OpenReview · 实时热榜

期刊：Transactions on Machine Learning Research · 摘要：Recent advances have significantly improved the training efficiency of diffusion transformers. However, these techniques have largely been studied in isolation, leaving unexplored the potential synergies from combining multiple approaches. We present SR-DiT (Speedrun Diffusion Transformer), a framework that systematically integrates token routing, architectural improvements, and training modifications on top of representation alignment. Our approach achieves FID 3.14 and KDD 0.290 on ImageNet-256 using only a 140M parameter model at 400K iterations without classifier-free guidance---comparabl… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/SwayStar123/SpeedrunDiT · OpenReview ID：0mYu3uPM3j

期刊：Transactions on Machine Learning Research · 摘要：Anomaly detection seeks to identify observations that deviate significantly from an underlying data distribution. While deep learning and ensemble-based approaches have achieved strong empirical performance, their computational and memory requirements limit their applicability in resource-constrained edge environments. Furthermore, many approaches to improving efficiency rely on supervised models, which require labeled anomalies that are often scarce in practice. We propose Yose-Ue, a resource-efficient, fully unsupervised anomaly detection framework based on treap-structured ensemble learnin… · 篇幅：Long submission (more than 12 pages of main content) · 代码：https://github.com/eduardoortegathethird/Yose-Ue · OpenReview ID：17y2ooyemG

期刊：Transactions on Machine Learning Research · 摘要：We introduce Functional Group-Aware Representations for Small Molecules (FARM), a novel foundation model designed to bridge the gap between SMILES (a linear string representation of molecular structures), natural language, and molecular graphs. The key innovation of FARM lies in its functional group (FG) annotation at the atomic level, which enables both FG-enhanced SMILES and FG graphs: SMILES are enriched with FG information to specify which functional group each atom belongs to, while the FG graph captures the molecular backbone by showing how the functional groups are connected. This toke… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/thaonguyen217/farm_molecular_representation · OpenReview ID：2All12TFlh

期刊：Transactions on Machine Learning Research · 摘要：Determining which data samples were used to train a model, known as Membership Inference Attack (MIA), is a well-studied and important problem with implications on data privacy. SotA methods (which are black-box attacks) rely on training many auxiliary reference models to imitate the behavior of the attacked model. As such, they rely on assumptions which rarely hold in real-world settings: (i) the attacker knows the training hyperparameters; (ii) all available non-training samples come from the same distribution as the training data; and (iii) the fraction of training data in the evaluation s… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/yuvalgol123/ImpMIA-code · OpenReview ID：34bnVED6EZ

期刊：Transactions on Machine Learning Research · 摘要：In the evolving landscape of deep learning, selecting the best pre-trained models from a growing number of choices is a challenge. Transferability scorers propose an efficient alternative to this challenge by calculating a proxy to rank a pool of pre-trained model candidates. Despite their promise, the field currently lacks standardized evaluation protocols, consistent baselines, and reproducible methodologies. This has led to contradictory findings across studies, with the best scorer in one study ranking among the worst in another. In this work, we introduce a benchmark for transferability… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/VirtualSpaceman/tmlr-transferability-benchmark · OpenReview ID：3i2ZRk8GDN

期刊：Transactions on Machine Learning Research · 摘要：Matrix manifolds play a fundamental role in machine learning, underpinning data representations (\textit{e.g.}, linear subspaces and covariance matrices) and optimization procedures. These manifolds follow Riemannian geometry, where intrinsic geometric structure plays an important role in geometric learning algorithms. However, traditional visualization methods based on Euclidean assumptions often fail to respect such non-Euclidean structure, leading to distortions in the resulting embeddings. To address this limitation, building upon the established Riemannian t-SNE paradigm, we develop thre… · 篇幅：Long submission (more than 12 pages of main content) · 代码：https://github.com/paradox-going/ManiReduce · OpenReview ID：4EZeC0JwqM

期刊：Transactions on Machine Learning Research · 摘要：Earth Observation (EO) uses satellite and aerial imagery to monitor the Earth’s surface, supporting critical applications in infrastructure, agriculture, and climate change. As governments and industry scale EO pipelines, reliable automation has become essential. Yet, current Vision-Language Models are limited to coarse-grained perception, struggling to execute the precise, multi-step reasoning required for operational decision-making. Recent evaluations on benchmarks like GeoBench-VLM highlight this shortcoming: even state-of-the-art models show low accuracy and frequently struggle with task… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：7yUrnyFgEq

期刊：Transactions on Machine Learning Research · 摘要：In mission critical domains such as sensor networks, operators often face the critical decision of whether to act on incomplete information or whether collecting missing values is likely to change the prediction. Existing methods typically focus on imputing missing values or quantifying model uncertainty, but they do not directly assess the stability of a prediction if missing values were to be revealed. To address this gap, we first introduce a framework for Missing Value Uncertainty (MVU), which is the distribution of predictions induced by incomplete inputs at inference time. We formalize… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/inouye-lab/MissingValueUncertainty/releases/tag/tmlr · OpenReview ID：BRWTS5e03Z

期刊：Transactions on Machine Learning Research · 摘要：Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in clinical practice. Existing methods rely on external guidance to supply detailed missing-state information for instructing generative models to synthesize missing MRIs. However, manual indicators are not always available or reliable in real-world scenarios due to the unpredictable nature of clinical environments. Moreover, these explicit masks are not informative enough to provide guidance for improving semantic consistency. In this work, we argue that g… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/JK-Liu7/CoPeDiT · OpenReview ID：DCaolE9oBN

期刊：Transactions on Machine Learning Research · 摘要：This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process. In contrast to traditional diffusion-based approaches that rely on a coupled forward-backward diffusion scheme, FoD directly learns image restoration through a single forward diffusion process, yielding a simple yet efficient framework. The core of FoD is a state-dependent stochastic differential equation (SDE) that involves a mean-reverting term in both the drift and diffusion functions. This mean-reverting structure drives the low-quality data toward the clean endpoint… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/Algolzw/FoD · OpenReview ID：Eq9k6Va3hY

期刊：Transactions on Machine Learning Research · 摘要：Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models (SLMs) is limited, leading to factually incorrect generations. This problem is often mitigated by giving the SLM access to an outside source: the ability to query a larger model, documents, or a database. Under this setting, we study the fundamental question of \emph{which tokens an SLM can and should learn} during pretraining, versus \emph{which ones it shou… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：JxVxBa3wO5

期刊：Transactions on Machine Learning Research · 摘要：Subjective evaluation tasks including critical analysis and rating remain at the top of Bloom’s Taxonomy. These have emerged as new pathways for evaluating Language Models (LMs) wherein correctness is relative. While LMs present diverse and human-aligned opinions on such tasks, their confidence and reliability in opinions remains unexplored. We take a deeper look at the reliability of LMs for subjective evaluations by selecting one such task of focus group surveys. LMs act as participants by completing survey questionnaires of diverse physical products. Participants must verbalize their opini… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/karush17/focus-groups · OpenReview ID：NGuOZYQZBq

期刊：Transactions on Machine Learning Research · 摘要：Language models can treat semantically distinct inputs as interchangeable at the representation level, creating blind spots that standard sparse autoencoder (SAE) objectives do not target. In safety-critical settings such as clinical dosage extraction, legal clause interpretation, or financial amount verication, such failures can propagate silently into downstream decisions. We study this problem as one of feature-basis orientation. Building on a symmetry-matching view from algebraic error-detection theory, we add a diferentiable V_Gini regularisation term to SAE training that penalises uneve… · 篇幅：Long submission (more than 12 pages of main content) · 代码：https://github.com/csabibme/blind_spot_reduction_SAE_TMLR · OpenReview ID：NWWpKC9CZH

期刊：Transactions on Machine Learning Research · 摘要：Class imbalance has been a critical bottleneck in classification problems, undermining a classifier's identification of minority instances. Data augmentation provides an effective solution by oversampling the minority. Extant methods often generate samples through duplication, perturbation, or interpolation, largely relying on the assumption of local smoothness of the data space to ensure synthetic data reliability. Alternatively, generative models are leveraged for data learning and synthesis. However, both approaches encounter significant limitations in tabular data, primarily due to data h… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/1836897243/TreeSmote · OpenReview ID：OelOS8cbBY

期刊：Transactions on Machine Learning Research · 摘要：Downscaling is essential for generating the high-resolution climate data needed for local planning, but traditional methods remain computationally demanding. Recent years have seen impressive results from AI downscaling models, particularly diffusion models, which have attracted attention due to their ability to generate ensembles and overcome the smoothing problem common in other AI methods. However, these models typically remain computationally intensive. We introduce a Hierarchical Diffusion Downscaling (HDD) model, which introduces an easily-extensible hierarchical sampling process to the… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：OhTYgFpMU2

期刊：Transactions on Machine Learning Research · 摘要：Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple to complex tasks. However, while large models achieve remarkable results across diverse tasks, they often incur substantial monetary inference cost, making frequent use impractical for many applications. In contrast, small models are often freely available and easy to deploy locally, but their performance on complex tasks remains limited. This trade-off raises a natural question: how can small and large models efficiently collaborate to combine their complementary strengths? To bridge this trade-o… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/prinwinter/cope · OpenReview ID：RPzbeL0koP

期刊：Transactions on Machine Learning Research · 摘要：We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent. It leverages training runs from a hyperparameter search to learn a latent representation of the training process, which is modeled as a dynamical systems. Given current training metrics, it predicts the future learning rate schedule with the best long-term validation performance. Our scheduler generalizes beyond previously observed training dynamics and creates specialized schedules that deviate noticeably from even the best-performing parametric functions. It outperforms all baselines… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：SwmzJgB9TA

期刊：Transactions on Machine Learning Research · 摘要：We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone of reinforcement learning. We are interested in the so-called ``robust'' setting, where the convergence guarantee does not depend on the potential function's minimal curvature. While prior work has established convergence guarantees in this setting, these results typically rely on the artificial assumption that each iterate is projected onto a bounded set. Removing such a condition was left as an open problem by Bhandari et al. (COLT'18), hypothesizing t… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：Tj1B5WDyt8

期刊：Transactions on Machine Learning Research · 摘要：We propose Semantic F1 Scores, novel evaluation metrics for subjective or fuzzy multi-label classification that quantify semantic relatedness between predicted and gold labels. Unlike the conventional F1 metrics that treat semantically related predictions as complete failures, Semantic F1 incorporates a label similarity matrix to compute soft precision-like and recall-like scores, from which the Semantic F1 scores are derived. Unlike existing similarity-based metrics, our novel two-step precision-recall formulation enables the comparison of label sets of arbitrary sizes without discarding lab… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/gchochla/semantic-f1-score · OpenReview ID：U0YJpGuFEc

期刊：Transactions on Machine Learning Research · 摘要：This work considers recovering a sequence of low-rank matrices from undersampled measurements, where the underlying subspace varies across samples over time. Existing works involve concatenating all of the samples from each time point to recover the underlying matrix under the assumption that the data are well-approximated by a single, static subspace. However, this assumption is inappropriate for applications where the best low-rank approximations vary over time. To address this issue, we propose a Riemannian block majorize minimization algorithm that constrains the time-varying subspaces as… · 篇幅：Long submission (more than 12 pages of main content) · OpenReview ID：W0ZNwXoBeh

期刊：Transactions on Machine Learning Research · 摘要：We introduce \texttt{OTIS}, an \textbf{o}pen \textbf{ti}me \textbf{s}eries encoder that yields high-quality time series features for downstream deployment on \emph{any} system, including resource-constrained wearables and industrial sensors. Currently, the development of powerful general-purpose encoders relies on the scaling laws hypothesis, using large encoder sizes to memorise the heterogeneous distributions of multi-domain training data. However, this reliance on scale creates a barrier to real-world utility, rendering deployment on resource-constrained systems infeasible due to strict me… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/oetu/otis · OpenReview ID：WW206A1Tru

期刊：Transactions on Machine Learning Research · 摘要：We present and test the largest benchmark for vericoding, LLM-generation of formally verified code from formal specifications — in contrast to vibe coding, which generates potentially buggy code from a natural language description. Our benchmark contains 12,504 formal specifications, with 3,029 in Dafny, 2,334 in Verus/Rust and 7,141 in Lean. Of these, 6,174 are new unseen problems. We find vericoding success rates of 27% in Lean, 44% in Verus/Rust and 82% in Dafny using off-the-shelf LLMs. Adding natural-language descriptions does not significantly improve performance. We also find that LLM… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：Zgh5kpGAm8

期刊：Transactions on Machine Learning Research · 摘要：Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundation models (TSFMs) can capture low-level dynamic patterns and provide accurate forecasting, further analysis usually requires additional background knowledge and sophisticated reasoning, which are lacking in most TSFMs but can be achieved through Large Language Models (LLMs). On the other hand, without expensive post-training, LLMs often struggle with the numerical understanding of time series data. Although it is intuitive to integrate… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：d6TD0f2xXq

期刊：Transactions on Machine Learning Research · 摘要：Many modern deep learning applications require balancing multiple objectives that are often conflicting. Examples include multi-task learning, fairness-aware learning, and the alignment of Large Language Models (LLMs). This leads to multi-objective deep learning, which tries to find optimal trade-offs or Pareto-optimal solutions by adapting mathematical principles from the field of Multi-Objective Optimization (MOO). However, directly applying gradient-based MOO techniques to deep neural networks presents unique challenges, including high computational costs, optimization instability, and the… · 篇幅：Long submission (more than 12 pages of main content) · OpenReview ID：eCUcXXH3PS

期刊：Transactions on Machine Learning Research · 摘要：Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and leading to high variance in outcomes. While prior work has attempted to scale within a single rollout, such approaches have yielded limited gains. Scaling over multiple rollouts offers a more promising alternative but doing so effectively is challenging due to the difficulty of evaluating and selecting among long-horizon agent behaviors. We introduce Behavior J… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：eve4jBYa8D

期刊：Transactions on Machine Learning Research · 摘要：Foundation models have achieved remarkable success across many domains, relying on pretraining over vast amounts of data. Graph-structured data often lacks the same scale as unstructured data, making the development of graph foundation models challenging. In this work, we propose Foundation-Informed Message Passing (FIMP), a message-passing framework that repurposes existing pretrained non-textual foundation models for graph-based tasks in multiple capacities, including tokenization, representation extraction, and weight initialization. We show that the self-attention layers of foundation mod… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：fj7sjOwtXc

期刊：Transactions on Machine Learning Research · 摘要：``How long can I live and remain free of cancer?'' is often the first question a patient asks after receiving a cancer diagnosis and treatment. Accurate survival prediction helps alleviate psychological distress and supports risk stratification and personalized treatment planning. Recent survival prediction frameworks have shown strong performance using computed tomography (CT) images. However, variations in imaging acquisition introduce out-of-distribution (OOD) samples caused by covariate shifts that undermine model reliability. Despite this challenge, to our knowledge, no existing benchmar… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/WenjieZhao1/CURE-OOD · OpenReview ID：fziI7nE1vO

期刊：Transactions on Machine Learning Research · 摘要：We consider a setting where agents take action by following their role models in a social network, and study strategies for a social planner to help agents by revealing whether the role models are positive or negative. Specifically, agents observe a local neighborhood of possible role models they can emulate, but do not know their true labels. Revealing a positive label encourages emulation, while revealing a negative one redirects agents toward alternative options. The social planner observes all labels, but operates under a limited disclosure budget that it selectively allocates to maximize… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/knaggita/InformationDisclosure · OpenReview ID：jdcXfoENf0

期刊：Transactions on Machine Learning Research · 摘要：Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training. Nevertheless, increasing model sizes impose substantial computational demands on client devices, limiting FL applicability in resource-constrained settings. We introduce a novel multi-domain federated learning framework in which lightweight client-side proxy models collaborate with a server-side Foundation Model (FM) to learn new concepts without sharing private data. Our approach, EFFEKT, enables efficient server-side training of domain-specific LoRA adapters wh… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/LTTM/EFFEKT · OpenReview ID：jpUDUJfE1K

期刊：Transactions on Machine Learning Research · 摘要：Value-based offline RL methods are prone to overestimate the values of out-of-distribution (OOD) actions, and this is often addressed by regularizing the action-value function in the Bellman update. However, existing regularization methods can suffer from being too conservative, which can arise from over-penalizing the values for both in-distribution actions and out-of-support actions. We present a new regularization method for offline value-based methods, called Density-Scaled (DS) regularization, which penalizes the value function based on the relative action density of the behavior policy.… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/jackyxie5/density-scaled-regularization · OpenReview ID：nDPrzkQTj1

期刊：Transactions on Machine Learning Research · 摘要：Video Large Language Models (Vid-LLMs) have recently achieved strong performance across a wide range of video understanding tasks, including question answering, captioning, and multimodal reasoning. However, these models frequently produce outputs that are not faithfully grounded in the underlying video content, a phenomenon commonly referred to as hallucination. Compared with hallucination in text-only or image-based models, hallucination in video understanding is further complicated by temporal dynamics, motion interpretation, long-context dependencies, and event-level reasoning. In this su… · 篇幅：Long submission (more than 12 pages of main content) · OpenReview ID：qbO71rVrIG

期刊：Transactions on Machine Learning Research · 摘要：Numerical preprocessing remains a critical component of tabular deep learning, as the representation of continuous features can strongly affect downstream performance. We systematically study spline-based numerical encodings, including B-splines, M-splines, and integrated splines (I-splines), under uniform, quantile-based, target-aware, and learnable-knot placement. For the learnable variants, we adopt a differentiable knot parameterization that enables stable end-to-end optimization of knot locations jointly with the backbone. We evaluate these encodings on a diverse collection of public reg… · 篇幅：Long submission (more than 12 pages of main content) · 代码：https://github.com/mkumar73/tdl-numerical-encodings/ · OpenReview ID：str7wQt9Qc

期刊：Transactions on Machine Learning Research · 摘要：Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal control (SOC) problems, where learning an optimal generative dynamics corresponds to optimizing a control under SDE constraints. In this work, we revisit and generalize \emph{Adjoint Matching}, a recently proposed SOC-based method for learning optimal controls, and place it on a rigorous footing by deriving it from the \emph{Stochastic Maximum Principle} (SMP). We formulate a general Hamiltonian adjoint matching objective for SOC problems with contro… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/frankhan91/smp-adjoint-matching · OpenReview ID：tR5VsdQFhK

期刊：Transactions on Machine Learning Research · 摘要：Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), an online, risk-aware batch selection algorithm that improves training efficiency and distributional robustness. ESLM operates in two phases: (i) instance-level selection via a shallow early-exit model pass that computes proxy per-instance statistics (e.g., loss or entropy) and retains data points using value-at-risk thresholding; and (ii) loss shaping with token-level selection via risk-aware thresholdi… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/melisilaydabal/eslm · OpenReview ID：vcynsg6rMN

期刊：Transactions on Machine Learning Research · 摘要：Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like drug discovery and protein engineering. Existing models often rely on a multi-stage training process where autoencoders that tokenize data into latent representations are trained in a first stage. Secondly, a generative model is trained on the latent representation of the autoencoder(s), i.e., gene… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：wPfw7GkMns

期刊：Transactions on Machine Learning Research · 摘要：Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite extensive efforts, the mechanisms behind Adam's advantage over SGD in Transformer optimization are still not fully understood. In this study, we analyze the optimization of Transformer models in the fine-tuning setting through the lens of gradient heterogeneity, defined as the variation in gradient norms across parameter blocks. We provide a theoretical analysis showing that gradient heterogeneity, together with Hessian heterogeneity, degrades the converg… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/tom4649/gradient-heterogeneity · OpenReview ID：wZJcQb5m1e

期刊：Transactions on Machine Learning Research · 摘要：We study fixed-budget temporal memory for streams of probability distributions. The proposed representation is a piecewise-linear density protocol on a replay interval $[0,1]$: recent experience is stored near $t=1$, older experience is represented by intermediate-time marginals, and new experience is incorporated by a deterministic \emph{Compress--Add--Smooth} (CAS) recursion. In the Gaussian-mixture instantiation considered here, each protocol node stores a labeled $K$-component Gaussian mixture in $d$ dimensions, and each daily update costs $O(LKd^2)$ arithmetic operations for a fixed temp… · 篇幅：Long submission (more than 12 pages of main content) · 代码：https://github.com/mchertkov/compress-add-smooth · OpenReview ID：wjoixYG0mC

期刊：Transactions on Machine Learning Research · 摘要：We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice Learning (MCL) for Probabilistic Time-Series Forecasting (PTSF). Stabilized Instance Normalization (SIN), the core of TimePre, is a normalization layer that explicitly addresses the trade-off among accuracy, efficiency, and stability. SIN stabilizes the hybrid architecture by correcting channel-wise statistical shifts, thereby preventing the hypothesis collapse that otherwise destabilizes this combination. Extensive experiments o… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/LyCharles/TimePre/ · OpenReview ID：yQLnvkJMbP

期刊：Transactions on Machine Learning Research · 摘要：Matching for causal inference can be computationally expensive at scale and can silently change the target population when overlap is limited. We propose Centroid-Referenced Mahalanobis Matching (CRM), which replaces global pairwise search with stratified sampling in two reference coordinates: each unit's Mahalanobis distance from the treated centroid and its Fisher coordinate along the treated-control mean shift. All covariates enter through the treated covariance geometry; CRM is therefore not principal-component preprocessing followed by nearest-neighbor matching. For $n$ units and $p$ pre… · 篇幅：Long submission (more than 12 pages of main content) · 代码：https://github.com/KemingHu-D/crm-matching · OpenReview ID：z74epfCe3A

期刊：Transactions on Machine Learning Research · 摘要：Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions. However, achieving temporally and spatially consistent generation over long horizons remains an open challenge: existing approaches either compress past frames at fixed rates based on temporal proximity, discarding spatially critical information, or retrieve only a handful of relevant frames without increasing the total amount of retained history. In this paper, we propose WorldPack, a video world model that intr… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：zJuiG3PiNJ

期刊：Transactions on Machine Learning Research · 摘要：In this paper, In this paper, we introduce causal responder detection (CARD), a method for distributionalwe introduce causal responder detection (CARD), a method for distributional responder analysis that identifies treated subjects whose outcomes significantly depart from the control response distribution while controlling the false discovery rate (FDR) marginally over the tested treated population. CARD builds on the AdaDetect framework and, in randomized settings, inherits finite-sample FDR control under the exchangeability conditions required by AdaDetect when coupled with the Benjamini–H… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：zPt0o32mYn

期刊：Transactions on Machine Learning Research · 摘要：This paper presents \textbf{FairNVT}, a lightweight debiasing framework for pretrained transformer-based encoders that improves prediction fairness while preserving task performance. FairNVT is motivated by the intuition that reducing sensitive-attribute information in the representation used by the downstream classifier can facilitate fairer predictions. Our approach learns task-relevant and sensitive embeddings via lightweight adapters, applies calibrated Gaussian noise to the sensitive embedding, and fuses it with the task representation. Together with orthogonality constraints and fairnes… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：rzm6gZrYgl

期刊：Transactions on Machine Learning Research · 摘要：Joint Embedding Predictive Architectures (JEPAs) learn representations by predicting latent target embeddings from contextual views, but their predictors are typically shallow feed‑forward networks with limited control over multi‑step dynamics and stability. We introduce \emph{Learnable Iterated Function Systems} (LIFS), a recursive and contractive latent operator that replaces the standard JEPA predictor with a mixture of affine maps applied over multiple refinement steps. The mixture weights are conditioned on the context embedding, enabling input‑adaptive geometric structure while preservi… · 篇幅：Long submission (more than 12 pages of main content) · OpenReview ID：k2Z2gPOtlq

期刊：Transactions on Machine Learning Research · 摘要：Most vision models operate on 8-bit standard RGB (sRGB) images produced by dedicated image sensor processing pipelines designed for human perception rather than machine reasoning. In contrast, RAW images preserve sensor measurements, dynamic range, and fine-grained scene structure that can be critical for downstream understanding. Yet, progress in the RAW-domain vision remains limited by the lack of large-scale, high-quality benchmarks. To close this gap, we introduce RawDet-7, a multi-scenario benchmark for object detection and object description on quantized RAW images, comprising ~25k trai… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：UHTJrsYieo

期刊：Transactions on Machine Learning Research · 摘要：We introduce SLayR, Scene Layout Generation with Rectified flow, a novel transformer-based model for text-to-layout generation, which can integrate into a complete text-to-image pipeline. SLayR addresses a domain in which current text-to-image pipelines struggle: generating scene layouts that are of significant variety and plausibility, when the given prompt is ambiguous and does not provide constraints on the scene. In this setting, SLayR surpasses existing baselines, including LLMs. To accurately evaluate the layout generation, we introduce a new benchmark suite, including numerical metrics… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：YGsQxG5ubd

期刊：Transactions on Machine Learning Research · 摘要：Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embeddings form meaningful clusters. Our suite of benchmarking experiments uses encoders pretrained solely on ImageNet-1k with either supervised or self-supervised training techniques, deployed on image datasets that were not seen during training, and clustered with conventional clustering algorithms. This evaluation provides new insights into the embeddings of self-supervised models, which prioritize different features… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/scottclowe/zs-ssl-clustering/ · OpenReview ID：gdwg7ntmT5

期刊：Transactions on Machine Learning Research · 摘要：It remains a critical challenge to adapt policies across domains with mismatched dynamics in reinforcement learning (RL). In this paper, we study cross-domain offline RL, where an offline dataset from another similar source domain can be accessed to enhance policy learning upon a target domain dataset. Directly merging the two datasets may lead to suboptimal performance due to potential dynamics mismatches. Existing approaches typically mitigate this issue through source domain transition filtering or reward modification, which, however, may lead to insufficient exploitation of the valuable s… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/soulchanging/STC · OpenReview ID：TupiNRpgHw

期刊：Transactions on Machine Learning Research · 摘要：Nutritional interventions are important for managing chronic health conditions, but current computational methods provide limited support for personalized dietary guidance. We identify three key gaps: (1) dietary pattern studies often ignore real-world constraints such as socioeconomic status, comorbidities, and limited food access; (2) recommendation systems rarely explain why a particular food helps a given patient; and (3) no unified benchmark evaluates methods across the connected tasks needed for nutritional interventions. We introduce GLEN-Bench, the first comprehensive graph-language b… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：XMUbOKWsem

期刊：Transactions on Machine Learning Research · 摘要：Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks, but explicit revisitation also adds routing, coordination, and token cost. We study complete cyclic subtask graphs for large language model (LLM) agents: a workflow controller in which executable subtasks are fully connected and a unified state-analysis-and-routing agent selects transitions from natural-language criteria. We evaluate task-specific (Spec-Cyc) and benchmark-generic (Gen-Cyc) cyclic graphs on TextCraft, ALFWorld, and Finance-Agent against ReAct and dependency-directed acyclic workflows. The results… · 篇幅：Regular submission (no more than 12 pages of main content) · 代码：https://github.com/luaygz/cyclic_task_graphs · OpenReview ID：FAkarhXCfI

期刊：Transactions on Machine Learning Research · 摘要：Deep neural networks often suffer from poor generalization in long-tailed settings. From a loss landscape perspective, this degradation is largely attributed to the tendency of the optimization process to converge into sharp, unstable minima for underrepresented data. We investigate the recently proposed Muon optimizer, providing theoretical evidence that its gradient orthogonalization balances deterministic update strength across positive-curvature modes, thereby reducing the relative dominance of sharp directions. While effective, the Muon optimizer imposes heavy computational overhead in l… · 篇幅：Regular submission (no more than 12 pages of main content) · OpenReview ID：I19SJW09zn