMA-Dialog with 40,704 dialogs and per-turn evidence and answer supervision, and TEMA-Bench for joint evaluation of evidence and final answers. Training combines temporal grounding initialization, full-dialog supervised fine-tuning, and completeness-first Span-only GRPO. Experiments on Qwen2.5-Omni and AF-Next show improved temporal question answering, particularly event localization and cross-audio comparison. Reinforcement learning applied solely to evidence further improves interval recovery and answer accuracy.Kaidi Yang, Hualei Wang, Zhaohui Wang et al.
  • 36
    Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark
    Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health record (EHR) data cannot be openly shared due to privacy, ethics or data use issues and it does not contain verifiable ground truth since the chart records only reflect what clinicians documented. We introduce Synthetic Hospital, an open, fully synthetic, fact-grounded longitudinal EHR benchmark that resolves the open sharing and verifiable ground truth barriers. Built entirely from public medical-education material with no protected health information, it comprises 1,268 longitudinal patients and 5,602 encounters, where every diagnosis, finding, and temporal relation is grounded in standard ontologies (ICD-10-CM, SNOMED CT, LOINC) and with a complete provenance chain back to its source medical education material. Synthetic Hospital is served through a simulated hospital record system that mirrors real EHR infrastructure (standard interoperability APIs, role-based access and function-calling interface). In a blinded review, physicians distinguished its records from real patient charts at near-chance rates (53\%). Across 10 frontier and open models, none approaches ceiling: the best model reconstructs a patient's longitudinal problem list with a severity-weighted F1 of 0.73, level with the mean of seven physicians on a matched subset but well below the best of them (0.89), and misses roughly half of clinically relevant findings when summarizing a chart. Overall, these results highlight that Synthetic Hospital is a difficult and realistic test of clinical AI performance.Christine Park, Valerie Chen, Tim Dettmers
  • 37
    TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
    We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning from one side, continuous-signal perception and zero-shot forecasting from the other, and fuses the two in a shared representation space where both modalities are understood and generated. We study the design choices that make such unified modeling work: where to align the two representation spaces, how to ground language in temporal structure, how to balance understanding with generation, and how to keep joint optimization stable. The resulting recipe combines a unified prompting scheme for diverse time-series and text tasks, stabilized joint training, and supervision from 2.2M curated series--text pairs and 4.9M instruction-tuning samples. Across benchmarks spanning time-series perception, understanding, reasoning, and both context-aided and unimodal forecasting, TimeBraid remains competitive with far larger general-purpose models and task-specific counterparts.Xinyue Wang, Jiacheng Pang, Kun Zhou et al.
  • 38
    CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
    Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge ---i.e., the algorithms they implement, the paradigms they follow, the patterns they instantiate, and the application domains they serve--- remains challenging, as current tools are constrained to syntactic and token-level analysis. We present a pipeline for building an open-taxonomy semantic annotation of source code using a code-specialised Large Language Model. The extracted entities are grounded in Wikidata through a three-stage linking procedure: a deterministic SPARQL stage handles unambiguous entities, a Deep Research Agent resolves the residual long tail, and a hierarchy-rollup stage imports the parent-of closure of each resolved Wikidata identifier. The resulting annotations are materialised as a source-code-specific open-taxonomy knowledge graph. We further introduce a calibrated quality-assurance protocol that quantifies annotation precision by combining a small human gold set with an LLM-as-a-judge filter. We applied our pipeline to the 167 million files of the Stack-Edu corpus, creating the first known large-scale open-taxonomy knowledge graph for source code. Our graph, named CodeGraph, contains approximately 158 million nodes, which include around 145 million files, about 63,000 extracted concept entities (such as algorithms, paradigms, design patterns, and application domains), and roughly 19,800 grounded Wikidata entities. Furthermore, CodeGraph features approximately 1 billion typed edges that connect files to their respective concepts, link these concepts to their grounded Wikidata identifiers, and relate them to their parent categories, covering 14 programming languages.Federico Pennino, Andrea Gurioli, Stefano Zacchiroli et al.
  • 39
    Controlling Backchannels in Streamable Full-duplex Models
    Backchannels, brief acknowledgements like "uh-huh" produced while the other party may still be talking, are central to natural conversation, but full-duplex spoken dialogue models rarely model them explicitly. We introduce a lightweight backchannel head that predicts, from a full-duplex model's own hidden states, when a backchannel should begin. Once this probability crosses a tunable threshold, a backchannel is force-decoded. Attached to both a 7B (PersonaPlex) and a 1B (F-Actor) model, it generalizes across scale. Probing confirms the hidden states anticipate real human timing, and generation evaluation shows more frequent, better-timed backchannels. Human raters judge the resulting backchannels on par with real ones.Maike Züfle, Peter Polák, Sefik Emre Eskimez et al.
  • 40
    Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams
    One long-form exam in a large course costs hundreds of grader-hours, and qualified graders are scarce; LLM graders are a tempting alternative. To show its pitfalls we grade a practical Computer Vision exam (570 dual-graded students) under 171 configurations spanning closed and open-weights models; the best reaches mean absolute error 1.64/35, below the 2.61/35 two human graders achieve against each other. The catch is the prompt: a short ''strict grader'' preamble drives 14 of 17 open-weights models out of the graded band (MAE ge 8), three stopping grading altogether. The damage traces to the preamble's two credit-withholding sentences, not to tone or model scale; one of them, ''never give partial credit'', alone makes two of three probed models stop grading. The closed flagships of three vendors shift calibration under it but stay in the band. In 162 further configurations on a second, independent Machine Learning exam from another course (1{,}038 dual-graded students), the preamble worsens ten models, moving three out of the band into collapse and one into refusal, yet improves seven whose neutral prompts over-mark: the vulnerability replicates, but its direction is exam-specific. Light LoRA fine-tuning repairs it: one adapter on the two exams' pooled sim 3{,}900 graded examples brings five small open models to parity or better with a human grader in agreement with the grader pair, and sensitivity to the three harsh personas nearly vanishes (le 0.32 MAE). We release the anonymised dataset, full ablation grid, and grading, fine-tuning and analysis pipelines.Ali Habibullah, Yazan Alshoibi, Mohammad Alshiekh et al.
  • 41
    Representation World Model: Learning States, Transition and Executable Plans in Representation
    We propose the Representation World Model (RWM), which learns states, transitions, and executable plans directly in representation space. Unlike existing world models that typically learn latent representations together with explicit dynamics models and perform planning through search, optimization, or policy-based prediction, RWM directly incorporates planning into the learned representation geometry. RWM learns the representation geometry by applying inverse-dynamics supervision locally along latent paths constructed from endpoint representations, requiring these paths to preserve task-relevant state and transition information. At inference, planning is performed by directly constructing a latent path between the current and goal representations, with inverse dynamics used to recover the corresponding actions, without recursive rollouts or action-space search. Experiments on continuous-control benchmarks demonstrate the effectiveness of RWM for direct planning, while results on robotic manipulation further show its potential to extend to more complex embodied control tasks. These results suggest that planning directly in representation space provides a promising alternative to conventional world-model planning.Yijun Yuan, Weicheng Zheng, Weibang Wang et al.
  • 42
    UpDown-SC: Gravity-Canonicalized Dual-Envelope Scan Context for Indoor LiDAR Place Recognition
    LiDAR place recognition is a key front end for loop closure and global relocalization, yet indoor retrieval remains difficult when attitude or sensor mounting height changes between mapping and query sessions. Scan Context stores the maximum height in each polar cell; indoors, broad ceilings can suppress the lower and mid-level geometry that distinguishes adjacent rooms and corridors. We present UpDown-SC, a training-free polar descriptor that first canonicalizes gravity and then represents two complementary surfaces: the upper envelope of lower/middle structures and the lower envelope of overhead structures. Their physical split is estimated once from a cell-balanced map height distribution and reused by every query. A mask-aware, non-uniform two-channel distance retains discriminative lower-level evidence while limiting sensitivity to its cross-session variation, without treating unobserved cells as zero-height measurements. Conventional Scan Context shortlisting and circular yaw alignment are retained, so retrieved hypotheses directly initialize geometric verification. Experiments across repeated indoor sessions, mounting-height changes, mixed outdoor-to-indoor trajectories, and an outdoor transfer sequence show more reliable first-choice retrieval on the indoor and mounting-height-varied sessions. A paired test finds a significant gain over Scan Context on the in-house sessions. UpDown-SC also gives the best or second-best F1max and AUPR under threshold-based acceptance while retaining a lightweight CPU front end. Continuous replay confirms that the retrieved hypotheses support metric prior-map localization. Code and evaluation artifacts: https://github.com/jiejie567/updown-sc.Jie Xu, Yongxin Yang, Ziyi Jin et al.
  • 43
    BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization
    We introduce BranchShine-CR, a 25M-parameter model for multilingual transcription into the International Phonetic Alphabet (IPA). It combines log-mel features, a rotary-position E-Branchformer encoder, intermediate self-conditioned connectionist temporal classification (CTC), and consistency regularization across augmented views. On 16,646 shared IPApack++ test utterances, it achieves 4.47% IPA character error rate, a 22.3% relative reduction from ZIPA-CTC-NS, with approximately one-twelfth as many parameters while being trained from scratch. BranchShine-CR also outperforms a similarly sized NeMo Conformer baseline across all 41 dataset language labels. Ablation studies indicate the individual components synergetically acting in model performance contribution. These findings support compact IPA recognition capabilities under limited compute budget, for applications in low-resource on-device pronunciation assessment.Nikhil Navas, Sergio Chevtchenko, Talisson Damiao et al.
  • 44
    Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models
    Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trains compact ALMs by supervising student-generated responses with teacher predictions, but does not explicitly distinguish acoustic support from linguistic predictability. We propose Reward-Tilted On-Policy Distillation (RT-OPD) to strengthen acoustic grounding. Given the same question and student-generated text, a frozen teacher predicts the next token with and without audio inputs. Their log-probability contrast defines a reward that reshapes the teacher distribution for reverse-KL distillation, emphasizing the additional evidence provided by audio. Across two compact students and three benchmarks, RT-OPD consistently outperforms Vanilla OPD. Experiments with silenced and replacement audio further suggest that RT-OPD strengthens the student's reliance on acoustic evidence. Our 3B model achieves 72.72% accuracy on MMAU, the highest among the compared 3B models and competitive with several 7B and 8B models. Code and model checkpoints are available at https://github.com/KaiyangLi1992/RT-OPD.Kaiyang Li, Shaobo Han, Yue Tian et al.
  • 45
    Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?
    Self-supervised learning (SSL) countermeasures (CMs) have shown strong performance in recent years. However, they often show degraded performance while facing unseen spoofing attacks and mismatched conditions. This study examines the Voxtral audio-language model (ALM) framework for spoofing detection, as a step toward combining CM capabilities within the ALM framework. We analyze how Voxtral captures spoofing cues through audio-text processing and propose an instruction-guided approach that uses label-sequence likelihoods to evaluate bonafide and spoofed speech. Experiments on the ASVspoof databases show that without task-specific adaptation, the LLM layers emphasize semantic representations, reducing the separability of spoof-discriminative acoustic cues compared to the Whisper-based audio encoder. Consequently, spoofing-related information becomes less separable after language-model processing. We also applied lightweight adaptation using weight-decomposed low-rank adaptation (DoRA) to the Voxtral model and propose the Spooftral model, achieving an equal error rate (EER) of 4.25% on the ASVspoof5 evaluation set.Avishai Weizman, Yehuda Ben-Shimol, Itshak Lapidot
  • 46
    Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy
    Human hand-object interactions (HOIs) provide a rich source of demonstrations for dexterous manipulation, but learning directly from them presents challenges in bridging morphology gaps, ensuring dynamical feasibility, and sim-to-real deployment. We present Morphometric Imitation, a three-stage framework that transforms reconstructed HOIs into zero-shot sim-to-real visuomotor policies. First, morphometric optimization (MMO) kinematically retargets human motion across hand morphologies while preserving demonstrated contacts. Second, residual reinforcement learning (RL) refines the kinematic reference using object pose and contact information from the human motion to produce dynamically feasible robot demonstrations. Third, these demonstrations are distilled into visuomotor policies. Across three robot hands and ten HOIs, MMO improves contact F1 over the strongest of five baselines by at least 8 points for every hand, while also improving the success rate of downstream dynamic retargeting by as much as 35 points. Ablations on the residual RL show complementary benefits from using object pose and contact information. Finally, the visuomotor policies achieve 89.3% zero-shot success in 300 real-world trials on 30 objects. Project page: https://morphometricimitation.github.io{this https URL}Tara Sadjadpour, Siming He, C. K. Wolfe et al.
  • 47
    Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
    Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback double the mean highest attacker-target probability found during optimization, while success on fresh validation calls rises from 1.8% to 3.5%. Exploratory analysis links these successes to small initial decision margins or greater attacker control over the observation. Together, these findings show that schema-defined outputs change but do not eliminate prompt-injection risk, highlighting the need to evaluate how untrusted content influences choices within the allowed action set.Tiantong Wu, Wei Yang Bryan Lim
  • 48
    LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion
    Dexterous manipulation demands long-term foresight and rapid reactive control. Vision-Language-Action (VLA) models, while proficient in high-level reasoning, often lack a fine-grained understanding of physical dynamics and spatial perception. Conversely, World-Action Models (WAMs) typically suffer from high inference latency due to iterative generation. These deficiencies result in a critical temporal misalignment where the model's intent fails to adapt to rapid physical contact changes. To overcome this fundamental bottleneck, we propose LiMA, an asynchronous dual-system generative framework that systematically decouples intent planning from reactive execution. LiMA organizes computation into a multi-scale hierarchy: a slow system handles sparse long-horizon spatiotemporal intent generation, while a fast system focuses on dense high-frequency motion refinement. To align sparse intent predictions with dense action trajectories, we introduce a Latent Schrödinger Bridge Coupling mechanism that formulates refinement as an entropy-regularized probabilistic transport process. LiMA reduces inference latency by 45.8% compared with Cosmos-Policy via asynchronous decoupling. Evaluated across six bimanual dexterous manipulation tasks spanning multiple horizons, LiMA achieves an overall success rate of 70.8% and an average subtask success rate of 78.9%, while maintaining performance in unseen scenarios. The project website is available at https://ccdcs.github.io/LiMA_repo/Ning Chen, Yankai Fu, Junkai Zhao et al.
  • 49
    Memory Attention
    Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We investigate whether token-indexed memory can replace the dedicated value projection when complemented by contextual information. We propose Memory Attention (MA), which forms values by combining layer-specific token memory with contextual keys. The memory supplies token-specific representations, while the keys preserve context dependence. At inference, normalization can be folded into the memory tables, reducing value construction to lookup and addition. Token-indexed retrieval also enables CPU offloading with prefetching, reducing GPU parameter storage. Under matched training token budgets and with additional memory parameters, experiments across attention configurations show improved language modeling and average downstream performance.Jiale Kang
  • 50
    Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control
    Pretrained generative Diffusion Transformers (DiTs) capture rich pixel-level visual and language-conditioned structure through large-scale image and video generation training. A growing line of robot policies builds on this generative prior, but how it should be transferred to control remains unclear, and existing approaches commonly instantiate this transfer through future visual prediction. We ask a more basic question: what a pretrained generative DiT actually contributes to action learning, and how this prior should be adapted for control. We introduce NowWAM, a future-target-free co-training formulation that denoises the current observation and predicts robot actions from the same visual stream, directly coupling the native generative objective to the action-facing representation across the denoising trajectory. Under matched controlled settings, past and future visual targets perform comparably, while restricting training to the clean endpoint substantially reduces robustness, suggesting that a separate future target is not essential for generative adaptation, while the denoising trajectory remains an effective interface for control. On LIBERO-Plus, NowWAM reaches 87.7% with FLUX2-Klein, improving over the future-target co-training baseline by 6.1 points while halving training visual tokens (784 to 392) and reducing step time from 2.85 s to 1.63 s, a 1.8x speedup. With the pure text-to-image Z-Image backbone, NowWAM further reaches 87.8%, showing that strong control adaptation is not tied to video generation or image-editing backbones.Zanyi Wang, Yuheng Lei, Dengyang Jiang et al.
共 50 条热搜查看完整榜单
共 50 条热搜查看完整榜单
共 30 条热搜查看完整榜单

OEIS · 精选数列

2小时前更新
共 10 条热搜查看完整榜单
  • 012203
    偏跟山过不去
    在英国生活20 年后，比尔·布莱森回到美国，决心徒步穿越全球最长的原始山径——阿巴拉契亚小道，重新认识美国。他带上干粮，背上行囊，走进山林时，才发现这次旅程的艰险程度远远超过了他的想象。森林里有响尾蛇、水蝮蛇和成群的铜斑蛇，有短尾猫、熊、郊狼以及野猪，还有被大量的劣质玉米烧酒害得疯疯癫癫的乡下人，染上狂犬病的黄鼠狼。 虽然布莱森有老友卡茨相伴，但这个身材发福、胃口奇大无比的中年男人，真的能与他共渡难关？ 夺人心魄的阿巴拉契亚小道沿途景色，一路上遇到的各种险境和形形色色的有趣人物，当地历史风情和美国人现实生活的全新场景，都由作者用一支生花妙笔娓娓道来，展示出一个千百万人不知道的美国。[英]比尔·布莱森
  • 023894
    我是个算命先生（李现、李一桐主演影视剧《我不是大师》原著）
    李现、李一桐主演影视剧《我不是大师》原著 算命先生的最高境界，不是算天，而是算人。 民国年间，江湖上活跃着一个隐秘群体--江相派。他们以“算命先生”自居，却恣行诈骗之术。 从军统特务、土匪头子，到书香人家、深宅妇孺，都逃不过他们的局! 他们看的是面相，算的是人心，捕捉的是人脸上不断闪烁的欲望。 狐仙上身、阴魂换命、赶尸招魂......骇人听闻的玄学奇案背后，暗藏着精心设计的敛财流水线。 “英耀”骗术、“扎飞”技法、“鲁班门”法术......绝不外传的江湖秘本，是拿捏人性的行骗心理学。 翻开本书，看顶级老江湖如何谋局、做局、破局! 看懂了这些局，你便看懂了人心!易之
  • 031.4万
    遥远的救世主（《天道》影视原著）
    穷人改命顶级阳谋，现象级神剧《天道》原著！ 认知决定命运，改命不必拼命！一段灵魂共鸣的智性爱恋、一场算无遗策的商海博弈、一个证道文化属性的社会实验。 突然解散私募基金、放弃巨额利润的商界“怪才”丁元英孑然一身，隐居避世，这位传统文化的叛逆者，与古城女警芮小丹不期而遇。俗世的高人与“天国的女儿”双双坠入一场灵魂交响的智性爱恋。 芮小丹不滞于物、不昧因果，只向丁元英要一件礼物——一个扶贫神话。 当“弱势文化”的牺牲品、“务实文化”的代表、“强势文化”的赢家、“觉悟文化”的化身齐聚一堂，不同认知的众人将走向怎样不同的命运？ 弱者扒着井沿看一眼世界又掉回去，不是运气差，是认知配不上机遇； 强者改命逆袭，不是手段高，是对规律的敬畏和对自己下刀子的狠劲。 可杀富济贫，真的能救贫吗？大爱无爱，是否有违天道？ 翻开这本触及灵魂和人性的觉醒之书，探索强势文化改命的秘密。豆豆
  • 04492
    夜航西飞
    有了《小王子》作者圣埃克絮佩里的催促，才有了这本不断再版的传世佳作。 这是作者柏瑞尔·马卡姆三十年非洲生活的回忆录，展现了这位非凡女性从童年至一九三六年的传奇人生：养马、驯马、猎狮、捕象、开飞机，并成为独自驾机飞越大西洋的首位飞行员。本书是由三十年非洲岁月片段串联起来的回忆，讲述了传奇女性柏瑞尔·马卡姆从童年到一九三六年的人生经历。她热衷于训练赛马和驾驶飞机。 书中有她在非洲度过的童年、参与狩猎的情景、与当地土著的情谊、训练赛马的过程，以及独自驾驶单翼双座木螺旋桨飞机，在东部非洲从事职业飞行并猎队搜寻大象踪迹的往事；还详细描述了她从非洲驾机回英国沿途所遭遇到的政治与自然险阻；最后更记录了她在一九三六年九月独自驾机从英国飞越大西洋直抵北美的经过。[英]柏瑞尔·马卡姆
  • 055122
    第一性原理：普通人的人生高效手册
    为什么你明明很努力，却始终感觉在原地踏步？ 大多数人终其一生，都在用“类比思维”过日子。别人怎么做，我就怎么做；过去怎么做，现在还怎么做。这种思维方式省力、安全，但也给你设了一道无形的天花板。 这本书要做的，就是把第一性原理从哲学家和企业家的书斋里，搬到你的日常生活中。 什么是第一性原理？简单说就是：把问题一层层剥开，直到看到最核心的基本事实，然后从那里出发，重新构建解决方案。小到今晚吃什么，大到人生方向怎么选，都可以用。 书里给出了一整套可操作的工具箱：四种拆解方法（连续追问、成本拆解、假设审查、类比消除）和四种重构方法（约束反推、极端假设、要素重组、验证回路）。并用SpaceX、香农信息论、Costco、指数基金、费曼学习法五个跨领域案例，完整演示了这套方法如何在真实世界中发挥作用。 读完这本书，你会获得一种能力：不再被别人的经验绑架、不再被过去的自己束缚。 你会学会如何拆掉思维里的那堵墙，看到问题真正的样子。武从文
  • 06253
    前世今生：穿越时空的疗愈
    你是否曾对生活中的某些片段感到莫名熟悉，仿佛它们是灵魂深处的印记？ 你是否对生命中的奇妙现象满怀疑惑，迫切地想要探寻其背后的奥秘？ 你是否内心深处正承受着痛苦，渴望找到那条真正的自我救赎之路？ 你是否在某些恍惚的瞬间，仿佛穿越时空界限，窥见了前世的影子？ 你是否渴望疗愈心灵深处的创伤，让那颗疲惫的心从此归于宁静？ 布莱恩·魏斯博士用其独特的前世回溯疗法，揭示了我们隐藏在潜意识深处的记忆碎片。这些记忆不仅承载着过去的创伤，更蕴含着神奇的疗愈与成长的力量。 你将见证无数生命如何在前世的纠葛与今生的重逢中获得救赎，以及如何步入生命的更高维度，在灵魂深处实现创伤的自我疗愈！[美]布莱恩·魏斯
  • 074618
    天幕红尘（《遥远的救世主》姊妹篇）
    跳出认知陷阱，逆转人生困局！从谋于术，到观于道，最后行于势——豆豆三部曲收官之作，继《遥远的救世主》后重磅政治小说！ 复制别人的路，永远走不出自己的命！高手从来都是看透规律、顺势而为。 苏联解体时代剧变，石油商人罗家明因投资失利，背负105万美元巨债绝望自尽。蜗居柏林，东西方世界的边缘人、马克思主义哲学的信奉者叶子农，因一句“见路不走”的箴言以身入局，直面旁人无解的债务死局。 他不循世俗老路、不照搬固有经验，立足现实精准破题，以跨国劳务输出盘活危机，完美诠释核心智慧：见路不走。 所谓“见路”，是盲从经验的致命陷阱；“不走”，是实事求是的通透抉择。 不懂规律，努力只是原地踏步；脱离现实，选择皆是豪赌。 可同样信奉“见路不走”，为何有人惨败落幕，有人顺势翻盘？ 普通人又如何真正吃透“见路不走”，活出自成一派的人生？ 翻开本书，参透顶级认知思维，拿回人生主动权！豆豆
  • 08339
    前世今生：穿越时空的灵魂伴侣
    你是否曾对某个陌生人涌起莫名的熟悉与好感？ 你是否做过一些说不清的梦或有过奇妙的直觉？ 你是否曾爱过又失去了某个人？ 你是否听到过自己内心深处对真爱的呼唤？ 到底是什么力量让爱能穿越时间和空间，永恒不变？ 你知道吗？真爱的秘密就藏在你的前世里。 佩德罗与伊丽莎白，两个原本陌生的男女，被命运的细线悄悄相连，在今生重逢，却浑然不知他们已在无数前世中紧紧相拥，爱恋延续了万年。 布莱恩·魏斯博士用他那令人震撼的前世回溯疗法，带领我们踏上了一场寻找灵魂伴侣的神奇旅程，并向我们揭示了一个深刻的真理：在这广袤无垠的宇宙中，我们每个人都有一个独一无二的灵魂伴侣。在无数次的轮回中，我们始终与TA深爱着彼此。而此刻，这个灵魂伴侣正静静地等待着与我们再次相遇……布莱恩·魏斯
  • 093633
    背叛（《天道》原著作者豆豆开山之作）
    普通人乱世立身的终极法则，《天道》原著作者豆豆开山之作！ 一段世纪之交的个人生命史，一部时代浪潮中的灵魂忏悔录！ 一次受人所托的探监，聪颖果决的记者夏英杰“慧眼识穷途”，爱上了入狱避祸的宋一坤。为了这段不被世人理解的感情，宋一坤随她避居海岛，从一本小说、一个商机起手，悄然撬动一场千万级商业风暴。 他出身贫寒，却有看透机会的洞察与绝处逢生的胆识； 她家境优渥，却不为名利所惑，只愿追随内心。 一个靠天才与谋略织就财富迷局，一个为爱奔赴、为信念坚守底线。 可当境外资本步步围猎，利益、友情、爱情与国有资产被同时推上赌桌，他们必须作出最残酷的选择。 是追逐利益，还是坚守正义？ 是信奉弱肉强食，还是守住为人的底线？ 翻开本书，见证一场义与利交织的惊心博弈，看良知如何照亮命运！豆豆
  • 10725
    马可瓦尔多（卡尔维诺作品）
    马可瓦尔多是位城市小工。他有一双敏锐善感的眼睛，时刻捕捉着四季的变化和都市的隐秘。春天花坛里冒出来的蘑菇，秋天城市上空的候鸟，都能让他那灰色贫乏的世界变得多彩肥沃。对他来说，“生命中除了以小时计酬的薪水、额外的工资补助和家庭津贴外，还有某些东西可以期待。”伊塔洛·卡尔维诺
  • 111109
    投资中最简单的事（全新升级版）
    投资本身是一件很复杂的事，我们是否可以化繁为简、直接追问什么才是投资的本质？有没有一些简单可行的法则和工具能够让我们直接触及投资的本质？ 《投资中最简单的事》（更新版）为读者呈现的正是符合投资的内核和本质的、与时俱进的普适性规律，这些规律不会因为时间的流逝而有所淡化，相反，自本书第一版面世5年来，这些规律经过了时间的检验和市场的充分验证，更新版不仅在第一版的基础上新增了作者当下的思考，还对于那些反复被证明有效的规律进行了拓展和完善。高毅资产董事长邱国鹭从多年投资的自身经验出发，剖析了“便宜才是硬道理”“定价权是核心竞争力”“人弃我取，逆向投资”“投资应该数月亮，胜而后求战”等简单易行的投资原则，阐明了“对于大多数人而言，只有价值投资才是真正可学、可用、可掌握的”这一观点，分享了易于普通投资者学习、操作的投资方法。在对“投资中最简单的事”娓娓道来的过程中，作者用生动晓畅的语言分享了自己投资生涯中的丰富投资实例，使本书兼具了易读性与实操性。邱国鹭
  • 12562
    远东冰原上的猫头鹰
    当乔纳森·斯拉特还是个观鸟新手时，他偶然遇到了地球上颇为神秘的一种鸟类，它比他所知的任何一只猫头鹰都大，看上去就像一只长着羽毛的小熊。他拍下一张照片，并分享给专家，这便是世界上体形硕大的猫头鹰——毛腿渔鸮。随后，斯拉特开始了为期五年的调研之旅，在俄罗斯东部茂密偏远的森林中寻找这种巨大而神秘的生物。 尽管毛腿渔鸮的翼展长度达6英尺，身高也超过2英尺，但它们总是神出鬼没，人类对其所知甚少，可供参考的资料也极为有限。它们在冬天最容易被发现，因为它们在觅食过程中会在雪域河岸上留下大而独特的足迹。毛腿渔鸮同时也是濒危物种。因此，斯拉特和他的团队开始着手捕获这种猫头鹰以做研究，并尝试据此制定出一个保护计划，以帮助这一物种存活下去。为了完成任务，他们不得不应对各种挑战：在冰冷的帐篷里通宵监测，疯狂地驶过将融的冰河，毫无防护地爬上朽烂的树木以检查巢穴中珍贵的渔鸮卵。为捕捉和追踪渔鸮，他们使用尖端的定位设备，亦即兴设计巧妙的陷阱，还必须始终警惕与熊或东北虎发生冲突。在斯拉特异常生动、精确，同时不失幽默的叙述下，毛腿渔鸮渐渐展露真容：它们是狡猾的猎人，忠诚的父母，怪异的“二重唱夫妇”，是不擅记仇且相对温顺的猛禽，也是在条件严酷、面积不断缩小的栖息地上顽强生存的珍稀物种。 除此之外，斯拉特还以令人捧腹的笔调描写了生活在俄罗斯边疆区域的各色人物：有似乎永远也不清醒、以伏特加为粮的嗜酒村民，有与黑帮交易失败后逃命至荒野的古怪隐居者，有为了可以卖10美元的貂皮而猎杀毛腿渔鸮作肉饵的无知少年……对于沿途经过或停驻的大小城市、村庄，斯拉特亦不吝啬笔墨，关注这些地方的历史，以及它们在苏联集体经济时期的发展和如今的没落。 斯拉特以一份惊心动魄的田野笔记，向读者全面展现了这片远东冰原上的生灵、人类、居住地、自然景观及文化风貌。乔纳森·斯拉特
  • 131341
    万历十五年
    《万历十五年》是历史学家黄仁宇的成名作和代表作，也是“大历史观”的开山之作，被无数读者誉为历史启蒙必读的“神作”，曾改变了一代人的阅读与思维方式。它不仅是一部明史著作，更是一套全新的思维方式：教读者跳出故事，看懂结构；跳出情绪，看懂制度；跳出一时得失，看懂长期大势。 公元1587年，大明万历十五年，表面平静无波，实则是帝国走向崩溃的关键转折点。 这一年，西班牙无敌舰队即将出征，世界历史翻开新页；而明朝的皇帝、首辅、清官、将军、思想家，却在各自的困局中徒劳挣扎。万历皇帝想改革却被文官架空，张居正铁腕变法死后遭抄家，海瑞以道德对抗腐败处处碰壁，戚继光英雄无用武之地……六个人物，六面镜子，照出一个以道德代替技术的制度如何让所有努力归零。 黄仁宇用“大历史观”切开这一年，告诉你：不是他们无能，而是系统已到山穷水尽。 读懂这本书，就读懂了中国历史的深层逻辑。[美]黄仁宇
  • 147961
    哈利波特完整系列（全七册）
    哈利·波特被丢在门阶上的时候还是个婴儿，当时的他并不知道自己就是那个"大难不死的男孩"，也不知道自己是魔法世界里的大名人。几年后，他意外地收到了霍格沃茨魔法学校的入学通知随后不久，他就开启了一场与众不同的魔法冒险。快来和哈利以及他的挚友赫敏和罗恩一起，开启这个有关真实、爱与希望之力的故事。作为本世代的经典之作，哈利波特电子书集书将无疑为你从另一个世界带来心灵上的慰藉。在他们所传递的希望、归属感，以及贯穿始终的真实与爱的加持下，这个小男孩的成长故事将继续激励新世代的读者。[英]J.K.罗琳
  • 151.0万
    毛泽东选集（全四卷）
    这部选集，包括了毛泽东同志在中国革命各个时期中的重要著作。几年前各地方曾经出过几种不同版本的《毛泽东选集》，都是没有经过著者审查的，体例颇为杂乱，文字亦有错讹，有些重要的著作又没有收进去。现在的这部选集，是按照中国共产党成立后所经历的各个历史时期并且按照著作年月次序而编辑的。这部选集尽可能地搜集了一些为各地方过去印行的集子还没有包括在内的重要著作。选集中的各篇著作，都经著者校阅过，其中有些地方著者曾作了一些文字上的修正，也有个别的文章曾作了一些内容上的补充和修改。
  • 16623
    大地上我们转瞬即逝的绚烂
    ◆一位西贡少年的成长回忆录与家族辛酸史 ◆一场对亲情、种族、阶级、性别和自我认同残酷而坦率的探索 ◆ 我是小狗。 名字是外祖母兰给我起的。在兰长大的那个村子，人们会给像我一样过于瘦弱的孩子起个贱名来护身。名字薄如空气，但也可作盾牌。小狗盾牌。 我和母亲、外祖母因战事而逃离到美国。我脱下我们的母语，戴上我的英语，像一副面具，好让别人能看到我的脸，进而再看到她们的。 我正以人子的身份给母亲写信。我有好多话想对她讲。回忆往事，还有那个未说出口的秘密。因为我不想在还没说出自己是谁的时候就被抹去。[美]王鸥行
  • 173.6万
    明朝那些事儿（全集）
    《明朝那些事儿》主要讲述的是从1344年到1644年这三百年间关于明朝的一些故事。以史料为基础，以年代和具体人物为主线，并加入了小说的笔法，语言幽默风趣。对明朝十七帝和其他王公权贵和小人物的命运进行全景展示，尤其对官场政治、战争、帝王心术着墨最多，并加入对当时政治经济制度、人伦道德的演义。它以一种网络语言向读者娓娓道出明朝三百多年的历史故事、人物。其中原本在历史中陌生、模糊的历史人物在书中一个个变得鲜活起来。《明朝那些事儿》为我们解读历史中的另一面，让历史变成一部活生生的生活故事。当年明月
  • 18556
    事实（比尔·盖茨推荐）
    比尔·盖茨送给全美大学生的毕业礼物：一人一本《事实》。《事实》教你用数据思考，避免情绪化决策！颠覆你思维方式的神作《事实》，畅销近20个国家：美国、英国、德国、日本、瑞典、西班牙、意大利、荷兰……《金融时报》《书单》《自然》等多家媒体赞誉《事实》汉斯·罗斯林的TED等演讲视频点击量突破2000万次！《事实》教你避免情绪化决策！认识情绪化本能，作出相应改变，摆脱非理性的困扰，重新把能量投入建设性的行为中！一旦你拥有了《事实》提供的思维方式，你就能：远离焦虑、变得乐观、充满希望、变得理性、发现潜在的商机、作出有效决策。汉斯·罗斯林 欧拉·罗斯林 安娜·罗斯林·罗朗德
  • 194228
    以日为鉴：衰退时代生存指南（微信读书特别版）
    "通过对日本“失去的三十年”泡沫经济时代中，教育、卫生、医疗等各个产业的详尽分析，梳理日本多种社会问题形成的根源所在。 每一个问题都在结合中国读者最关心的话题： “考公务员是最合理的就业选择吗？” “医生未来的待遇会更好还是更差？” “生育率下降会影响教师就业吗？” “研究生扩招，报考人数下降，研究生还值得读吗？” 作为文化相近、轨迹相似的邻国，日本的社会发展史，是最能给国人带来思考和借鉴意义的发展史。 在经济寒冬、社会问题频发、年轻人陷入迷茫的今天，“职业选择”已经成了头等大事。 也许今天你可以求助“择校专家”，那么五年后呢？“师医公”还会是今天的“铁饭碗”吗？ 在这里，有十余年外资投行分析师经验的作者，将通过我们的近邻日本的各种社会问题和经历，为疑惑的你给出答案。"分析师Boden
  • 20985
    做对“懒”爸妈　养出省心娃
    孩子成长过程中，总是问题不断，从小的细节，到大的是非。简单粗暴的体罚伤害亲子关系，温柔的坚持容易憋出内伤。而且即使父母说得对，也告诉了孩子应该怎么做，纠错的效果还是会打折扣。因为父母说得对，跟孩子做得到，并不能简单地画等号。频繁地给孩子讲道理纠错，还可能会让孩子产生逆反心理。 作为父母，如何有效引导孩子解决问题、助其成长？ 优势累积教育法是沈奕斐博士在多年的中国家庭关系和家庭教育研究的基础之上，结合哈佛大学的多元智能概念和犹太家庭教育理念，提出的一套系统、科学、有效的家庭教育方法。 该方法运用社会学中的优势累积概念，针对中国家庭教育夹在传统权 威式教育和西方快乐教育之间的困境，在教育学的基础上，借鉴积极心理学的方法，通过改变家长的认知从而改变家长的情绪和行为，让父母真正放松下来，享受愉快的亲子关系，重建家庭的和谐。同时促进孩子的个性化成长，找到自我激励机制。沈奕斐
共 20 条热搜查看完整榜单
共 44 条热搜查看完整榜单

arXiv · cs.CL

6天前更新
  • 01
    Cross-sector generalization of accident-process role classification in occupational accident narratives
    Occupational accident narratives contain valuable information about work situations, unfavourable conditions, accident events, and their consequences. Automatically structuring these narratives can facilitate large-scale accident analysis and support occupational risk prevention. However, the terminology and writing styles used to describe accidents vary considerably across sectors and organisations, raising questions about the ability of automated coding systems to generalize beyond their trainAho Yapi
  • 02
    Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
    Multi-hop retrieval failures are not uniformly distributed across queries: they cluster in structurally predictable subpopulations. We prove two results formalizing this structure. First (CWAR Reducibility): confident-failure reduction is achievable if and only if retrieval features carry mutual information about success, a condition satisfied by LLM-judge pipelines but substantially weaker in dense-only settings, explaining the AUC-AC gap between regimes. Second (Feature Regime Complementarity)Andre Bacellar
  • 03
    An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
    Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be trusted has received comparatively little attention. When the memory store contains conflicting positions, standard retrieval-augmented generation (RAG) blindly injects memories and amplifies hallucinations: in models susceptible to memory injection, the RAG hallucination rate under conflicting memories is markedly higher than that of a memory-fYiming Zhang
  • 04
    QuranicMMLU: A Cognitively-Aware Benchmark for Evaluating Generative AI Solutions on Quranic Linguistic Knowledge
    We introduce QuranicMMLU, a benchmark for evaluating generative AI on Quranic Arabic across multiple dimensions of linguistic complexity. Existing Quranic benchmarks center on general question answering and semantic retrieval, without probing specific linguistic competencies or stratifying by cognitive demand and verse difficulty. We construct a five-pillar Quranic taxonomy spanning Phonology, Morphology, Syntax, Semantics, and Pragmatics, with 31 leaves covering phenomena from tajwīd and root-aRawan El Ghali
  • 05
    DiaVLo: Diagnosing Behaviours of Vision-Language Models
    Vision-language models (VLMs) rely on storing and transferring appropriate information across their sub-components. Verifying that the VLMs exhibit desired behaviours, while avoiding harmful ones, is central to their reliable deployment. Yet, methods that identify VLM behaviours remain scarce. We present DiaVLo, a diagnostic framework that leverages human curation and VLMs' generation capabilities to construct specifications of desired and observed VLM behaviours, surfacing potential misalignmenLorenzo Corti
  • 06
    Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention
    Gating the value pathway of attention reportedly improves language model pretraining, and prior studies disagree on why. We argue and provide experimental evidence that such gates supply two different things that softmax attention lacks: abstention and noise filtering. The first is abstention, which allows an attention head to output nothing, bypassing the requirement that attention weights must sum to one. The second is noise filtering, which allows the value pathway of an attention head to supRichard Zhe Wang
  • 07
    RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
    Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface, implement software, and run and visually verify their artifacts. We introduce RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover itShuai Bai
  • 08
    Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
    Most work in computational ethics treats annotator disagreement on moral content as noise to be voted away, collapsed into majority vote or the more permissive any-annotator rule the moment a single annotator flags an item. We argue this uncertainty should instead be modeled and learned from. We introduce Moral Entropy, a Bayesian framework that keeps a full posterior over the true label and decomposes its entropy into aleatoric uncertainty (irreducible disagreement about the moral content) andMaciej Skorski
  • 09
    NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities
    We introduce NemotronLabs VoiceChat, an open full-duplex speech-to-speech model with native tool-calling capabilities. NemotronLabs VoiceChat combines a streaming speech encoder and decoder-only language model with parallel specialized output streams for agent text and structured function calls, an auxiliary RNN-T branch for incremental user transcription, and a streaming TTS decoder. This design enables the model to listen, transcribe, reason, invoke tools, and speak within a unified streamingJagadeesh Balam
  • 10
    Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective
    Detecting pretraining data in large language models is challenging because high likelihood can reflect either training exposure or strong generalization. In the joint space of prediction loss and predictive entropy, a likelihood-only detector uses a horizontal boundary and can mistake predictable non-members for members. Motivated by this, we introduce an inclined boundary that evaluates prediction loss relative to predictive entropy. Our analysis shows that entropy correction can preserve the eChenye Ke
  • 11
    TrialAtlas: Multi-Agent Research Organization for Clinical Trial Design and Optimization
    Nearly 90% of drugs entering clinical development ultimately fail, despite billions of dollars in investment. Pharmaceutical companies therefore rely on clinical development planning (CDP) and probability of technical and regulatory success assessment to anticipate development risks, yet these decisions remain labor-intensive and subjective, requiring experts across clinical science, statistics, regulatory affairs, and competitive intelligence to jointly acquire, synthesize, and reason over heteJiacheng Lin
  • 12
    Do Personality-Tuned LLMs Make Better Social Agents?
    LLMs are increasingly used in social simulations for socially interactive agents and robots, offering more flexibility than rule-based systems. However, even though they mimic human behaviour very well, there is a persistent alienness to them. This work investigates whether personality-aware fine-tuning can reduce this gap by improving the consistency and controllability of personality-conditioned dialogue generation compared with instruction prompting alone. We fine-tune two small open-weight LTim Krabbe
  • 13
    Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts
    Long transcripts are costly inputs for downstream NLP systems and often contain irrelevant context. We study query-conditioned topic localization: predicting the sentence span in a transcript that best addresses a topic-title query. To improve span localization, we reuse ASR encoder states as sentence-level representations and fuse them with textual embeddings. This lets lightweight span locators exploit speech information without running a separate audio encoder. Experiments on two public datasSteffen Freisinger
  • 14
    RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding
    Speculative decoding accelerates LLM inference by drafting multiple tokens in parallel, with tree-based methods further improving efficiency through hierarchical structures. Dynamic-tree methods such as EAGLE-3 perform well under greedy decoding via deterministic top-K expansion and global pruning. However, in stochastic decoding (T>0), this mechanism collapses the draft distribution into one-hot probabilities, causing a severe drop in acceptance rate. This creates a dilemma: dynamic-tree methodQiao Hu
  • 15
    CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation
    Defenses against jailbreak attacks on Large Language Models (LLMs) operate at different pipeline stages, such as input modification or output guard, but it remains unclear which defenses to deploy at each stage and how to combine them. Prior empirical studies, fragmented by inconsistent attack-success-rate definitions and experimental settings, have evaluated defenses largely in isolation. Here we present the first systematic study, to our knowledge, of defense combinations both within and acrosJiale Luo
  • 16
    Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo-Labelling for Multilingual Dysarthric Speech
    Most multilingual dysarthria-severity systems either train on a single aetiology-language pair or pool heterogeneous aetiologies into one label space. We test that pooling assumption with four matched HuBERT-base contrastive embedding models under a shared backbone, training recipe, corpus registry and held-out evaluation: one mixed-aetiology baseline and three aetiology-specific models for cerebral palsy (CP), Parkinson's disease (PD) and amyotrophic lateral sclerosis (ALS). Training combines cBernard Muller
  • 17
    World Modeling in Transformers
    Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonstrate this in TaxiGPT, a transformer trained on random walks through Manhattan whose failures have been interpreted as evidence of an incoherent internal map. Through mechanistic analysis and causal interventions, we show that the model represents intersections and streets, tracks its position, and uses a goal compass to navigate. We trace its faiPierre Beckmann
  • 18
    CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords
    Chinese social media has generated a vast and continually evolving lexicon of internet buzzwords whose meanings are often non-literal and deeply rooted in local cultural and pragmatic contexts. Existing research has primarily focused on interpreting these buzzwords within Chinese, leaving largely unexplored whether LLMs can transfer such culturally grounded knowledge across languages and accurately convey the intended meanings in English. This cross-lingual capability is also critical for safetyYifan Wang
  • 19
    Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation
    Conversational speech depends on dialogue context and the listener's immediately preceding behavior. We propose ReACT-TTS, a two-stage framework that uses a one-second pre-response listener facial sequence to plan the next utterance's emotion and prosody before speech realization. On a strict dyadic MELD protocol, Temporal conditioning yields higher mean macro-F1 and VAD concordance than Text-only across ten seeds, while accuracy remains essentially unchanged. Ablations show that temporal modeliYunji Chu
  • 20
    The Spoken Wikipedia Presentation Corpus
    We present the Spoken Wikipedia Presentation Corpus, an extension of the Spoken Wikipedia Corpora featuring LLM-generated slide decks for multimodal ASR. Slides are created from LLM-segmented sections using a hybrid pipeline that combines LLM-based content planning with rule-based design decisions. For each section, an LLM generates a slide title, bullet points, a takeaway message, and a visual description that is used to create an illustration. Rule-based matching then selects layouts, themes,Thomas Ranzenberger
  • 21
    PRISM-BN: A Controlled Corpus and Benchmark for Text-to-Parameterized Bayesian Network Extraction
    Probabilistic Graphical Models (PGMs), especially Bayesian Networks (BNs), expose directed structure and probabilistic parameters, making them natural symbolic targets for neurosymbolic AI. Yet training text-to-parameterized-BN systems requires paired text-to-BN resources unavailable at scale. We introduce PRISM-BN, a controlled corpus of 5054 BN-grounded descriptions paired with discrete reference BNs containing variables, states, directed edges, root priors, and full multi-parent CPDs across fAmartya Bhattacharya
  • 22
    Accelerating Dense LLMs via L0-regularized Mixture-of-Experts
    Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeable performance degradation, while Mixture-of-Experts (MoE) models require extensive computational resources. In this paper, we propose L0-MoE, a lightweight MoE approach using L0-regularization to accelerate dense LLMs nearly without performance loss. Our method introduces a cluster confusion matrix for domain-aware dataset curation and applies dyZhenyu Zhang
  • 23
    Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER
    Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats every lexical deviation from the reference as equally costly, regardless of whether it changes meaning. This raises the question: does WER actually track how humans judge ASR transcript quality? We introduce HATS-en, an English dataset for human-centered ASR evaluation. Using this dataset, we benchmark lexical metrics against several configurations of BERTScore and SemDist, varying the language moHritika Sharma
  • 24
    When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap
    Activation steering has become a widely used approach for controlling language models during explicit chain-of-thought (CoT) reasoning, motivating its extension to latent CoT. However, we find that steering continuous thoughts produces substantially weaker effects on subsequent language generation than steering explicit CoT, even when the hidden representations are moved by comparable amounts. We first show that task information remains identifiable in continuous thoughts. Hence, we hypothesizeGaoxiang Huang
  • 25
    Analysing the Linearity of Linguistic Relations in Language Model Embedding Spaces
    We propose a framework to analyse how strongly different linguistic relations are linearly encoded in language model embedding spaces. We formalise linear encoding via a constrained linear approximation over related and unrelated word pairs and apply this to an extended BATS dataset covering inflectional, derivational, lexicographic, and encyclopedic relations in GloVe, RoBERTa, and ModernBERT. Our experiments show near-perfect linear encodings for inflectional and derivational relations, but suVasudevan Nedumpozhimana
  • 26
    Configurable Multi-Stage Vision Pipeline for Crop Disease and Pest Diagnosis
    Farmer.Chat is Digital Green's farm advisory service for smallholder farmers. When something looks wrong with a crop, the farmer takes a photograph and sends it, and that photograph is the whole question: no symptom described, no crop named, often no text at all. The service has to determine whether the picture can be used, what crop it shows, and what is wrong with it, from images taken on cheap phones in a field, in poor light and with a moving camera. The system doing this today cannot be adjNaga Ganesh
  • 27
    Chinese Competitive Debating Dataset and Benchmark
    Debate adjudication requires tracking how arguments develop through interaction, yet existing datasets rarely combine fine-grained debate transcripts with professional judgments collected during real competitions under a shared rubric. We introduce a dataset and benchmark for evaluating large language models' understanding of competitive Chinese-language debate at the match, stage, and speaker levels. We organized 182 matches and recruited 120 professional judges, with each match independently aZongrui Yang
  • 28
    Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30
    Recent work applies human psychometric questionnaires to large language models to elicit moral and value profiles, but it is not clear whether these instruments measure anything stable in models or whether the resulting profiles can be moved toward a target human population. We administer the Norwegian Moral Foundations Questionnaire (MFQ-30) to six open-weight LLMs and compare their foundation profiles to a sample of N = 1,282 Norwegian respondents. We test two steering interventions, prompt-leHans Andersen
  • 29
    Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction
    In-context learning using Large Language Models (LLMs) offers a compelling path to training-free post-OCR correction, yet its effectiveness for Devanagari script remains entirely unexplored. We present the first systematic evaluation of LLMs (3B-32B) for post-OCR correction in Hindi and Marathi, comparing three in-context example retrieval strategies: domain-random selection, dense semantic retrieval, and our proposed CharBM25, which retrieves examples by character n-gram BM25 similarity over OCAbhishek Bhandari
  • 30
    GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions
    Coding agents can modify and test code across large software projects. Game development is a domain where agents must implement gameplay rules. A game can end in a valid state even after violating its rules during the run. Current game-development benchmarks replay fixed examples, score videos, or ask another model to judge the result. However, no existing benchmark checks game rules throughout execution across varied evaluator-selected scenarios while ensuring exactly reproducible verdicts. WeXinyu Che
  • 31
    MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance
    Recent advances in Large Language Models (LLMs) have revolutionized artificial intelligence and how human interact with AIs. Despite impressive advancements, LLMs struggle with complex mathematical, scientific, and logical tasks. Inspired by human cognitive flexibility - our ability to dynamically switch mental perspectives - we propose MIRAGE (Multi-perspective Inference-time Reasoning via Agent-Guided Exploration), a novel inference-time creative thinking framework. MIRAGE includes a SelectorArash Lagzian
  • 32
    Benchmarking Gender Bias in Machine Translation Evaluation Metrics across Occupations
    Gender bias remains a persistent concern in machine translation (MT), affecting both generated translations and their automatic evaluation. When a source text leaves a person's gender unspecified, translations may realize that person using masculine or feminine forms, and both MT systems and evaluation metrics may exhibit systematic preferences between these alternatives despite the source providing no basis for such a distinction. We study this behavior in the WMT 2026 Automated Translation QuaOrfeas Menis Mastromichalakis
  • 33
    Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue
    Conversational AI systems produce fluent, socially appropriate responses, yet whether they participate in cooperative communication or merely simulate its surface forms remains unclear - a question central to how these systems are evaluated, trusted, and designed. This study investigates how morality, politeness, and alignment - three dimensions central to cooperative dialogue - function in human-AI interaction compared to human-human conversation. We analyze 15,881 human-ChatGPT and 10,784 humaMarina Mitiaeva
  • 34
    Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction
    Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather than carefully composed text prompts. However, existing benchmarks of interactive capabilities still focus primarily on response quality, leaving a more fundamental question underexplored: can a model correctly infer the user's underlying demand from complex multimodal interaction? Real-world user demands are often underspecified in speech and mQi Chen
  • 35
    Offline Multimodal Large Language Models for Decision Support in Air Operations
    Air operations rely on complex rules, established procedures, and time-critical analysis under limited connectivity and strict security constraints. In such environments, analysts must combine written doctrine with images, often without access to external computing resources. This paper studies offline large language models as decision support tools, deployed in isolated and restricted environments to give analysts access to doctrinal knowledge that remains traceable to its original sources throJoao P. A. Dantas
  • 36
    Consistent Relexicalization of Clinical Documents using Graph-Based Approach
    Relexicalization is a pivotal technique in clinical NLP, as it facilitates robust masking of sensitive information while synthesizing datasets that retain high-fidelity, real-world characteristics. However, preserving structural integrity, relational coherence, and temporal consistency during transformation remains a significant challenge. Existing approaches frequently rely on independent entity replacement, which results in clinical inconsistencies across longitudinal records. This reduces theDipankar Das
  • 37
    Prediction Dynamics in Depth-Recurrent Language Models
    Depth-recurrent language models refine predictions through repeated latent updates. Why can intermediate answers agree with the endpoint while their scores continue to change? We derive a sharp margin characterization that decomposes the conservatism of a magnitude bound into common translation, direction relative to the winner, and the pairing of each competitor's update with its score gap. Across Huginn-3.5B and Ouro-1.4B, accounting for update direction and competitor pairing reduces the meanXinyue Luo
  • 38
    ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL
    Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended agent tasks, where solutions are diverse and reliable scalar rewards are hard to obtain. Recent pairwise evaluation methods alleviate reward discrimination collapse by replacing pointwise scoring with relative preferences. However, they still compress rich comparative feedback into a single trajectory-level reward, obscuring decisive intermediateQiang Zhang
  • 39
    Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining
    Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocabularies. We introduce \textbf{Phonemic Tokenizer}, a linguistically motivated tokenizer for Vietnamese and Chinese that converts each syllable into IPA and factorizes it into three phonological components: onset, rime, and tone. The three components jointly occupy one contextual position, preserving syllable-level sequNghia Hieu Nguyen
  • 40
    From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers
    Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existing in-context learning-based methods fail to capture how individuals react under different situations. In addition, LLM-based evaluation is difficult for obscure individuals. To address these challenges, we propose Situation--Internal state--Behavior Persona method to incorporate situation-dependent behavioral strategies. We further design an evaluaJi-Lun Peng
  • 41
    Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees
    Empirical identity leakage from released text is increasingly driven by attackers that combine large language models (LLMs) with auxiliary knowledge to link documents to individuals. Existing audits typically report success rates for specific attack pipelines but lack finite-sample statistical guarantees, while training-time protections such as differential privacy are difficult to translate into release-time decisions for individual natural-language documents. We introduce Conformal Privacy AudShuo Huang
  • 42
    FairLMs: A Turnkey Library for Fairness in Language Models
    Fairness research on language models involves measuring bias, applying mitigation methods, and examining the evidence on which an evaluation rests. Existing tools offer complementary functionality through different interfaces, so combining them requires reconciling model interfaces, evidence formats, access constraints, and result types before applicability can be checked or methods compared. We introduce \textbf{FairLMs}, a Python library that connects these activities through explicit declaratJiale Zhang
  • 43
    How Many Humans Is a Judge Panel Worth?
    How many human judgments does a panel of language models represent? The answer depends on what is matched. We audit categorical judge panels against empirical human label distributions, retaining disagreement that binary errors relative to one gold label collapse. We measure spectral residual diversity by matching the participation ratio of a normalized residual Gram matrix to conditionally independent human-reference draws, giving nu_H. We separately match distributional squared error, giving nChao Li
  • 44
    When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Traces
    Large Reasoning Models increasingly use intermediate traces for machine translation, but it remains unclear when such reasoning helps or hurts. We analyze reasoning traces across models, languages, domains, and datasets, focusing on reasoning language, length, and structure. We find that the best reasoning language is model-specific, reasoning length has a non-monotonic relationship with quality, and traces exhibit recurring functional patterns. To uncover these patterns, we introduce HierarchicYuxiang Liu
  • 45
    Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction
    Reference-based metrics for Grammatical Error Correction (GEC) such as M$^2$ and ERRANT assume that the reference set enumerates all valid edits, and therefore often penalize corrections that are grammatical and meaning-preserving but phrased differently. We introduce RM-EVAL, a reward model trained on human preference data from SEEDA, as a reference-free meta-evaluator that predicts human-like quality judgments at both full-sequence and partial-sequence levels. Beyond evaluation, we show that tRuotian Wu
  • 46
    Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency
    Factual hallucination is commonly defined by incorrect factual outputs. We study a paraphrase-induced hallucination setting, where a model answers a factual question correctly in its original form but generates an incorrect answer under a semantically equivalent paraphrase. Such inconsistencies expose latent factual instability under semantic invariance. However, general-purpose paraphrases are often insufficient as robustness-oriented supervision: near-copy paraphrases provide weak signals, whiWenhan Yu
  • 47
    When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success
    Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is scored against a reference. We investigate whether improvement under this protocol is predictive of improved autonomous workflow execution. We study pre-SFT and supervised fine-tuned (SFT) Qwen3 models at 4B and 14B parameters and Gemma 3 models at 4B and 12B parameters on multi-turn customer-support workflows. We find that SFT consistently improvMd Tahmid Rahman Laskar
  • 48
    I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance
    Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introduce proactive audio assistance, where an AudioLLM monitors an audio stream and autonomously decides when to alert the user from a single natural-language intent, motivated by wearable applications for Deaf and Hard of Hearing users. We propose Interrupt and Silent Modeling (ISM), a model-agnostic paradigm that embeds proactive decisions into LLM decoding via two special tokens: \texttt{ } and \textAmit Kumar Singh Yadav
  • 49
    Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological Inflection
    Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors clustered in rare morphological subclasses. We present an orthography-aware diagnosis of Japanese past-tense verb inflection, treating hiragana not merely as a transcriptional medium but as a representational system that encodes morphophonological structure. Using two character-level Transformer architectures evaluated across five random seeds, wWen Zhang
  • 50
    CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loop
    Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools instead serve fixed item banks and treat a wrong answer as a single bit of signal. We present CoLearn, an interactive, agentic tutor that supports an iterative tutoring loop: the learner practises, and the system builds an evidence-grounded memory of the learner's mastery and misconceptions. This memory is updated as evideKailai He
  • 51
    Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake
    Before patients can use AI-assisted psychiatric intake systems, health systems need practical ways to routinely evaluate these tools against their clinical standards for quality assurance. Because clinicians may use different intake styles, evaluation for this task must (1) support comparison across interviewing approaches, (2) minimize clinician burden, and (3) measure clinically relevant performance for health systems deploying these technologies. We present a clinician-grounded evaluation plaKing Shi
共 100 条热搜查看完整榜单
共 50 条热搜查看完整榜单
共 8 条热搜查看完整榜单

OEIS · 待补充数列

6小时前更新
共 10 条热搜查看完整榜单