Machine Learning

Papers filed under cs.LG on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

19,801 to 19,860 of 20,180

Quantifying the Gap Between Laboratory Battery Test Patterns and Field Duty Profiles
Chunyang Zhao, Chresten Træholt
cs.LGarXiv:2608.16212v12026
DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design
Xinling Yu, Yixing Li, Ziyue Liu +4
cs.LGphysics.data-anarXiv:2608.16080v12026
OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations
Simon Donike, Ruben Cartuyvels, Antonino Ian Ferola +3
cs.LGcs.AIcs.CVarXiv:2608.16373v22026
Optimizing Multi-Market Participation of Battery and Electrolyser Systems Based on Field Performance
Chunyang Zhao, Stoyan Trenchev, Shi You +1
cs.LGarXiv:2608.16238v12026
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
Reza Bayat, Ali Behrouz, Vahab Mirrokni +1
cs.LGcs.AIcs.CLarXiv:2608.16844v12026
OpenSkill: Open-World Self-Evolution for LLM Agents
Zhiling Yan, Dingjie Song, Hanrong Zhang +8
cs.AIcs.CLcs.LGarXiv:2606.06741v12026
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
Yang Tian, Rui Wang, Xumeng Wen +5
cs.LGcs.CLarXiv:2606.09348v22026
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
Zihan Lin, Xiaohan Wang, Jie Cao +6
cs.LGcs.CLarXiv:2605.00380v22026
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Yifu Yuan, Yaoting Huang, Xianze Yao +20
cs.ROcs.AIcs.LGarXiv:2606.11324v22026
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
cs.AIcs.CLcs.CRarXiv:2605.29801v12026
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
Ting-Yun Chang, Harvey Yiyun Fu, Deqing Fu +3
cs.LGcs.CLarXiv:2606.03928v12026
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Yan Wang, Qifan Zhang, Jiachen Yu +12
cs.LGcs.AIarXiv:2606.09079v32026
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Yucheng Li, Huiqiang Jiang, Yang Xu +14
cs.LGcs.CLarXiv:2606.12370v12026
Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning
Kuo-Chung Peng, Samuel Yen-Chi Chen, Jiun-Cheng Jiang +16
cs.LGcs.AIquant-pharXiv:2605.06734v22026
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9
cs.CLcs.LGarXiv:2605.10899v12026
Mint-Agent: Introducing Finance-Native Agentic Foundation Models
Mint-Agent Team, B. Zhang, Yaze Geng +7
cs.CLcs.LGarXiv:2608.16386v12026
Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant
Zaid Abulawi, Mengnan Li, Guillaume Giudicelli +2
cs.LGcs.CEarXiv:2608.15881v12026
DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs
Zeyu Cao, Xuan Guo, Cheng Zhang +3
cs.LGcs.AIcs.ARarXiv:2608.14614v12026
Explaining Reinforcement Learning Decisions in Self-adaptive Systems
Jasmina Gajcin, Juan C. Rosero, Ivana Dusparic
cs.LGcs.AIarXiv:2608.14620v12026
WANDR: A Benchmark for Wide and Deep Research
Vitaliy Polshkov, Marcin Pitera, Jeremy Yang +7
cs.LGarXiv:2608.14747v12026
A Novel Fourier Feature Network for Solving Partial Differential Equations
Qihong Yang, Zhijie Su, Yangtao Deng +1
cs.LGcs.AIarXiv:2608.14733v12026
Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks
Preben M. Ness, Fariz Ikhwantri, Dusica Marijan
cs.LGarXiv:2608.14823v12026
Tapered Language Models
Reza Bayat, Ali Behrouz, Aaron Courville
cs.LGcs.AIcs.CLarXiv:2606.23670v12026
Spectral Rank Certification for Foundation Model Adapters
Mohammed Ahnouch, Lotfi Elaachak
cs.LGstat.MEarXiv:2608.15351v12026
A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data
Mary Chriselda Antony Oliver, Kaitlyn Hohmeier, Tuyen Tran +3
stat.MLcs.LGmath.MGarXiv:2608.15306v12026
Coded Hankel Polynomial Chaos: Spectral Identification of Dominant Polynomial-Chaos Modes
Zhiliang Deng, Xiaomei Yang
stat.MLcs.LGarXiv:2608.16126v12026
Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization
Anling Xiang, Yuwen Yang, Yang Shen
cs.LGarXiv:2608.16216v12026
Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface
Siqi Li, Zhi Li, Tong Liu +5
cs.LGcs.HCeess.SParXiv:2608.16134v12026
Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts
Seungyeol Baek, Yoonbyung Chai, Yonghyeon Lee +2
cs.AIcs.LGarXiv:2608.15621v12026
Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic
Simon Ellershaw, Christopher Tomlinson, Zeljko Kraljevic +6
cs.LGcs.AIarXiv:2608.16273v12026
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Rohan Surana, Gagan Mundada, Xunyi Jiang +19
cs.LGarXiv:2605.02913v12026
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
Ninad Daithankar, Alexi Gladstone, Yann LeCun +1
cs.CVcs.AIcs.LGarXiv:2606.15956v12026
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Yuhao Shen, Tianyu Liu, Xinyi Hu +9
cs.LGcs.AIarXiv:2605.20104v12026
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Rui Yang, Qianhui Wu, Yuxi Chen +7
cs.LGcs.AIcs.CLarXiv:2606.02031v22026
Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
Xiaoyu Yang, En Yu, Wei Duan +1
cs.CVcs.AIcs.LGarXiv:2510.04142v32025
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Ali Behrouz, Farnoosh Hashemi, Adel Javanmard +1
cs.LGcs.AIarXiv:2606.03979v22026
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Lorenz K. Muller, Philippe Bich, Chiara Boretti +3
cs.LGarXiv:2606.03458v12026
Prescriptive Scaling Laws for Data Constrained Training
Justin Lovelace, Christian Belardi, Srivatsa Kundurthy +2
cs.LGcs.CLarXiv:2605.01640v12026
ClawGym: A Scalable Framework for Building Effective Claw Agents
Fei Bai, Huatong Song, Shuang Sun +11
cs.CLcs.AIcs.LGarXiv:2604.26904v32026
Hoeffding adaptive splitting trees for data stream classification with concept drift and ensemble learning
Daniel Nowak Assis, Jean Paul Barddal, Fabrício Enembreck
cs.LGcs.AIarXiv:2608.16659v12026
The Last Human-Written Paper: Agent-Native Research Artifacts
Jiachen Liu, Jiaxin Pei, Jintao Huang +34
cs.LGarXiv:2604.24658v32026
T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework
Zahra Fazel, Sunanda Gamage, Shayan Shirahmad Gale Bagi +5
cs.AIcs.CLcs.LGarXiv:2608.14953v12026
Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning
Allen Nie, Anirudhan Badrinath, Nicholas Tomlin +5
cs.AIcs.LGarXiv:2608.14851v12026
Solve the Loop: Attractor Models for Language and Reasoning
Jacob Fein-Ashley, Paria Rashidinejad
cs.LGcs.AIcs.CLarXiv:2605.12466v12026
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Bardia Mohammadi, Lars Klein, Aman Chadha +2
cs.SEcs.LGarXiv:2608.16630v12026
Healthcare AI GYM for Medical Agents
Minbyul Jeong
cs.LGcs.AIarXiv:2605.02943v12026
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
Taekhyun Park, Yongjae Lee, Dohee Kim +1
cs.LGcs.AIarXiv:2605.11011v12026
Can Muon Fine-tune Adam-Pretrained Models?
Xingyu Qu, Peigeng Huang, Samuel Horvath
cs.LGarXiv:2605.10468v12026
A Privacy Study of Sparse Collaborative Inference
Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek
cs.LGarXiv:2608.16236v12026
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Yuanda Xu, Hejian Sang, Zhengze Zhou +3
cs.LGcs.AIarXiv:2605.12483v42026
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
Yiqiao Jin, Yiyang Wang, Lucheng Fu +7
cs.CLcs.AIcs.LGarXiv:2605.06597v22026
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo +3
cs.CLcs.AIcs.LGarXiv:2605.07721v22026
GrepSeek: Training Search Agents for Direct Corpus Interaction
Alireza Salemi, Chang Zeng, Atharva Nijasure +4
cs.CLcs.AIcs.IRarXiv:2605.29307v12026
Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
Zewen Liu, Zhan Shi, Yisi Sang +7
cs.LGcs.AIarXiv:2606.01770v22026
SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling
Haoran Xu, Hongyu Wang, Yifei Gao +3
cs.CLcs.LGarXiv:2606.09304v12026
RigidBench: Evaluating Rigid-Body Physics in Video Generation Models
Swarnim Jain, Shangzhe Wu
cs.CVcs.LGarXiv:2608.15555v12026
IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages
Sahil Deepak Gawande, Mayank Singh
cs.CLcs.LGarXiv:2607.23242v12026
Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
Thomas MacDougall, Maksim Kuznetsov, Roman Schutski +5
cs.LGcs.AIcs.CLarXiv:2607.18144v12026
Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems
Zhaoqiang Liu, Tongyao Pang, Ruibing Wang +1
stat.MLcs.AIcs.LGarXiv:2608.15144v12026
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
cs.LGcs.AIarXiv:2605.07396v12026

Machine Learning

Quantifying the Gap Between Laboratory Battery Test Patterns and Field Duty Profiles

DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design

OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations

Optimizing Multi-Market Participation of Battery and Electrolyser Systems Based on Field Performance

Proteus: Incremental Memory Activation for Long-Context Sequence Modeling

OpenSkill: Open-World Self-Evolution for LLM Agents

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Value-Aware Stochastic KV Cache Eviction for Reasoning Models

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant

DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs

Explaining Reinforcement Learning Decisions in Self-adaptive Systems

WANDR: A Benchmark for Wide and Deep Research

A Novel Fourier Feature Network for Solving Partial Differential Equations

Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks

Tapered Language Models

Spectral Rank Certification for Foundation Model Adapters

A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data

Coded Hankel Polynomial Chaos: Spectral Identification of Dominant Polynomial-Chaos Modes

Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization

Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface

Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts

Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Prescriptive Scaling Laws for Data Constrained Training

ClawGym: A Scalable Framework for Building Effective Claw Agents

Hoeffding adaptive splitting trees for data stream classification with concept drift and ensemble learning

The Last Human-Written Paper: Agent-Native Research Artifacts

T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework

Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning

Solve the Loop: Attractor Models for Language and Reasoning

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

Healthcare AI GYM for Medical Agents

LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

Can Muon Fine-tune Adam-Pretrained Models?

A Privacy Study of Sparse Collaborative Inference

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

GrepSeek: Training Search Agents for Direct Corpus Interaction

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling

RigidBench: Evaluating Rigid-Body Physics in Video Generation Models

IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages

Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems

Rubric-based On-policy Distillation