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)

7,081 to 7,140 of 20,199

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
Xiangxiang Chu, Hailang Huang, Xiao Zhang +2
cs.LGcs.AIarXiv:2504.02546v42025
Beyond Local Power: Functional Connectivity Analysis for Subject-Independent Learning Style Recognition
Wiga Maulana Baihaqi, Indriana Hidayah, Sri Kusrohmaniah +1
q-bio.NCcs.LGeess.SParXiv:2608.12000v12026
AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
Ivan Moshkov, Darragh Hanley, Ivan Sorokin +5
cs.AIcs.CLcs.LGarXiv:2504.16891v12025
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson +4
cs.AIcs.CLcs.LGarXiv:2502.01100v22025
Dion3: Full-Stack Orthogonal Updates
Noah Amsel, Jack Zhang, Kwangjun Ahn +5
cs.LGcs.AIarXiv:2608.11612v12026
InSight-doc: Agentic Visual Perception for Long-Document Understanding
Kaican Li, Weiyan Xie, Lewei Yao +4
cs.CVcs.CLcs.LGarXiv:2608.10628v12026
A deep learning model for estimating story points
Morakot Choetkiertikul, Hoa Khanh Dam, Truyen Tran +3
cs.SEcs.LGstat.MLarXiv:1609.00489v22016
Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
Ziwei Ji, Matus Telgarsky
cs.LGmath.OCstat.MLarXiv:1909.12292v42019
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
Kimin Lee, Kibok Lee, Jinwoo Shin +1
cs.LGstat.MLarXiv:1910.05396v32019
Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure
Víctor Gallego
cs.LGcs.AIarXiv:2608.08722v12026
Summaries:한국어
CEM-RL: Combining evolutionary and gradient-based methods for policy search
Aloïs Pourchot, Olivier Sigaud
cs.LGcs.NEstat.MLarXiv:1810.01222v32018
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization
Víctor Gallego
cs.LGcs.NEarXiv:2608.08156v12026
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
Changzhi Liu, Yilun Liu, Sikuan Yan +2
cs.AIcs.LGarXiv:2608.07645v12026
Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control
Alain Bensoussan, Minh-Nhat Phung, Minh-Binh Tran
math.OCcs.LGarXiv:2608.07265v22026
End-to-End Lane Marker Detection via Row-wise Classification
Seungwoo Yoo, Heeseok Lee, Heesoo Myeong +4
cs.CVcs.LGarXiv:2005.08630v12020
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
Yongliang Wu, Yizhou Zhou, Zhou Ziheng +7
cs.LGarXiv:2508.05629v32025
Recursive Harness Self-Improvement
Hyunin Lee, Jinglue Xu, Jeffrey Seely +3
cs.LGcs.AIarXiv:2607.15524v12026
Summaries:한국어
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Qingyu Zhang, Qianhao Yuan, Hongyu Lin +5
cs.LGcs.AIcs.CLarXiv:2607.13124v22026
Summaries:한국어
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Chen Tang, Yizhou Wang, Jianyu Wu +26
cs.CLcs.AIcs.CEarXiv:2607.07708v12026
Summaries:한국어
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
Andrey Podivilov, Vadim Lomshakov, Sergey Savin +4
cs.AIcs.LGcs.SEarXiv:2607.06624v22026
Multiplayer Interactive World Models with Representation Autoencoders
Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary +24
cs.CVcs.AIcs.LGarXiv:2607.05352v22026
TESSERA v2: Scaling Pixel-wise Earth Foundation Models
Zhengpeng Feng, Sadiq Jaffer, Ira Shokar +12
cs.CVcs.LGarXiv:2607.03949v22026
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Donghyun Lee, Jitesh Chavan, Duy Nguyen +5
cs.CVcs.AIcs.LGarXiv:2607.02461v12026
Discrete Diffusion Language Models for Interactive Radiology Report Drafting
Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge +1
cs.AIcs.LGarXiv:2607.01436v12026
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini
cs.CLcs.AIcs.LGarXiv:2607.01002v12026
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina +3
cs.LGcs.AIcs.CLarXiv:2606.32034v12026
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
Yuanda Xu, Zhengze Zhou, Hejian Sang +6
cs.LGcs.AIarXiv:2606.32017v22026
SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal +1
cs.LGarXiv:2606.30573v12026
$μ_0$: A Scalable 3D Interaction-Trace World Model
Seungjae Lee, Yoonkyo Jung, Jusuk Lee +6
cs.ROcs.CVcs.LGarXiv:2606.13769v22026
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
Zixi Li, Youzhen Li
cs.SDcs.LGeess.ASarXiv:2606.07207v12026
Regret Minimization with Adaptive Opponents in Repeated Games
Mingyang Liu, Asuman Ozdaglar, Tiancheng Yu +1
cs.LGcs.AIcs.GTarXiv:2606.06486v12026
Reinforcement Learning from Rich Feedback with Distributional DAgger
Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad
cs.LGcs.AIcs.CLarXiv:2606.05152v22026
Unlocking Feature Learning in Gated Delta Networks at Scale
Yifeng Liu, Quanquan Gu
cs.LGcs.AIarXiv:2606.04048v12026
Self-Distilled Policy Gradient
Yifeng Liu, Shiyuan Zhang, Yifan Zhang +1
cs.LGarXiv:2606.04036v12026
Neural Networks Provably Learn Spectral Representations for Group Composition
Jianliang He, Leda Wang, Fengzhuo Zhang +2
cs.LGmath.OCmath.RTarXiv:2606.02993v22026
Unified Neural Scaling Laws
Ethan Caballero, Priyank Jaini, David Krueger +1
cs.LGcs.AIcs.NEarXiv:2605.26248v12026
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Samson Gourevitch, Yazid Janati, Dario Shariatian +4
cs.LGstat.MLarXiv:2605.22765v12026
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
Mingkai Deng, Jinyu Hou, Lara Sá Neves +4
cs.AIcs.CLcs.LGarXiv:2605.22138v12026
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
Xitai Jiang, Zihan Tang, Wenze Lin +3
cs.LGcs.AIcs.CLarXiv:2605.22074v12026
SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction
Gustav Olaf Yunus Laitinen-Fredriksson Lundström-Imanov, Hafize Gonca Cömert
cs.LGecon.EMstat.MLarXiv:2605.19014v12026
DynMuon: A Dynamic Spectral Shaping View of Muon
Fangzhou Wu, Rikhav Shah, Sandeep Silwal +1
cs.LGcs.AIarXiv:2605.17109v32026
FutureSim: Replaying World Events to Evaluate Adaptive Agents
Shashwat Goel, Nikhil Chandak, Arvindh Arun +5
cs.LGcs.AIcs.CLarXiv:2605.15188v12026
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Mind Lab, :, Song Cao +60
cs.LGcs.AIcs.DCarXiv:2605.13779v22026
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
Xin Li, Hao Jiang, Annan Wang +2
cs.LGcs.CLarXiv:2605.08737v12026
3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis
Stefan Schulz, Fernando Edelstein, Hannah Dröge +2
cs.CVcs.LGcs.MMarXiv:2604.11211v12026
Streaming Structured Inference with Flash-SemiCRF
Benjamin K. Johnson, Thomas Goralski, Ayush Semwal +2
cs.LGarXiv:2604.18780v12026
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
Rafał Powalski, Łukasz Borchmann, Dawid Jurkiewicz +3
cs.CLcs.LGarXiv:2102.09550v32021
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion
Satoshi Hayakawa
cs.LGcs.AImath.PRarXiv:2609.01043v12026
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
Donald Shenaj, Federico Errica, Antonio Carta
cs.CVcs.AIcs.LGarXiv:2603.21884v12026
I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning
Aliyu Agboola Alege
cs.AIcs.LGarXiv:2603.15670v22026
Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD
Emiel Hoogeboom, David Ruhe, Jonathan Heek +2
cs.LGcs.CVstat.MLarXiv:2603.20155v12026
Remasking Discrete Diffusion Models with Inference-Time Scaling
Guanghan Wang, Yair Schiff, Subham Sekhar Sahoo +1
cs.LGstat.MLarXiv:2503.00307v42025
SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis
Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss +1
cs.LGcs.AIstat.MLarXiv:2603.05483v12026
MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts
Sunil Mohan, Donghui Li
cs.CLcs.LGarXiv:1902.09476v12019
Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection
Kadir-Kaan Özer, René Ebeling, Markus Enzweiler
cs.LGcs.AIarXiv:2603.12916v32026
Denoising Diffusion Generative Models Secretly Calculate Attentions
Farzan Haddadi, Leila Monfared, Ebrahim Rezaii +3
cs.AIcs.CVcs.LGarXiv:2609.00885v12026
Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal
Alekh Agarwal, Sham Kakade, Lin F. Yang
cs.LGmath.PRstat.MLarXiv:1906.03804v32019
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
Arnas Uselis, Andrea Dittadi, Seong Joon Oh
cs.CVcs.LGarXiv:2602.24264v22026
Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling
Jérome Eertmans, Enrico M. Vitucci, Vittorio Degli-Esposti +3
cs.LGeess.SParXiv:2603.01655v22026
On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
Jianliang He, Leda Wang, Siyu Chen +1
cs.LGmath.OCstat.MLarXiv:2602.16849v12026

Machine Learning

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

Beyond Local Power: Functional Connectivity Analysis for Subject-Independent Learning Style Recognition

AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Dion3: Full-Stack Orthogonal Updates

InSight-doc: Agentic Visual Perception for Long-Document Understanding

A deep learning model for estimating story points

Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks

Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning

Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure

CEM-RL: Combining evolutionary and gradient-based methods for policy search

A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization

Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution

Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control

End-to-End Lane Marker Detection via Row-wise Classification

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Recursive Harness Self-Improvement

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation

Multiplayer Interactive World Models with Representation Autoencoders

TESSERA v2: Scaling Pixel-wise Earth Foundation Models

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Discrete Diffusion Language Models for Interactive Radiology Report Drafting

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions

$μ_0$: A Scalable 3D Interaction-Trace World Model

Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development

Regret Minimization with Adaptive Opponents in Repeated Games

Reinforcement Learning from Rich Feedback with Distributional DAgger

Unlocking Feature Learning in Gated Delta Networks at Scale

Self-Distilled Policy Gradient

Neural Networks Provably Learn Spectral Representations for Group Composition

Unified Neural Scaling Laws

Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning

SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction

DynMuon: A Dynamic Spectral Shaping View of Muon

FutureSim: Replaying World Events to Evaluate Adaptive Agents

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs

3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis

Streaming Structured Inference with Flash-SemiCRF

Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer

From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation

I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD

Remasking Discrete Diffusion Models with Inference-Time Scaling

SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts

Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection

Denoising Diffusion Generative Models Secretly Calculate Attentions

Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking