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)

17,701 to 17,760 of 20,192

Self-Distillation Enables Continual Learning
Idan Shenfeld, Mehul Damani, Jonas Hübotter +1
cs.LGarXiv:2601.19897v22026
Summaries:한국어
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Peng Xia, Jianwen Chen, Hanyang Wang +10
cs.LGarXiv:2602.08234v12026
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
Hejian Sang, Yuanda Xu, Zhengze Zhou +3
cs.LGarXiv:2603.05433v72026
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Weinan Dai, Hanlin Wu, Qiying Yu +13
cs.LGcs.AIarXiv:2602.24286v12026
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
cs.AIcs.CLcs.CVarXiv:2603.04448v22026
OpenClaw-RL: Train Any Agent Simply by Talking
Yinjie Wang, Xuyang Chen, Xiaolong Jin +2
cs.CLcs.AIcs.CVarXiv:2603.10165v22026
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Haozhen Zhang, Quanyu Long, Jianzhu Bao +4
cs.CLcs.AIcs.LGarXiv:2602.02474v22026
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Shenyuan Gao, William Liang, Kaiyuan Zheng +27
cs.ROcs.AIcs.CVarXiv:2602.06949v12026
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33
cs.ROcs.CVcs.LGarXiv:2602.15922v12026
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Jeonghye Kim, Xufang Luo, Minbeom Kim +5
cs.CLcs.LGarXiv:2603.24472v42026
GLM-5: from Vibe Coding to Agentic Engineering
GLM-5-Team, :, Aohan Zeng +184
cs.LGcs.CLarXiv:2602.15763v22026
Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
Razvan Mihai Popescu, David Gros, Andrei Botocan +3
cs.SEcs.AIcs.LGarXiv:2604.00917v12026
Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
Deepak Nathani, Cheng Zhang, Chang Huan +7
cs.AIcs.LGcs.MAarXiv:2604.00842v12026
Do Phone-Use Agents Respect Your Privacy?
Zhengyang Tang, Ke Ji, Xidong Wang +19
cs.CRcs.AIcs.CLarXiv:2604.00986v22026
Woosh: A Sound Effects Foundation Model
Gaëtan Hadjeres, Marc Ferras, Khaled Koutini +7
cs.SDcs.AIcs.LGarXiv:2604.01929v32026
Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning
Rafael Pardinas, Ehsan Kamalloo, David Vazquez +1
cs.LGarXiv:2604.02007v22026
Forecasting Supply Chain Disruptions with Foresight Learning
Benjamin Turtel, Paul Wilczewski, Kris Skotheim
cs.LGarXiv:2604.01298v12026
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
Zhanzhi Lou, Hui Chen, Yibo Li +2
cs.LGcs.AIarXiv:2604.00830v32026
Test-Time Scaling Makes Overtraining Compute-Optimal
Nicholas Roberts, Sungjun Cho, Zhiqi Gao +7
cs.LGcs.CLstat.MLarXiv:2604.01411v12026
A Survey of On-Policy Distillation for Large Language Models
Mingyang Song, Mao Zheng
cs.LGcs.CLarXiv:2604.00626v42026
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao +3
cs.CLcs.AIcs.LGarXiv:2604.01128v12026
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Gleb Rodionov, Roman Garipov, George Yakushev
cs.LGarXiv:2604.01161v22026
ActionParty: Multi-Subject Action Binding in Generative Video Games
Alexander Pondaven, Ziyi Wu, Igor Gilitschenski +4
cs.CVcs.AIcs.LGarXiv:2604.02330v22026
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Jiachun Jin, Zetong Zhou, Xiao Yang +4
cs.CVcs.LGarXiv:2604.02097v12026
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
Zhengxi Lu, Zhiyuan Yao, Jinyang Wu +7
cs.LGarXiv:2604.02268v22026
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang +6
cs.LGcs.AIarXiv:2604.02288v12026
Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
Shuibai Zhang, Caspian Zhuang, Chihan Cui +8
cs.LGcs.CLarXiv:2604.01622v22026
The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models
Prashant C. Raju
cs.LGcs.ITq-bio.QMarXiv:2604.04155v12026
Disentangling by Factorising
Hyunjik Kim, Andriy Mnih
stat.MLcs.LGarXiv:1802.05983v32018
Addressable Memory for Video World Models
Xindi Wu, Sven Elflein, James Lucas +5
cs.CVcs.LGarXiv:2608.07408v12026
Born Again Neural Networks
Tommaso Furlanello, Zachary C. Lipton, Michael Tschannen +2
stat.MLcs.AIcs.LGarXiv:1805.04770v22018
ClawArena: Benchmarking AI Agents in Evolving Information Environments
Haonian Ji, Kaiwen Xiong, Siwei Han +9
cs.LGcs.AIcs.CLarXiv:2604.04202v22026
General Multimodal Protein Design Enables DNA-Encoding of Chemistry
Jarrid Rector-Brooks, Théophile Lambert, Marta Skreta +15
cs.LGarXiv:2604.05181v12026
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Justin Chih-Yao Chen, Archiki Prasad, Zaid Khan +4
cs.LGcs.AIcs.CLarXiv:2604.04767v12026
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Chenxi Wang, Zhuoyun Yu, Xin Xie +8
cs.CLcs.AIcs.IRarXiv:2604.04804v22026
Synthetic Sandbox for Training Machine Learning Engineering Agents
Yuhang Zhou, Lizhu Zhang, Yifan Wu +4
cs.CLcs.LGarXiv:2604.04872v12026
LightThinker++: From Reasoning Compression to Memory Management
Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7
cs.CLcs.AIcs.IRarXiv:2604.03679v12026
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Shenzhi Yang, Guangcheng Zhu, Bowen Song +7
cs.LGcs.AIarXiv:2604.03993v12026
REAM: Merging Improves Pruning of Experts in LLMs
Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand +3
cs.AIcs.CLcs.LGarXiv:2604.04356v12026
Neural Computers
Mingchen Zhuge, Changsheng Zhao, Haozhe Liu +16
cs.LGcs.AIarXiv:2604.06425v22026
R3PM-Net: Real-time, Robust, Real-world Point Matching Network
Yasaman Kashefbahrami, Erkut Akdag, Panagiotis Meletis +3
cs.CVcs.LGarXiv:2604.05060v22026
FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
Xiangru Jian, Hao Xu, Wei Pang +13
cs.CVcs.AIcs.LGarXiv:2604.07413v22026
CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation
Siddharth Jain, Venkat Narayan Vedam
cs.IRcs.CLcs.LGarXiv:2604.05467v12026
FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification
Ling Yue, Chaoqian Ouyang, Hang Xu +7
cs.AIcs.LGarXiv:2604.04074v42026
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
Le Chen, Erhu Feng, Yubin Xia +1
cs.SEcs.LGarXiv:2604.03088v32026
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
cs.LGarXiv:2604.06268v12026
Target Policy Optimization
Jean Kaddour
cs.LGarXiv:2604.06159v12026
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Rishab Balasubramanian, Pin-Jie Lin, Rituraj Sharma +6
cs.LGcs.AIarXiv:2604.06377v32026
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
Yi Xu, Philipp Jettkant, Laura Ruis
cs.LGcs.AIcs.CLarXiv:2604.06427v12026
In-Place Test-Time Training
Guhao Feng, Shengjie Luo, Kai Hua +4
cs.LGcs.AIcs.CLarXiv:2604.06169v12026
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
Changxin Ke, Rui Zhang, Jiaming Guo +10
cs.SEcs.LGarXiv:2604.05963v12026
MoRight: Motion Control Done Right
Shaowei Liu, Xuanchi Ren, Tianchang Shen +5
cs.CVcs.AIcs.GRarXiv:2604.07348v12026
Fast Spatial Memory with Elastic Test-Time Training
Ziqiao Ma, Xueyang Yu, Haoyu Zhen +3
cs.CVcs.GRcs.LGarXiv:2604.07350v12026
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
Qiyao Ma, Dechen Gao, Rui Cai +4
cs.CLcs.LGarXiv:2604.07343v22026
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
Yitong Li, Junsong Chen, Shuchen Xue +8
cs.LGcs.AIcs.CVarXiv:2604.06916v12026
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
Quantong Qiu, Zhiyi Hong, Yi Yang +5
cs.LGcs.CLarXiv:2604.07394v12026
Small Vision-Language Models are Smart Compressors for Long Video Understanding
Junjie Fei, Jun Chen, Zechun Liu +13
cs.CVcs.AIcs.CLarXiv:2604.08120v12026
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Jiawei Chen, Ruoxi Xu, Boxi Cao +11
cs.CLcs.AIcs.LGarXiv:2604.08362v22026
Structured Distillation of Web Agent Capabilities Enables Generalization
Xing Han Lù, Siva Reddy
cs.LGarXiv:2604.07776v12026
Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
Mu Nan, Muquan Yu, Weijian Mai +12
cs.LGq-bio.NCarXiv:2604.08537v12026

Machine Learning

Self-Distillation Enables Continual Learning

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

SkillNet: Create, Evaluate, and Connect AI Skills

OpenClaw-RL: Train Any Agent Simply by Talking

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

World Action Models are Zero-shot Policies

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

GLM-5: from Vibe Coding to Agentic Engineering

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants

Do Phone-Use Agents Respect Your Privacy?

Woosh: A Sound Effects Foundation Model

Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning

Forecasting Supply Chain Disruptions with Foresight Learning

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

Test-Time Scaling Makes Overtraining Compute-Optimal

A Survey of On-Policy Distillation for Large Language Models

Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

Reasoning Shift: How Context Silently Shortens LLM Reasoning

ActionParty: Multi-Subject Action Binding in Generative Video Games

LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models

The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models

Disentangling by Factorising

Addressable Memory for Video World Models

Born Again Neural Networks

ClawArena: Benchmarking AI Agents in Evolving Information Environments

General Multimodal Protein Design Enables DNA-Encoding of Chemistry

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Synthetic Sandbox for Training Machine Learning Engineering Agents

LightThinker++: From Reasoning Compression to Memory Management

Can LLMs Learn to Reason Robustly under Noisy Supervision?

REAM: Merging Improves Pruning of Experts in LLMs

Neural Computers

R3PM-Net: Real-time, Robust, Real-world Point Matching Network

FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios

CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation

FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses

RAGEN-2: Reasoning Collapse in Agentic RL

Target Policy Optimization

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning

In-Place Test-Time Training

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

MoRight: Motion Control Done Right

Fast Spatial Memory with Elastic Test-Time Training

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

Small Vision-Language Models are Smart Compressors for Long Video Understanding

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

Structured Distillation of Web Agent Capabilities Enables Generalization

Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding