什么火了

热点

今日热点 · 前 3

一件事为什么火、在哪些平台上榜、热度是涨是落。

看今日热点 →

AI 热点 · 前 3

只看和 AI、科技有关的热点。

看 AI 热点 →

最近的重大发布

各家 AI 模型的发布、开源和传言，官方消息和媒体报道分开标。

打开时间线 →

相关

按分类 · 2,106 个榜单

综合 · 热门站点

全部综合站点 →

科技 · 热门站点

全部科技站点 →

娱乐 · 热门站点

全部娱乐站点 →

游戏 · 热门站点

全部游戏站点 →

生活 · 热门站点

全部生活站点 →

知识 · 热门站点

全部知识站点 →

社区 · 热门站点

全部社区站点 →

更多

快讯

快讯来源

各家快讯一页排开，重要的标出来。

全部快讯来源 →

AI 资讯

常读的 AI 公众号和科技媒体，新文章都在这一页。

去看 AI 资讯 →

更多

金价

品牌

各家今天的金价多少钱一克，从低到高排好。

看今日金价 →

今天最低的 3 家

看足金饰品榜 →

相关

知识热榜

101 个榜单
今日全部9条查看完整榜单
  • 011.3万阅读
    剑来好评如潮完结
    大千世界，无奇不有。 我陈平安，唯有一剑，可搬山，倒海，降妖，镇魔，敕神，摘星，断江，摧城，开天！烽火戏诸侯
  • 027351阅读
    凡人修仙传（杨洋主演同名电视剧原著）脍炙人口完结
    一个普通山村小子，偶然下进入到当地江湖小门派，成了一名记名弟子。他以这样身份，如何在门派中立足,如何以平庸的资质进入到修仙者的行列，从而笑傲三界之中！ 　　 诸位道友，忘语新书《仙者》，经在起点中文网上传了，欢迎大家继续支持哦！忘语
  • 036159阅读
    青山值得一读
    当今名利已斩天下九分侠气，诸位，这是天下最后一分侠气的故事。会说话的肘子
  • 042878阅读
    校花的贴身高手不值一读
    传奇杀手回归都市，奉旨保护校花！ 我是校花的贴身高手，你们最好离我远一点，不然大小姐又要吃醋了！鱼人二代
  • 052674阅读
    绍宋好评如潮完结
    绍者，一曰继；二曰导。 公元1127年，北宋灭亡。旋即，皇九子赵构在万众期待中于商丘登基，继承宋统，改元建炎。 然而，三个月内，李纲罢相，陈东被杀，岳飞被驱逐出军，宗泽被遗弃东京，河北抗金布置被全面裁撤……经过这么多努力之后，满朝文武终于统一了思想，定下了拥护赵官家南下淮甸转扬州的辉煌抗金路线。 不过刚一启程，在亳州明道宫参拜了道祖之后，这位赵官家便一头栽入了闻名天下的九龙井中，起来后就不认得自己心腹是谁了！ 朕要抗金！可朕的心腹都在何处？！ 这是一个来自于九百年后灵魂的真诚呐喊，他在无可奈何继承了大宋的名号后，更要将这个朝廷与天下导向一条新路。 故称绍宋。榴弹怕水
  • 062534阅读
    诡秘之主（同名动画原著）神作完结
    蒸汽与机械的浪潮中，谁能触及非凡？历史和黑暗的迷雾里，又是谁在耳语？我从诡秘中醒来，睁眼看见这个世界： 枪械，大炮，巨舰，飞空艇，差分机；魔药，占卜，诅咒，倒吊人，封印物……光明依旧照耀，神秘从未远离，这是一段“愚者”的传说。爱潜水的乌贼
  • 072439阅读
    仙逆（同名影视原著）脍炙人口完结
    顺为凡，逆则仙，只在心中一念间… 仙逆动画，9月25日起每周一10:00腾讯视频火热播出，VIP抢先看2集；相约在动画中重新见证王林的一世执着！耳根
  • 082337阅读
    医道官途（神医官场流封神之作 · 大神作家石章鱼力作）好评如潮完结
    神医官场流封神之作！大神作家石章鱼力作！出版名《国医高手》。 隋末第一圣手张一针死在乱军中，再睁眼，成了九十年代春阳县人民医院的实习生张扬。没人知道，这具二十岁的身体里装着一千多年前的神医绝学。 别人看病救人，他看病铺路：治好谁，就结交谁；救过谁，就敢跟谁开口。妇科实习生、乡计生办代主任、副市长，直至主政一方的市委书记，他每治好一个人，就多一条路。 "当医生只能医人，而当官可以医国。"看一个隋朝神医，如何凭一针一手闯入官场核心。石章鱼
  • 092233阅读
    北派盗墓笔记脍炙人口
    【盗墓+悬疑+鉴宝】从南到北，江湖态，三教九流，这么多年从少年混到了中年，酒量见长，月蹉跎，我曾接触过许许多多的奇人异事，各位如有兴趣，不妨搬来板凳，听一听，江湖见闻。云峰
  • 102148阅读
    神秘复苏好评如潮完结
    “我叫杨间，当你看到这句话的时候我已经死了......” 一张诡异的羊皮卷，一只窥视黑暗的眼睛，这是一个活下来的人经历的故事。 ——————佛前献花
  • 112145阅读
    天之下好评如潮
    【9月4日实体书开售！】【第三部小说连载中，每周五14:00点更新】昆仑纪元，分治天下的九大门派为新一届盟主之位明争暗斗，关外，萨教蛮族卷土重来……乱世中，芸芸众生百态沉浮，九大家英杰辈出，最终汇成一首大江湖时代的磅礴史诗，并推动天下大势由分治走向大一统。三弦
  • 121962阅读
    牧神记（同名国漫原著）好评如潮完结
    大墟的祖训说，天黑，别出门。 大墟残老村的老弱病残们从江边捡到了一个婴儿，取名秦牧，含辛茹苦将他养大。这一天夜幕降临，黑暗笼罩大墟，秦牧走出了家门…… 做个春风中荡漾的反派吧！ 瞎子对他说。 秦牧的反派之路，正在崛起！宅猪
  • 131894阅读
    凡人修仙之仙界篇值得一读完结
    凡人修仙，风云再起 时空穿梭，轮回逆转 金仙太乙，大罗道祖 三千大道，法则至尊 《凡人修仙传》仙界篇，一个韩立叱咤仙界的故事，一个凡人小子修仙的不灭传说。 特说明下，没有看过前传的书友，并不影响本书的阅读体验，但感兴趣的书友，也可以先去看看《凡人修仙传》，再来看本书哦。 诸位道友，忘语新书《仙者》，经在起点中文网上传了，欢迎大家继续支持哦！忘语
  • 141819阅读
    斗破苍穹好评如潮完结
    这里是属于斗气的世界，没有花俏艳丽的魔法，有的，仅仅是繁衍到巅峰的斗气！ 　　新书等级制度：斗者，斗师，大斗师，斗灵，斗王，斗皇，斗宗，斗尊，斗圣，斗帝。 …… 斗破苍穹年番动画，每周日10:00正在腾讯视频火热播出，VIP抢先看2集；于深渊涅槃，收陨落心炎！斗破官方首套盲盒上市！更有惊喜隐藏款等你入手！天蚕土豆
  • 151606阅读
    庆余年（同名电视剧原著）好评如潮完结
    积善之家，必有余庆，留余庆，留余庆，忽遇恩人；幸娘亲，幸娘亲，积得阴功。劝人生，济困扶穷……而谁可知，人生于世，上承余庆，终究却是要自己做出道路抉择，正是所谓岔枝发： 　　东风携云雨，幼藤吐新芽。 　　急催如颦鼓，洗尽茸与华。 　　且待朝阳至，绿遍庭中架。 　　更盼黄叶时，采得数枚瓜。 　　…… 　　…… 　　《庆余年》同名影视剧由张若昀、李沁、陈道明、吴刚等主演，11月26日起在腾讯视频、爱奇艺开播。猫腻
  • 161576阅读
    玄鉴仙族脍炙人口
    陆江仙熬夜猝死，残魂却附在了一面满是裂痕的青灰色铜镜上，飘落到了浩瀚无垠的修仙世界。 凶险难测的大黎山，眉尺河旁小小的村落，一个小家族拾到了这枚镜子，于是传仙道授仙法，开启波澜壮阔的新时代。 (家族修仙，不圣母，种田，无系统，群像文)季越人
  • 171323阅读
    首席御医（神医官场流开山之作）好评如潮完结
    神医官场流开山之作！挽救你的生命，即挽救你的政治生命！冬奥冠军王濛推荐，银河九天口碑神作，出版名《首席医官》。 实习报到第一天，曾毅就干了件轰动省人民医院的事：直言国内顶尖专家治疗方案错误。 老专家们拍桌怒斥，他直击病症核心，几剂中药，领导夫人病根尽除！ 望闻问切出神入化，针灸正骨化有形为无形，国医大师也对他青眼有加。 凭借一身中医绝学，曾毅成为领导的健康顾问，一步步走进权力中心。 省医疗保健专家、卫生局长、招商主任，直至主政一方。面对官场中的利益博弈与人情考验，他以医术立身，以智慧破局，在风云变幻的仕途中不断成长。 “上医医国，中医医人，下医医病。” 看一介中医，如何凭一身医术闯入官场核心，为百姓谋福祉，为国医争尊严！银河九天
  • 181317阅读
    没钱修什么仙？脍炙人口
    老者：“你想报仇？” 少年：“我被强者反复侮辱，被师尊视为垃圾，我怎么可能不想报仇？” 老者摸了摸少年的脑袋，叹道：“好孩子，我来传功给你吧。” 少年惊道：“前辈！这怎么行？” 老者伸出手：“把你手机给我。” 少年看着手机上的变化，震惊道：“前辈！这哪里来的百年功力？” 老者微微一笑：“好孩子，这是你在天庭的备用功力，以后急用的时候随用随取，别再被人侮辱了。” 少年皱眉：“这不是法力贷吗？我怕……” 老者：“天庭是大平台，新用户借百年功力有30天免息，日息最低半天功力，还没你吐纳一周天多。” …… 张羽冷哼一声，关掉了上面的广告。熊狼狗
  • 191291阅读
    盗墓笔记好评如潮完结
    50年前由长沙土夫子（盗墓贼）出土的战国帛书，记载了一个奇特战国古墓的位置，50年后，其中一个土夫子的孙子在他的笔记中发现这个秘密，纠集了一批经验丰富的盗墓贼前去寻宝，谁也没有想到，这个古墓竟然有着这么多诡异的事情：七星疑棺，青眼狐尸，九头蛇柏。这神秘的墓主人到底是谁，他们到底能不能找到真正的棺椁？故事悬念重重，情节跌荡，值得一看。南派三叔
今日全部19条查看完整榜单

arXiv · cs.NE

3小时前更新
  • 01
    Pricing Symbolic Rules by What GNNs Leave Unlearned
    Symbolic knowledge (motif counts, ring counts, label constraints) is routinely added to graph neural networks (GNNs) and justified by their limited expressivity. We replace this yardstick with an exact one. The largest log-loss reduction a rule $S$ can give a model family is $I(Y;S\midσ)$ given what the family computes; every realised gain splits exactly into this term plus repaid neural debt; and for a trained network with representation $T$ the value is $I(Y;S\mid T)$, the label information trSatabarto Sarkar
  • 02
    Maximizing Detection Probability in UAV Search Missions using Random-Key Optimizers
    This paper focuses on the stochastic and real-time constraints of Unmanned Aerial Vehicle (UAV) path planning in Search and Rescue (SAR) missions. We introduce a configurable data-driven and intelligent routing architecture that combines a closed-loop probability update with the Random-Key Optimizers (RKO). Our problem is mathematically modeled as a dynamic probabilistic variant of the Open Vehicle Routing Problem (OVRP), enabling the solver to switch adaptively between two objectives, thereby bAntonio Dantas
  • 03
    A method to automatically discover symbolic local learning rules
    We present a general method for discovering symbolic local learning rules that can replace backpropagation, applicable, in principle, to any deep learning architecture and task. The method automatically discovers local loss functions specific to each layer by (1) constructing a dictionary of monomials of local tensor variables, inspired by Penrose diagram notation, (2) regressing over coefficients weighting these monomials to build layerwise polynomial losses whose gradients together minimize aAndrea Perin
  • 04
    AscendMOEA: An Ascend NPU-Accelerated Platform for Tensorized Multi-Objective Evolutionary Algorithms
    Multi-objective evolutionary optimization increasingly involves large populations, expensive problem evaluations, and diverse algorithmic structures. These workloads expose the limited parallelism of loop-based implementations, while rewrites for accelerator execution can alter selection order, tie handling, and population updates. AscendMOEA is presented as a scalable platform that executes multi-objective evolutionary algorithms (MOEAs) on Huawei Ascend neural processing units (NPUs) and conveQianlong Dang
  • 05
    Attention Is Only as Good as Its Witnesses: When Higher-Order Layers Help, and When They Do Not
    Transformers stop learning graph search as graphs grow, and learn the card game SET only after many distinct questions, although attention can represent both. We read these failures, and the uneven record of higher-order attention, from what a layer sums over: each layer we study computes the partition function of a family of witnesses and reads it at a temperature. Two laws follow. The depth law is a known result of logic, which we state for these layers: L layers over two-step walks reach exacMostafa 'Neo' Mohsenvand
  • 06
    Understanding Spike Encoding across IoT Sensing Modalities: An Empirical Study
    Spiking neural networks (SNNs) offer a path to energy-efficient sensing on Internet of Things (IoT) devices. The input encoder shapes that opportunity by changing the cues available for recognition and the work required to process them. We study these choices across wireless, inertial, surface electromyographic, and tactile sensing. For wireless activity recognition, interleaving reduces estimated energy for arithmetic in the network layers, latency from the prepared input window to returned scoYuxuan Hou
  • 07
    Neural Activity Synchronization-Based Fast Local Learnable Spiking Neural Network Architecture
    Implementing intelligent learning systems on low- power edge devices is challenging due to the high compu- tational complexity, training latency, and energy demands of traditional Artificial Neural Networks (ANNs). Spiking Neural Networks (SNNs), biologically plausible and spike-driven, come as an alternative. However, SNN training commonly relies on backpropagation through time (BPTT), which is computationally expensive, inherently global, and unsuitable for battery-driven devices. This work prPranith Dutta
  • 08
    The forces at hand: social learning is permissive, not instructive, for the evolution of phenotypic plasticity
    Evolution can favour a trait for two reasons: an instructive cause makes selection favour the trait; a permissive one lets it persist once selection no longer removes it. The distinction matters most for phenotypic plasticity and its replacement by inherited behaviour, genetic assimilation, the Baldwin effect. Social learning is credited with favouring plasticity on evidence that cannot tell the two apart: how much plasticity remains at the end of a simulation. Here we show, analytically and comNam H. Le
  • 09
    Bridging Spiking and Continuous Dynamics in Spiking Neural Networks: A Muscle-Inspired Model
    Transforming the spike trains produced by spiking neural networks (SNNs) into continuous signals through biologically inspired mechanisms remains an open challenge in generative and regression tasks. In biological systems, a similar transformation occurs when muscles integrate neural spikes to produce smooth, coordinated movements. Inspired by this mechanism, we introduce a muscle-response model, a biologically motivated dynamical layer that converts spike trains into continuous representations.Maryam Soltani
  • 10
    OMCDE: Opposition-based Multi-Stage Matrix-Based Competitive Differential Evolution
    Differential Evolution has proven to be an effective algorithm for continuous global optimization, but it's modern high-performing variants often introduce additional complexity and computational cost. We propose OMCDE, a matrix-based competitive Differential Evolution algorithm that aims to improve optimization performance while maintaining computational efficiency. The proposed approach integrates competition-driven search dynamics, adaptive behavior between optimization stages, and oppositionMohammad Sarhangzadeh
  • 11
    Circuit Theory-Informed AI for Condition Monitoring in Power Electronics
    Artificial intelligence for power electronics is evolving toward a deeper comprehension of system intrinsic behaviors and dynamics. As a novel integration of neural computation and electric circuits, spike-based neuromorphic computing offers promising potential in high energy efficiency and adaptability for data-driven applications. Building on the latency-coding principles, this article proposes a framework for data-light condition monitoring that relies solely on three-phase AC current measureYubo Song
  • 12
    Two-Layer Evolutionary Scheduling for Machine Learning Jobs in Multi-Cluster Environments
    The rapid growth of large-scale machine learning (ML) workloads has led to unprecedented demands on GPU cluster scheduling systems. However, existing heuristic schedulers struggle to handle the complexity and dynamics of multi-cluster GPU environments, often leading to load imbalance, long queuing delays, and poor alignment to business objectives. This paper formulates the ML scheduling problem in multi-cluster GPU environments as online multi-objective optimization that minimizes the average anJingyuan Xu
  • 13
    SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
    LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decodQile Jiang
  • 14
    Invariance before structure: two modes of emergent compression in representation learning
    Learned representations show striking invariance across biological and artificial neural networks, with different substrates and variations driven by drift, heterogeneity and initialisation. To understand this invariance, we propose Emergent Adaptive Representation Learning (EARL), a framework that distinguishes two modes of emergence in learned representations: state-space compression, where a learned representation gains predictive power over its own future beyond what the network's units canHardik Rajpal
  • 15
    Projection-Free Gradient Tracking Neurodynamic for Distributed Nonnegative Sparse Optimization
    This paper proposes a continuous-time, projection-free neurodynamic system based on gradient tracking for distributed nonnegative sparse optimization. Unlike traditional methods, our approach avoids projecting states onto the feasible set. Instead, it employs gradient tracking to estimate average gradients under heterogeneous costs, coupling primal and dual dynamics such that feasibility and sparsity emerge naturally from the equilibrium conditions. The system ensures unique solutions through aJuntao Li
  • 16
    When Does Blockwise Additivity Break? Diagnosing and Repairing the Additive Assumption in Distillation-Based Architecture Search
    Blockwise distillation methods for architecture search, such as DNA, DONNA, LANA and Puzzle, score each candidate replacement block in isolation and assemble a child network by minimizing the sum of per-block scores. We test this additive assumption on DeiT-S and DeiT-B with seven replacement blocks per layer, seven block-latency budgets from 70% to 40%, three fine-tuning seeds and paired bootstrap confidence intervals. (i) At mild compression the additive integer linear program (ILP) is close tYuefeng Xu
  • 17
    Learning Time-Varying Connectomes for Stable Behavior Across Development
    Neural circuits must maintain functionality to drive effective behavior while their size, topology, geometry, and intrinsic dynamics change across development. To model developing visuomotor circuits and behavior, we investigated whether a single compact generative encoding could produce functional recurrent controllers across such changes. Building on the HyperNEAT algorithm, we represented this program as a compositional pattern-producing network that received developmental time as an input toChristof Fehrman
  • 18
    Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes
    The best classical optimizer for a continuous black-box problem depends on its budget and landscape. Existing routers decide from the dimension and budget, past improvement or features fitted to one benchmark, and few test an optimizer's implicit assumptions online. AMM (Adaptive Multi Mode) routes a known budget among quasi-Newton, trust-region, coordinate, multistart and evolution-strategy optimization engines with online probes of curvature, plateaus, separability, kinks, basins and fractal sBenjamin Jacob Bodner
  • 19
    SpikePose: Lightweight Video Human Pose Estimation
    Efficient video human pose estimation must balance localisation accuracy, motion quality, and energy cost. We present SpikePose, a lightweight video pose estimator that pairs a frame-reset, single-step spiking encoder with motion-aligned heatmap memory (MAM). The encoder supplies per-frame spatial evidence, while MAM estimates joint displacement, aligns historical heatmaps, and adaptively fuses them with current predictions. By confining temporal reasoning to a compact, lightweight module outsidYunhao Huang
  • 20
    From Admission to Retention: Predicting Durable Offspring in Quality-Diversity Search
    Automated failure discovery can be framed as a diversity problem: the objective is to expose distinct ways a system fails rather than a single critical adversarial case. Yet uniform parent sampling provides no way to allocate search effort toward individuals likely to produce durable archive contributions. We study this credit assignment problem in an unstructured Quality-Diversity (QD) archive, testing whether signals available before an individual has reproduced distinguish offspring that mereCorrado Calamita
  • 21
    Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning
    Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory fragmentation caused by theXi Chen
  • 22
    Explainable Anomaly Detection in 5G Networks through Continuous Time Graphs
    5G networks increasingly resemble distributed systems in their design. It then becomes crucial to move beyond traditional network-based detection methods and to explore alternative approaches. In this work, we propose a formalization of 5G network exchanges as a dynamic graph, on which we apply techniques from the field of graph-based learning to detect anomalies effectively. This representation allows for fine-grained analysis of packet-level semantic content, while simultaneously capturing seqThomas Hoger
  • 23
    Mobility-Aware Mobile Edge Computing for Energy-Balanced Data Collection in IoT-Enabled Underwater Sensor Networks
    Underwater wireless sensor networks (UWSNs) face critical challenges in energy imbalance, connectivity, and data collection due to harsh environments. To address these issues, this paper focuses on the problem is how to achieve energy-balanced data collection in IoT-enabled UWSNs with a mobility-aware mobile edge computing (MEC), named MECEBDC. Unlike existing approaches, the proposed scheme jointly optimizes energy-aware clustering, cluster head selection, and AUV-assisted data collection. FurtNguyen Thi My Binh
  • 24
    Neural networks and games
    Hopfield neural networks and noncooperative games provide seemingly different approaches to understanding how collective outcomes emerge from local interactions. In a neural network, individual units adjust their states according to local signals; in a game, players choose actions to maximise individual payoffs. I establish an exact equivalence between symmetric binary Hopfield networks and binary-action games that admit a quadratic potential. The equivalence identifies stable network configuratPhilip R. Neary
  • 25
    Learning Behaviorally Relevant Dynamics in Multimodal Neural Recordings
    Multimodal neural data can enable a more complete understanding of brain dynamics underlying behavior. Modalities such as spiking activity, local field potentials (LFPs), and behavior capture diverse spatiotemporal aspects of brain processes, yet prior neural-behavioral models that separate sources of variability rely on a single neural modality. By leveraging these complementary strengths, multimodal neural fusion can provide a unified, rich representation of brain-behavior processes and addresParastoo Azizeddin
  • 26
    Solving the Nonlinear Westervelt Equation in Ultrasound Propagation Using Physics-Informed Neural Networks
    Modeling the nonlinear acoustic wave propagation in biological tissues needs accuracy, especially in ultrasound imaging and therapeutic applications. The 1D Westervelt equation, \( p_{xx} - p_{tt} + γ\, p_{ttt} + η\,(p^{2})_{tt}=0, \) could be used to describe a finite-amplitude ultrasound propagation in these tissues. This equation accounts for nonlinearity, \(η\), and attenuation, \(γ\). To solve this equation, we observe that traditional solvers may struggle to do so correctly. This is due toLuke Oluwaseye Joel
  • 27
    Refined CMA-ES for CEC 2026 Bound-Constrained Single-Objective Optimization
    We present a simplified and parameter-adjusted variant of CMA-ES designed for the CEC 2026 Bound-Constrained Single-Objective Optimization competition. Unlike typical algorithmic developments that increase complexity by adding mechanisms, Refined CMA-ES systematically removes components that do not improve performance, such as the flat-land escape, while retaining standard features that provide measurable benefits. Adjusting key parameters (population size and initial step-size) yields substantiAdam Stelmaszczyk
  • 28
    Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks
    Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain. We propose a structured visual representations landscape and design an activation-based prior that allows us to effectively regularize the landscape with activations from brain regions or neural network unitYusong Zhao
  • 29
    Exact Fusion of Softmax Attention Heads Can Require Exponentially Many Atoms
    Fusing independently normalized attention heads can increase the number of explicit key-value entries, or atoms, needed to preserve their output. We prove a sharp separation for $W_d(q)=\sum_{j=1}^dσ(q_j)$: its $d$ two-atom heads use $2d$ head-atom terms, whereas its minimum single-head representation has exactly $2^d$ atoms, even with arbitrary fixed replacement keys, scalar values, and positive masses. The same lower bound holds for every fixed uniform error below $1/2$ on $\mathbb R^d$, and tHiroyasu Usami
  • 30
    Iterated Narrow Networks: Turing Completeness at Width 4 on Convex Input Spaces and the Complexity of Verification
    We study the iterates of a fixed ReLU network $N$ of width 4, that is, the discrete-time system $x_{k+1} = N(x_k)$ on $[0,1]^4$. Equivalently, $x_k$ is the output of a weight-tied network made of $k$ copies of $N$, or of a recurrent network with no external input, started at $x_0$. We prove that every deterministic Turing machine $M$ admits such a network $N_M$. The network can be constructed in polynomial time from $M$. Each iteration has depth $\mathrm{poly}(|M|)$. The iterates of $N_M$ simulaOlivier Bournez
  • 31
    HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing
    We present HyVox, a hybrid neuromorphic--von Neumann system for low-energy open-set speaker identification under tight energy budgets. HyVox splits the workload at the speaker embedding. A neuromorphic processor embeds the speech with sparse, event-driven computation, and a von Neumann microcontroller holds the speaker gallery and makes every decision: it scores queries by cosine similarity, rejects unknown speakers, and enrolls new users by writing a prototype, with no weight update. On the neuSnehasis Addy
  • 32
    Exposure-Length Trade-off Optimization for Obstacle-Aware Intrusion Paths in Heterogeneous Wireless Sensor Networks
    Barrier coverage is a key paradigm for intrusion detection and surveillance in IoT-enabled heterogeneous wireless sensor networks, where monitoring quality depends not only on the existence of sensing barriers but also on the detectability of feasible crossing paths. In this paper, we study the obstacle-aware maximal exposure path planning problem in heterogeneous sensor fields under truncated omni-directional sensing and line-of-sight occlusion. Unlike conventional maximal exposure formulationsNguyen Thi My Binh
  • 33
    Is Newborn Wiring Special? Separating Wiring from Weight Placement in Connectome Reservoirs
    Reservoir computing offers a way to study the brain's wiring before it is even trained. The recurrent network remains fixed, while only a linear readout is trained. The human connectome is found to perform better than randomly rewired versions of itself, suggesting that biological wiring is special. To understand the source of this advantage, a mathematical graph-theoretic decomposition is introduced. Rewiring a weighted network changes both the regions that are connected and the weights assigneRiccardo Bertamini
  • 34
    A Tool in the Forward Pass: Frozen Tape Modules as Layers of a Small Language Model
    Calling a tool through generated text adds decoding steps, even when the computation itself is short. We study an alternative: a small neural module that runs inside a language model's forward pass. A learned writer turns hidden states into a symbolic tape, a short sequence of discrete symbols that encodes the computation. The module, trained separately and then frozen, reduces the tape to a result, and a learned reader returns that result to the model. We evaluate arithmetic and object trackingMichael Granitzer
  • 35
    Boosted Physics-Informed Neural Networks for Solving Homogeneous and Non-Homogeneous Lane-Emden Type Equations
    The Lane-Emden Equation is a class of nonlinear differential equations commonly used to model phenomena in astrophysics and mathematical physics, such as stellar structure and thermal behavior in polytropic gas spheres. This study presents a novel hybrid framework that integrates Physics-Informed Neural Networks (PINNs) with boosting methods to enhance the accuracy and robustness of solutions for Lane-Emden type differential equations. Standard PINNs leverage physical laws encoded within the losLuke Oluwaseye Joel
  • 36
    From Connection Loss to Collision: Closed-Loop Fault Assessment of a Fly-Connectome SNN
    The public release of the complete adult fruit-fly brain connectome enables brain-scale spiking-network studies, motivating closed-loop assessment of connection loss. We test a connectome-derived controller in synthetic pursuit-escape and check record consistency. Across 576 test episodes in paired campaigns, the baseline mapping at 50% connection-row deletion yields 11/48 proportional and 0/48 relay collisions by 1 s, despite paired P/R trigger/burst schedules. The prespecified secondary relay-Shuchao Gao
  • 37
    Proof-Carrying Evolution: Black-Box Search, White-Box Flight
    We study whether a language model can help design controllers whose behavior can be formally checked. In proof-carrying evolution (PCE), a search proposes controllers together with their certificates. Their mathematical forms are fixed; a proposer chooses their numerical parameters together. Certificate checks guide selection, and only a certified candidate can be returned. The deployed artifact is a control law and its certificate; the language model is used only during design. We compare fourAmit Jain
  • 38
    In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents
    Long-horizon LLM agents play an important role in solving complex and sustained tasks, with ever-growing interaction contexts. However, these accumulated contexts will raise substantial computational cost and obscure key decision-relevant evidence. Existing methods typically train external compressors or context-management agents to rewrite context as shorter hard-token sequences, but such external selection may not align with the LLM's evolving representation and is necessarily lossy. In this pXuning He
  • 39
    Input-dependent Neuromodulation Enhances Mixed-Signal Neuromorphic Hardware
    Gating mechanisms allow a fixed neural network to adapt its computation to the current input by dynamically modulating its effective parameters. In the brain, neuromodulation uses this principle to move neural circuits between dynamical regimes, and deep learning exploits input-dependent gating, e.g., in gated recurrent networks and self-attention. Input-dependent modulation has also recently been shown to improve spiking neural networks, with particularly strong benefits in small, parameter-limAashman Mehta
  • 40
    Memory and Recall of Color Images Using Neural Networks-1 - The Cue-Ball Model based on the Associative Memory Mechanism -
    This paper presents a neural network model for storing and recalling color images of different sizes using the Cue BallRecall Net systems [1,2,3,4,5]. The Cue Ball system consists of a Recall Net composed of multiple memory neurons each responsible for memorizing a single, distinct memory and a large number of neurons that represent image patterns. The images used in this study [6] consist of ten images(see Appendix). The pixel values of these images were converted into digital values and used fHiroshi Inazawa
  • 41
    Local Budget Benefits, Population Commitment, and Solver Performance: A DGO Case Study with Controlled DE Transfer
    An evaluated candidate can improve a local search step, alter the population used by later steps, and affect a solver's final result. We distinguish these three questions using Da Gou Gun Optimization (DGO), a population optimizer designed for this study. Its JQ100 configuration evaluates an interpolation candidate during a two-sided probe. We define local budget value, population commitment effects and complete-policy performance, and give an exact example in which a locally better commitment lShiqi Li
  • 42
    Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
    Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer detail does not necessarily require more global communication: low-frequency structure benefits from global exchange, while high-frequency detail can be modeled locally. Based on this insight, we introduce SpecSlot, a pixel-space rectified-flow Transformer that decouples output detail from the length oJiongfan Yang
  • 43
    Dynamic Powergrid Optimization with FPGA-based Neuromorphic Higher-order Ising Machines
    The advent of large, high-density FPGAs such as the AMD Versal enables efficient hardware implementation of neuromorphic Ising machines, unlocking unprecedented performance for complex combinatorial optimizations. A critical application for this computing paradigm is dynamic powergrid optimization, specifically Distribution Network Reconfiguration (DNR), which seeks to mitigate severe resistive losses and reduce electricity costs by optimizing network switch configurations in real time. This papSaptarshi Maiti
  • 44
    AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn
    Humans and animals have a unique capacity to generalize and learn in novel circumstances, including "0-shot" inference (ZI) and continual learning (CL) -- two powerful cognitive abilities. Despite this importance, efforts to model ZI and CL are seriously limited in several ways. First, existing models typically lack components critical to ZI and CL in the brain, namely, strong inductive biases (for ZI) and autonomous control of learning (for CL). Second, models can be less tractable to analysisDaniel Levine
  • 45
    HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization
    Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization tarJianghan Zhu
  • 46
    AI at a Turning Point: From ChatGPT through Neural Networks to Neuromorphic AI
    The tension between the established technologies of connectionist AI and their neuromorphic challengers is attracting growing attention, above all because of the enormous energy demand of the former and the low power consumption of the latter. Developing and running large AI models consumes gigawatt- to terawatt-hours of energy, while the human brain operates on a continuous 20 watts. Spiking neural networks (SNNs) counter this energy demand with a frugal approach and bring elements of self-orgaVolker Kempe
  • 47
    Diagnosing Optimizer-Landscape Interaction via Representation in Subset Selection Multitasking: Evidence from Piano Fingering
    Continuous relaxations are commonly used as an encoding scheme for evolutionary multitasking optimization (EMTO), allowing heterogeneous tasks to be optimized within a unified search space. However, these continuous representations fundamentally reshape the induced fitness landscape, and their impact on optimization behavior and knowledge transfer remains underexplored. In this work, we bridge the gap by analyzing the interaction between the representation-induced fitness landscape and optimizerAnanda Phan Iman
  • 48
    Hardware-Aware Model Inversion in Memristive Spiking Neural Networks
    Hardware-accelerated spiking neural networks (SNNs) implemented on memristive crossbar arrays offer significant gains in energy efficiency, while device variability and analog noise are sometimes assumed to hinder information extraction. However, whether these hardware effects improve, preserve, or degrade privacy after deployment remains largely unexplored. Therefore, we ask whether model-inversion leakage characterized on an SNN remains representative after the same model is mapped to a non-idPablo Sorrentino
  • 49
    GC-LIF: Spiking Group-Equivariant Neural Network With Group-Coupled Membrane Dynamics
    Spiking neural networks (SNNs) promise event-driven, low-power inference, but on vision tasks they still acquire rotation invariance only through data augmentation. Group-equivariant CNNs build such symmetries into the architecture, yet a faithful spiking analogue is missing: a leaky integrate-and-fire (LIF) neuron placed after a $G$-equivariant convolution can break equivariance through its membrane recurrence. We give a necessary and sufficient condition for this not to happen. The layer is eqNhan Trong Luu
  • 50
    FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss
    Formula-Driven Supervised Learning (FDSL) enables vision pre-training without real images, but existing methods cast pre-training as classification on discretized labels, discarding continuity in the generative process. We propose Formula-Driven Supervised Metric Learning (FDSML), which derives relational supervision from image-generation parameters beyond discrete class labels. FDSML combines FineFractalDB, our refined fractal dataset with higher intra-class variation and more stable structuresHina Otake
  • 51
    MulClip: A table-free activation function with monotonic and folding regimes for reservoir computing on microcontrollers
    This letter proposes MulClip, a lightweight activation function for reservoir computing (RC) on microcontrollers (MCUs). In a ring reservoir, a representative sparse RC topology, multiply-accumulate operations are few, and evaluating tanh accounted for 75% of the state-update time on a Cortex-M4. MulClip introduces curvature into the response using only comparison, absolute value, multiplication, and subtraction, and places its clipping threshold not at the extremum but at the point where the reGuren Matsumura
共 2000 条查看完整榜单
今日全部53条查看完整榜单

LessWrong · 历史高分

24分钟前更新
今日全部50条查看完整榜单
共 8 条查看完整榜单
  • 012143阅读
    兰香缘（谭松韵‌、‌刘学义主演电视剧《兰香如故》原著）值得一读完结
    她是首辅的孙女，家族卷入夺嫡风波获罪。 与新婚丈夫双双死在发配途中。 她带着记忆重来，成为江南望族林家的家生丫鬟陈香兰。 这是一个小丫鬟想脱离宅门而不得的故事 《兰香缘》简体实体书已上市，可到淘宝、拼多多搜索“兰香缘”下单购买禾晏山
  • 021369阅读
    天灾第十年跟我去种田好评如潮
    熬过核污染水排海、全蓝星火山大爆发和伽马射线暴之后的天灾第十年，夏青昂首挺胸走出安全区。 谁都别拦着我，我要去种田。 领地里的羊？同伴。周边进化林里的狼？邻居。熊？交易对象。猴和松鼠？姐的员工！ [有男主，戏份不多]南极蓝
  • 031173阅读
    长安好好评如潮完结
    京城那位胆小娇弱的第一美人不幸落到了人贩子手中。 京中众人摇头叹息：这波要完。 千里之外，废物美人睁开眼睛，反手就把人贩子给卖了—— …… 换了芯儿的少女挥霍着贩卖人贩子得来的银钱回到都城，才发现昔日的小弟如今都成了大佬，且一个个的都把“她”当作女儿养—— 一，二，三，四…… 所以，如今她竟有四个男妈妈?！ …… 本文又名《美强惨女主重生后》《废物美人她为何突然倒拔垂杨柳》《我行我上，众卿平身》非10
  • 041167阅读
    白骨小组
    警方在深山中发现两具白骨：一名年轻孕妇，和她尚未出世的胎儿。 法医鉴定显示，女子生前曾遭剖腹取子，手法与二十年前一桩悬案惊人一致。 小镇姑娘冯思姜，貌美单纯，她遇到年轻英俊的游客周暮阳，如同飞蛾扑火，坠入爱河。为了逃离原生家庭压力，她决定随他离开小镇，奔赴新生活。丁墨
  • 051122阅读
    农家小福女神作完结
    周家的四哥赌输了钱，母亲病重，赌场的人还想让满宝偿债。 村里人都说周家的宝贝疙瘩好日子到头了，老娘也握着满宝的小手哭唧唧。 满宝却手握系统，带着兄弟嫂子们开荒，种地，种药材，开铺子…… 日子越过越好，嫂子们却开始忧心满宝的婚事。 满宝抿嘴一笑：“我早就想好了，就选被我从小揍到大的竹马白善宝。” 坑品有保证，已完结的作品有《林氏荣华》《重生娘子在种田》等六本书。郁雨竹
  • 061078阅读
    御兽从零分开始脍炙人口
    睁开眼，乔桑发现自己穿成了初中生。 紧接着来了一场模拟考。 985毕业她怕了吗？ 她怕了…… 这考的都什么啊！ 臭臭鳅的最终进化形态叫什么？ 人类已移民的星球都有哪些？ …… …… 欢迎来到御兽世界。给我加葱
  • 07935阅读
    如意事脍炙人口完结
    ————新书《逢晴日》正在更新中———— 许明意再次睁开眼睛的时候，回到了十六岁身患怪病的那一年。 这时，她那老当益壮的祖父正值凯旋——“路上救下的这位年轻人长得颇好，带回家给孙女冲喜再合宜不过。” 于是，昏迷中被安排得明明白白的定南王世孙就这么被拐回了京城…… ——————非10
  • 08921阅读
    末日乐园好评如潮完结
    【2024年新书《伪像报告》连载中】 【2023年新书《野鹿便利店》恐怖超短篇完结可宰】 “我觉得……我男朋友好像想杀掉我。” 林三酒喃喃地说道。 想起自己多金帅气又温柔的男友，她不禁浑身打了个冷战。 由身边人亲手拉开帷幕的末日地狱， 正向她呼啸而来。 **本文非爽文**须尾俱全
  • 09915阅读
    墨桑神作完结
    李大当家和她家一户口本男人的故事…… ……………… 详细版： 黑马:我姓马，名少卿，字云灿，号黑马（是因为心黑，不是因为脸黑！）。马爷我大家出身，琴棋书画诗酒花样样精通，我为我家桑老大站台! 大常:我姓常，名山，伟岸如山，稳重如山，我为我家桑老大站台! 大头:我姓李，名首，字大头，我为我家桑老大站台! 蚂蚱:我姓李，名蝗，字蚂蚱，我为我家桑老大站台! 窜条:我姓李，名鱼，字窜条，我为我家桑老大站台! 小陆子:我姓陆，名乘风，我想姓李，老大不让（委屈），我为我家桑老大站台! 顾晞:等等我！我是男主！李姑娘别抛下我，我要跟你一起出海浪!闲听落花
  • 10884阅读
    逢晴日好评如潮完结
    天和十二年，隆冬，大雪夜，十一岁的少微挥刀斩断亲缘，孤身下山而去。 那夜，像路边倒霉的野狗一样莫名挨了她一顿揍的皇子刘岐从地上爬起来，擦了擦鼻血，站在大雪中，目送那道浑身是血的背影消失。 …… 【注:成长型女主，非女帝，非大女主； 是言情，有男主，宝们请按照口味选择是否入坑；】非10
  • 11783阅读
    琅琊榜神作完结
    一卷风云琅琊榜，囊尽天下奇英才。 　　讲述了“麒麟才子”梅长苏才冠绝伦，以病弱之躯拨开重重迷雾、智博奸佞，为昭雪多年冤案、扶持新君所进行的复仇故事。从阳刚的侧面反映了男人之间的义薄云天、情义千秋，吟诵了一曲热血男儿的蜕变之歌。 　　电视剧琅琊榜由孔笙、李雪联合执导，胡歌、王凯、刘涛等主演，于2015年9月19日火热播出。海宴
  • 12669阅读
    首辅娇娘好评如潮完结
    新文《将军，夫人喊你种田了》已开更。 * 本是侯府千金，却因出生时抱错沦为农家女。 好不容易长到如花似玉的年纪，却无人上门娶她。 说她容颜丑陋，天生痴傻，还是克父克母的小灾星？ 可她半路捡来的夫君，是未来首辅。 她上山领养的小和尚，是六国神将。 就连随手救下的老太太，竟然也是当朝太后。 某男恶狠狠道：“娘子，谁敢欺负你，为夫把他办了！” 神将道：“姐姐，六国疆土，你想去哪里，我都打给你！” 太后道：“皇帝欺负娇娇了？等着！哀家这就去把他废了！” 【明明可以凭运气却偏要靠实力的霸王花女主】VS【深藏不露折翼少年男主】偏方方
  • 13655阅读
    重生之将门毒后值得一读完结
    将门嫡女，贞静柔婉，痴恋定王，自奔为眷。 　　六年辅佐，终成母仪天下。 　　陪他打江山，兴国土，涉险成为他国人质，五年归来，后宫已无容身之所。 　　他怀中的美人笑容明艳：“姐姐，江山定了，你也该退了。” 　　女儿惨死，太子被废。沈家满门忠烈，无一幸免。一朝倾覆，子丧族亡！ 　　沈妙怎么也没想到，患难夫妻，相互扶持，不过是一场逢场作戏的笑话！ 　　他道：“看在你跟了朕二十年，赐你全尸，谢恩吧。” 　　三尺白绫下，沈妙立下毒誓：是日何时丧，予与汝皆亡！ 　　重生回十四岁那年，悲剧未生，亲人还在，她还是那个温柔雅静的将门嫡女。 　　极品亲戚包藏祸心，堂姐堂妹恶毒无情，新进姨娘虎视眈眈，还有渣男意欲故技重来？ 　　家族要护，大仇要报，江山帝位，也要分一杯羹。这辈子，且看谁斗得过谁！ 　　但是那谢家小侯爷，提枪打马过的桀骜少年，偏立在她墙头傲然：“颠个皇权罢了，记住，天下归你，你——归我！” 　　---------------------------------------------------------- 　　——幽州十三京。 　　——归你。 　　——漠北定元城。 　　——归你。 　　——江南豫州，定西东海，临安青湖，洛阳古城。 　　——都归你。 　　——全都归我，谢景行你要什么？ 　　——嗯，你。 　　------------------------------------------------------------- 　　最初他漠然道：“沈谢两家泾渭分明，沈家丫头突然示好，不怀好意！” 　　后来他冷静道：“都是一条绳上的蚂蚱，沈妙你安分点，有本候担着，谁敢逼你嫁人？” 　　再后来他傲娇道：“颠个乾坤不过如此。沈娇娇，万里江山，你我二人瓜分如何？” 　　最后，他霸气的把手一挥：“媳妇，分来分去甚麻烦，不分了！全归你，你归我！” 　　沈妙：“给本宫滚出去！”霸气重生的皇后凉凉和不良少年谢小候爷，男女主身心干净，强强联手，宠文一对一。请各位小天使多多支持哦~千山茶客
  • 14599阅读
    魏晋干饭人好评如潮完结
    魏晋多风流，五胡即将乱中原，这是赵含章穿来的时代，庶民寒族多凄苦，簪缨世族只空谈。 为了衣冠不南渡，天下少饿殍，黎民百姓人人能吃饱饭，赵含章只能撸起袖子上了。 魏晋无清谈，我辈天下干饭人！ 这是一篇和相亲对象在乱世里为了生存而努力干事业的基建文，又叫《我在乱世搞基建》 　　赵含章在相亲回校的路上遭受意外，一睁开眼睛就到了正混乱的南北朝，在这个秩序崩坏，礼仪道德全都喂狗的时代，却又有人不甘屈服于命运，向往着自由，乐观向上的努力着。郁雨竹
  • 15526阅读
    权臣闲妻值得一读完结
    古言新文《皇城第一娇》求关注求收藏~【甜宠】【虐渣】【爽文】 本文简介： 又名《权臣升级指南》、《权臣调教手册》or《调教权臣手册》？ 　　谢安澜，国安特工代号青狐，腥风血雨没要了她的命，休个假一觉睡到了解放前。一梦醒来成为了东陵国泉州陆家的四少夫人。 　　房子票子美男子转眼成空，眼前只有手无缚鸡之力，刚被她一脚踹下床的庶子相公一名。万事不管，公公一名，外表贤良笑面虎，婆婆一名，各种心思妯娌兄弟若干。 　　谢安澜万分郁悒：老娘真是哔了...人类最亲密的好朋友了！ 　　本想拿捏着娇弱美少年相公作威作福，不想这货外表纯良内里却是要黑天黑地黑世人。 　　——“我眼中只有听话的和不听话的人，你是个聪明人。” 　　——“夫妻本是同林鸟，大难临头...我一定拉你一起死。” 　　——“我要权掌天下。” 　　——“那我...只好醉卧美人膝了。” 　　......那就看看，到底是谁卧谁的膝吧？ 　　 　　 　　推荐凤轻完结盛世三部曲： 　　《盛世嫡妃》 　　《盛世谋臣》 　　《盛世医妃》 狐狸窝系列之二《凤策长安》凤轻
  • 16512阅读
    盛华脍炙人口完结
    《吾家阿囡》的传奇开始啦！快来！ 一路拼搏通关而过，代子监国十余年的李太后，一头跌回了五岁那年； 好吧，只好重来一遍喽。 新书《暖君》连载中。闲听落花
  • 17501阅读
    嫡谋脍炙人口完结
    (嫡谋实体书已经出版，有简体和繁体两个版本)　 *** 前一世，所谓的血脉至亲告诉她，能为家族利益献身是她身为任家女子一生最大的荣耀。 　　结果她与姐姐反目成仇，让母亲垂泪早逝，累父亲血溅箭下…… 　　重生于幼学之年，她再不是那任人摆布的棋子！ 　　且看她如何谋算人心，一一揭去他们的画皮，灭之于无形！ 　　所谓荣耀，是守护所爱至亲一生平安顺遂。 　　所谓荣耀，是但得一人心，白首不相离。面北眉南
  • 18453阅读
    佔有姜西（又名：许你情深深似海）脍炙人口完结
    初见。 他问：“多少钱？” 她答：“一小时2000” “睡后？” “税前。” 他是人尽皆知的黑面阎王。 她是桀骜不驯的金牌教师。 他走火入魔，她若即若离。 他追她逃…… 谁都没想到不近女色的秦佔会化身妻奴，千里追妻！鱼不语
  • 19440阅读
    逆霖
    楚国，齐洲城，齐王府里发生一桩凶杀案。 当被拷打昏死的嫌犯再次睁开眼 一个新的故事就开始了 …… …… 言情文。希行
  • 20404阅读
    散落星河的记忆（套装全4册）神作完结
    套装包括：《散落星河的记忆1:迷失》《散落星河的记忆2:窃梦》《散落星河的记忆3:化蝶》《散落星河的记忆4:璀璨》桐华
今日全部20条查看完整榜单
  • 01
    The wholehearted life
    Roshi Joan Halifax is an original, generous, gritty and profound Buddhist teacher. How does she look back on her life? - by Ben Daitz Read on AeonBen Daitz
  • 02
    A trip to upside-down world
    Goats everywhere! Three-hour handstands! Magical doorknobs! Discover a whole new way of looking at a Cubist masterpiece - by Aeon Video Watch on AeonAeon Video
  • 03
    Equality talk
    In the summer of 1646, the idea of equality gained new and profound depths. We are still catching up with the consequences - by Teresa M Bejan Read on AeonTeresa M Bejan
  • 04
    Celestial nuisance
    The cosmos has become a lab for the Big Questions in physics. Along the way, we’ve lost sight of its glorious messiness - by Dylan Jow Read on AeonDylan Jow
  • 05
    Their eyes
    In Kenya, the Philippines and Venezuela, low-paid labour fuels the driverless future of the Global North - by Aeon Video Watch on AeonAeon Video
  • 06
    Methodical/mercurial
    I need order and routine – just as much as I crave excitement and variety. What’s life like with both autism and ADHD? - by Sarah Hendrickx Read on AeonSarah Hendrickx
  • 07
    Like aliens
    Like living metaphors, these self-contained miniature worlds show us the wondrous and fragile beauty of our biosphere - by Aeon Video Watch on AeonAeon Video
  • 08
    Believing and thinking
    The separation of church and state has an unspoken psychological basis: we choose what we believe, but not what we think - by Neil Van Leeuwen & Jacob Eisler Read on AeonNeil Van Leeuwen & Jacob Eisler
  • 09
    Jo Marchant: In search of now
    What is ‘now’? Through physics via philosophy and psychology, discover the science and mystery of the present moment - by Aeon Video Watch on AeonAeon Video
  • 10
    The self-making world
    Long mocked and misunderstood, Lamarck’s radical idea that organisms shape themselves and their world is making a comeback - by Jessica Riskin Read on AeonJessica Riskin
  • 11
    In praise of the dilettante
    A wayfaring cosmopolitan who never gets stuck, the dilettante is the right anti-hero for our hyper-specialised age - by Jay Miller Read on AeonJay Miller
  • 12
    Hills and mountains
    A girl’s story of forced marriage reveals how the Soviet invasion of 1979 transformed life in Afghanistan - by Aeon Video Watch on AeonAeon Video
  • 13
    The physics of getting fired
    Physics offered me a sense of order and purpose. But when life got messy I realised it had a much deeper insight to give - by Zahaan Bharmal Read on AeonZahaan Bharmal
  • 14
    The Amarna letters
    Petty disputes, pleas for help and requests for gold – explore letters sent to Egyptian pharaohs more than 3,000 years ago - by Aeon Video Watch on AeonAeon Video
  • 15
    Love with nowhere to go
    Grief is not only for the dead. When we are unable to honour other profound losses, we become strangers to ourselves - by Derek van Zoonen Read on AeonDerek van Zoonen
  • 16
    Great art explained: Tamara in the green Bugatti
    A very modern conception of womanhood: in the Jazz Age paintings of Tamara de Lempicka, women were bold, free and stylish - by Aeon Video Watch on AeonAeon Video
  • 17
    How to build real peace
    From Colombia to Syria, I’ve seen that capitalist logic can’t help to rebuild postwar countries but cooperatives can - by Azize Aslan Read on AeonAzize Aslan
  • 18
    Traction!
    Tribologists study friction: what happens when things rub together. It’s indispensable, from the wheel to the paths of stars - by Jennifer R Vail Read on AeonJennifer R Vail
  • 19
    Bhutan: the last place
    What happened when people in Bhutan, the last country on Earth without television, were allowed to watch it in 1999? - by Aeon Video Watch on AeonAeon Video
  • 20
    Other people
    Disconnection is at the heart of today’s crises. So my husband and I chose a radical and revealing remedy: living communally - by Elizabeth Oldfield Read on AeonElizabeth Oldfield
今日全部20条查看完整榜单
  • 01
    当平替产品泛滥，品牌如何把仿冒变成增长红利？
    如今AI与社交媒体降低了产品复刻的门槛，各类平替产品越来越多。当爆款遭遇大量仿冒，Lululemon、欧米茄没有单纯诉诸法律，而是用更柔性的方式直面平替用户。仿冒其实像一面镜子，帮助企业看清自身真正的竞争壁垒，将外部威胁转化为新的增长机会。格雷厄姆·肯尼（Graham Kenny）、甘娜・波格雷布纳（Ganna Pogrebna）
  • 02
    AI把创新效率拉满，为什么好想法却越来越少？
    同样手握大模型，不同团队的创新输出却天差地别。AI 能够大幅提升处理效率，却容易放大人类固有的认知偏差与组织偏见。创新不全是技术问题，认清 AI 的能力边界，守住人与真实世界的连接，才是破解创新困局的关键。朱利安·德弗雷塔斯（Julian De Freitas）、阿耶莱特·伊斯雷利（Ayelet Israeli）、吉迪恩·纳韦（Gideon Nave）、阿尔乔姆·季莫申科（Artem Timoshenko）、奥利维耶·图比亚（Olivier Toubia）
  • 03
    外部空降的高管，为何很少能升任CEO？
    很多外聘高管交出出色业绩，却与 CEO 岗位失之交臂。大家常归咎于能力短板，实则容易忽视组织认同度这一隐形壁垒。继任并非只筛选能人，空降人才需要完成身份蜕变。企业的人才规划，应当把这份集体共识纳入考量。阿南德·乔希（Anand Joshi）
  • 04
    AI时代，高潜力人才与普通员工的区别，在于三种能力
    AI正在重塑雇主对新员工的技能期望。吉姆·杜塞特（Jim Doucette）、维沙尔·高尔（Vishal Gaur）
  • 05
    廉价资本时代终结，靠烧钱换增长的日子到头了
    那些严谨配置资本、有选择性地投资、并让战略与经济效益始终保持清晰联系的公司，将更有能力胜出。迈克尔·曼金斯（Michael Mankins）、马修·克鲁皮（Matthew Crupi）、周浩
  • 06
    打折不是认输，而是一种高级的赚钱艺术
    关键不在于要不要打折，而在于如何聪明地打折。拉菲·穆罕默德（Rafi Mohammed）
  • 07
    “主动道歉” 竟是错的？这项研究颠覆常识
    当服务出错时，企业第一时间道歉真的能安抚客户吗？梅森·R·詹金斯（Mason R. Jenkins）、玛丽·斯特菲尔（Mary Steffel）、保罗·W·丰贝尔（Paul W. Fombelle）
  • 08
    AI正在批量制造伪专家，这些关键信号要警惕
    传统的“思想领导力”正在失效，而一种更宝贵的能力——“思想践行力”——正在崛起。约翰·温索（John Winsor）
  • 09
    让员工真正接受任务，关键在于做好三件事
    通过提供真正的自由，在做出决策时传达确定性，并让分配过程显得合理，领导者可以培养员工的接受感，使他们能够真心投入。亚当·埃里克·格林伯格（Adam Eric Greenberg）、维基·G·莫维茨（Vicki G. Morwitz）、库尔特·P·芒茨（Kurt P. Munz）
共 9 条查看完整榜单
  • 01
    November 10, 2026 | A Golden Tradition
    Nine-year-old Kerim Efe Umut sits on a ceremonial throne as a family friend pins a gold coin to his sash during his sünnet düğünü , or circumcision celebration, in Istanbul, Turkey. Traditionally, guests give gold coins to mark the occasion, but photographer Emre Çaylak says rising gold prices and economic pressures have led some guests to give Turkish lira instead. The celebration is an important coming-of-age tradition in Turkey, where boys often wear elaborate outfits inspired by Ottoman-eraEmre Çaylak
  • 02
    November 9, 2026 | Hidden in the Air
    For more than three years, Benjamin Pawlica has documented the nearly invisible process of mushroom sporulation. “It can only be revealed through carefully controlled backlighting,” he says. Capturing the phenomenon also requires patience: The mushrooms must be mature, and high humidity, little wind, and limited sunlight can help create the right conditions. Here, a cluster of Hypholoma fasciculare releases a dense cloud of spores in France’s Forêts National Park.Benjamin Pawlica
  • 03
    November 6, 2026 | Across the Distance
    After immigrating from Moscow to the United States with her mother, photographer Sasha Arutyunova began using her camera to understand how migration and distance had transformed her family. Her ongoing series Wind and Other Dangers , photographed across Russia, Armenia, and the United States since 2008, explores family, intimacy, identity, and belonging across continents. This image, Balcony, Pompano Beach , is part of the series, now on view at Chicago’s Filter Space through November 21.Sasha Arutyunova
  • 04
    November 5, 2026 | Salt From Above
    Photographer Aya Okawa was drawn to the bright colors and geometric patterns of these salt ponds in San Diego, California. They’re part of a historic salt plant that has operated in various forms since the late 1800s. The ponds’ striking colors can change as a result of fluctuations in salinity and wind, creating an ever-shifting landscape that Okawa captures from the air.Aya Okawa
  • 05
    November 4, 2026 | Behind the Backdrop
    For her series Am I What You’re Looking For? , photographer Endia Beal asked young Black women entering the workforce to dress as they would for a job interview and pose in their homes against a backdrop of an office. Beal intentionally left the edges of the backdrop visible, drawing attention to the ways Black women may feel pressure to change how they present themselves to fit into professional spaces. This photograph is featured in If Emmett Till Lived , an exhibition at Chicago’s Museum of CEndia Beal, MoCP
  • 06
    November 3, 2026 | A World of Ice and Light
    Photographer Christoph Johann was keen to explore the landscape of Alaska's Sheridan Glacier due to the way pockets of light shine through its extraordinary ice formations. Working with Points North Heli Adventures and skier Simon Hillis, he set out to capture some unexpected perspectives of the area. "Sometimes, the most incredible moments happen when you step off the beaten path and into another world," Johann tells National Geographic .Christoph Johann
  • 07
    November 2, 2026 | Mobile Bloom
    Colorful street vendors carrying everything from fruit and candy to clothing and flowers are a common site in Hanoi, Vietnam, especially around Lunar New Year. While some opt for street stalls, many will load up their goods on a bike or motorbike instead. Photographer Martina Giammaria is often drawn to flowers in her work, and in this case, she "liked the idea that this person was almost entirely covered by those flowers, like they were growing on their body."Martina Giammaria
  • 08
    October 30, 2026 | On Fire, On Purpose
    At the Tall Timbers Research Station and Land Conservancy near Tallahassee, Florida, prescribed burns are a normal part of studying fire ecology and working toward long-term land conservation. These low- to moderate-intensity fires can improve forest health by clearing dense vegetation and invasive plants. In turn, fire-tolerant native vegetation has room to grow, helping make forests more resilient to severe wildfires.Lindsey Kennedy
  • 09
    October 29, 2026 | Dressed for Celebration
    During Dia de los Muertos celebrations, women and girls in Mexico commonly dress as the famous skeletal figure known as La Catrina. In the early 1900s, artist José Guadalupe Posada created the character to satirize Mexicans who embraced European customs—a figure cloaked in European clothes, while its "bones" remain Mexican. Later popularized by artist Diego Rivera, La Catrina is the most recognizable symbol of the holiday and embodies Mexican identity.Dana Ullman
  • 10
    October 28, 2026 | A Sea of Cars in the Desert
    Drag racer and auto mechanic Larry Harms has been running his autobody business in an Idaho desert since 1967. Over the years, L & L Classic Auto became one of the world’s largest salvage yards and the resting place for over 10,000 vehicles from rare Cadillacs and GMC Pacers to school buses. But in June 2026, a fast-moving wildfire swept through the yard, burning 9,000 vehicles. The photo is featured in Laura McPhee's latest book, Silence So Deep It Rings: A Desert Chronicle .Laura McPhee
共 10 条查看完整榜单
共 10 条查看完整榜单
今日全部15条查看完整榜单