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)

30,241 to 30,300 of 33,067

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi +1
cs.CRcs.LGarXiv:2602.20156v32026
MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies
Vasilii Feofanov, Songkang Wen, Jianfeng Zhang +2
cs.LGcs.AIarXiv:2602.17868v12026
Resource-Efficient Iterative LLM-Based NAS with Feedback Memory
Xiaojie Gu, Dmitry Ignatov, Radu Timofte
cs.LGcs.AIarXiv:2603.12091v12026
Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs
Christos Koutsiaris
cs.IRcs.AIcs.CLarXiv:2602.14784v12026
Uncertainty-Aware Vision-Language Segmentation for Medical Imaging
Aryan Das, Tanishq Rachamalla, Koushik Biswas +2
cs.CVcs.LGarXiv:2602.14498v22026
SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM
Xiaojiang Zhang, Jinghui Wang, Zifei Cheng +14
cs.LGarXiv:2504.14286v22025
On the Generalization Capacities of MLLMs for Spatial Intelligence
Gongjie Zhang, Wenhao Li, Quanhao Qian +4
cs.CVcs.LGarXiv:2603.06704v12026
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Jingcheng Hu, Yinmin Zhang, Shijie Shang +17
cs.LGarXiv:2601.05593v12026
Open Problems in Machine Unlearning for AI Safety
Fazl Barez, Tingchen Fu, Ameya Prabhu +16
cs.LGcs.AIcs.CYarXiv:2501.04952v12025
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Keyon Vafa, Peter G. Chang, Ashesh Rambachan +1
cs.LGcs.AIarXiv:2507.06952v42025
Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
Hanna Yukhymenko, Anton Alexandrov, Martin Vechev
cs.CLcs.AIcs.LGarXiv:2602.22207v12026
3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing
Binghao Huang, Yixuan Wang, Xinyi Yang +2
cs.ROcs.AIcs.LGarXiv:2410.24091v22024
Self-Evaluation Unlocks Any-Step Text-to-Image Generation
Xin Yu, Xiaojuan Qi, Zhengqi Li +6
cs.CVcs.AIcs.LGarXiv:2512.22374v12025
Learning a Generative Meta-Model of LLM Activations
Grace Luo, Jiahai Feng, Trevor Darrell +2
cs.LGcs.AIcs.CLarXiv:2602.06964v12026
Evaluating Gemini Robotics Policies in a Veo World Simulator
Gemini Robotics Team, Krzysztof Choromanski, Coline Devin +20
cs.ROcs.AIcs.CVarXiv:2512.10675v22025
Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
Shanchuan Lin, Ceyuan Yang, Hao He +6
cs.CVcs.AIcs.LGarXiv:2506.09350v22025
Scaling Spatial Intelligence with Multimodal Foundation Models
Zhongang Cai, Ruisi Wang, Chenyang Gu +26
cs.CVcs.AIcs.LGarXiv:2511.13719v42025
Autellix: An Efficient Serving Engine for LLM Agents as General Programs
Michael Luo, Xiaoxiang Shi, Colin Cai +8
cs.LGcs.AIcs.DCarXiv:2502.13965v12025
Boomerang Distillation Enables Zero-Shot Model Size Interpolation
Sara Kangaslahti, Nihal V. Nayak, Jonathan Geuter +3
cs.LGarXiv:2510.05064v22025
Where Do the Joules Go? Diagnosing Inference Energy Consumption
Jae-Won Chung, Ruofan Wu, Jeff J. Ma +1
cs.LGcs.DCarXiv:2601.22076v22026
Regression Language Models for Code
Yash Akhauri, Xingyou Song, Arissa Wongpanich +2
cs.CLcs.AIcs.LGarXiv:2509.26476v32025
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Lu Han, Xu-Yang Chen, Han-Jia Ye +1
cs.LGarXiv:2404.14197v32024
Jamba: A Hybrid Transformer-Mamba Language Model
Opher Lieber, Barak Lenz, Hofit Bata +19
cs.CLcs.LGarXiv:2403.19887v22024
Towards Automated Kernel Generation in the Era of LLMs
Yang Yu, Peiyu Zang, Chi Hsu Tsai +11
cs.LGcs.CLarXiv:2601.15727v32026
RM -RF: Reward Model for Run-Free Unit Test Evaluation
Elena Bruches, Daniil Grebenkin, Mikhail Klementev +8
cs.SEcs.LGarXiv:2601.13097v12026
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Xingjun Ma, Yixu Wang, Hengyuan Xu +18
cs.AIcs.CLcs.CVarXiv:2601.10527v22026
Mercury: Ultra-Fast Language Models Based on Diffusion
Inception Labs, Samar Khanna, Siddhant Kharbanda +10
cs.CLcs.AIcs.LGarXiv:2506.17298v12025
A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective
Xiangfei Qiu, Hanyin Cheng, Xingjian Wu +5
cs.LGarXiv:2502.10721v32025
What Large Language Models Know and What People Think They Know
Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar +5
cs.LGcs.AIcs.CLarXiv:2401.13835v22024
FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
Luca Della Libera, Cem Subakan, Mirco Ravanelli
cs.SDcs.AIcs.LGarXiv:2509.16195v12025
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
Xingjian Leng, Jaskirat Singh, Yunzhong Hou +3
cs.CVcs.LGarXiv:2504.10483v32025
AgentOCR: Reimagining Agent History via Optical Self-Compression
Lang Feng, Fuchao Yang, Feng Chen +5
cs.LGcs.AIarXiv:2601.04786v32026
xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
Kaiyuan Chen, Yixin Ren, Yang Liu +30
cs.LGarXiv:2506.13651v12025
A Survey on Diffusion Language Models
Tianyi Li, Mingda Chen, Bowei Guo +1
cs.CLcs.AIcs.LGarXiv:2508.10875v32025
PCMind-2.1-Kaiyuan-2B Technical Report
Kairong Luo, Zhenbo Sun, Xinyu Shi +9
cs.CLcs.AIcs.LGarXiv:2512.07612v12025
TradingAgents: Multi-Agents LLM Financial Trading Framework
Yijia Xiao, Edward Sun, Di Luo +1
q-fin.TRcs.AIcs.CEarXiv:2412.20138v72024
S*: Test Time Scaling for Code Generation
Dacheng Li, Shiyi Cao, Chengkun Cao +6
cs.LGcs.AIarXiv:2502.14382v12025
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
Chengsen Wang, Qi Qi, Jingyu Wang +5
cs.CLcs.LGarXiv:2412.11376v12024
When Bad Data Leads to Good Models
Kenneth Li, Yida Chen, Fernanda Viégas +1
cs.LGcs.AIcs.CLarXiv:2505.04741v12025
Summaries:한국어
Learning coordinated badminton skills for legged manipulators
Yuntao Ma, Andrei Cramariuc, Farbod Farshidian +1
cs.ROcs.LGarXiv:2505.22974v22025
DexterityGen: Foundation Controller for Unprecedented Dexterity
Zhao-Heng Yin, Changhao Wang, Luis Pineda +11
cs.ROcs.AIcs.LGarXiv:2502.04307v12025
Multilingual Routing in Mixture-of-Experts
Lucas Bandarkar, Chenyuan Yang, Mohsen Fayyaz +2
cs.CLcs.AIcs.LGarXiv:2510.04694v22025
LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Feng Li, Renrui Zhang, Hao Zhang +5
cs.CVcs.CLcs.LGarXiv:2407.07895v22024
Characterization of Large Language Model Development in the Datacenter
Qinghao Hu, Zhisheng Ye, Zerui Wang +9
cs.DCcs.LGarXiv:2403.07648v22024
Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
Saffron Huang, Esin Durmus, Miles McCain +7
cs.CLcs.AIcs.CYarXiv:2504.15236v12025
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning
Jiaxing Zhao, Xihan Wei, Liefeng Bo
cs.LGcs.CVarXiv:2503.05379v22025
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
Pranjal Aggarwal, Sean Welleck
cs.CLcs.AIcs.LGarXiv:2503.04697v22025
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Yixin Liu, Kai Zhang, Yuan Li +9
cs.CVcs.AIcs.LGarXiv:2402.17177v32024
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Marianne Arriola, Aaron Gokaslan, Justin T. Chiu +5
cs.LGcs.AIarXiv:2503.09573v32025
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Yuhui Li, Fangyun Wei, Chao Zhang +1
cs.LGcs.CLarXiv:2401.15077v32024
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
Dayu Yang, Tianyang Liu, Daoan Zhang +8
cs.CLcs.AIcs.LGarXiv:2502.19411v12025
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova +5
cs.CLcs.AIcs.LGarXiv:2401.12070v32024
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca +9
cs.LGcs.AIcs.NEarXiv:2502.14546v12025
mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
Marc Marone, Orion Weller, William Fleshman +3
cs.CLcs.IRcs.LGarXiv:2509.06888v12025
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
Mingqi Wu, Zhihao Zhang, Qiaole Dong +11
cs.LGcs.AIcs.CLarXiv:2507.10532v32025
One Token to Fool LLM-as-a-Judge
Yulai Zhao, Haolin Liu, Dian Yu +4
cs.LGcs.CLarXiv:2507.08794v32025
House of Cards: Massive Weights in LLMs
Jaehoon Oh, Seungjun Shin, Dokwan Oh
cs.LGcs.AIcs.CLarXiv:2410.01866v22024
Maximizing Confidence Alone Improves Reasoning
Mihir Prabhudesai, Lili Chen, Alex Ippoliti +3
cs.LGcs.AIarXiv:2505.22660v42025
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Zengzhi Wang, Fan Zhou, Xuefeng Li +1
cs.CLcs.AIcs.LGarXiv:2506.20512v12025
PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
Wei Chow, Jiageng Mao, Boyi Li +3
cs.CVcs.AIcs.CLarXiv:2501.16411v22025

Machine Learning

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies

Resource-Efficient Iterative LLM-Based NAS with Feedback Memory

Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs

Uncertainty-Aware Vision-Language Segmentation for Medical Imaging

SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

On the Generalization Capacities of MLLMs for Spatial Intelligence

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Open Problems in Machine Unlearning for AI Safety

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing

Self-Evaluation Unlocks Any-Step Text-to-Image Generation

Learning a Generative Meta-Model of LLM Activations

Evaluating Gemini Robotics Policies in a Veo World Simulator

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Scaling Spatial Intelligence with Multimodal Foundation Models

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Boomerang Distillation Enables Zero-Shot Model Size Interpolation

Where Do the Joules Go? Diagnosing Inference Energy Consumption

Regression Language Models for Code

SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion

Jamba: A Hybrid Transformer-Mamba Language Model

Towards Automated Kernel Generation in the Era of LLMs

RM -RF: Reward Model for Run-Free Unit Test Evaluation

A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5

Mercury: Ultra-Fast Language Models Based on Diffusion

A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective

What Large Language Models Know and What People Think They Know

FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

AgentOCR: Reimagining Agent History via Optical Self-Compression

xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations

A Survey on Diffusion Language Models

PCMind-2.1-Kaiyuan-2B Technical Report

TradingAgents: Multi-Agents LLM Financial Trading Framework

S*: Test Time Scaling for Code Generation

ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data

When Bad Data Leads to Good Models

Learning coordinated badminton skills for legged manipulators

DexterityGen: Foundation Controller for Unprecedented Dexterity

Multilingual Routing in Mixture-of-Experts

LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Characterization of Large Language Model Development in the Datacenter

Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions

R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

One Token to Fool LLM-as-a-Judge

House of Cards: Massive Weights in LLMs

Maximizing Confidence Alone Improves Reasoning

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding