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)

17,761 to 17,820 of 20,193

Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
Mu Nan, Muquan Yu, Weijian Mai +12
cs.LGq-bio.NCarXiv:2604.08537v12026
Envisioning the Future, One Step at a Time
Stefan Andreas Baumann, Jannik Wiese, Tommaso Martorella +2
cs.CVcs.AIcs.LGarXiv:2604.09527v12026
MixFlow: Mixed Source Distributions Improve Rectified Flows
Nazir Nayal, Christopher Wewer, Jan Eric Lenssen
cs.CVcs.LGarXiv:2604.09181v12026
DMax: Aggressive Parallel Decoding for dLLMs
Zigeng Chen, Gongfan Fang, Xinyin Ma +2
cs.LGcs.AIarXiv:2604.08302v32026
Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
Chanhyuk Choi, Taesoo Kim, Donggyu Lee +2
cs.CVcs.LGarXiv:2604.07786v22026
Efficient RL Training for LLMs with Experience Replay
Charles Arnal, Vivien Cabannes, Taco Cohen +2
cs.LGarXiv:2604.08706v12026
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
Makanjuola Ogunleye, Eman Abdelrahman, Ismini Lourentzou
cs.CVcs.AIcs.LGarXiv:2604.08645v12026
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
Yi-Lun Liao, Alexander J. Hoffman, Sabrina C. Shen +3
cs.LGcs.AIphysics.comp-pharXiv:2604.09130v12026
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
Hadas Orgad, Boyi Wei, Kaden Zheng +4
cs.CLcs.AIcs.LGarXiv:2604.09544v22026
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
Lifeng Chen, Tianqi You, Hao Liu +8
cs.LGcs.AIeess.IVarXiv:2604.09450v22026
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Ximing Xing, Ziteng Xue, Zhenxi Li +8
cs.LGarXiv:2604.05072v22026
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
Ivan Sedykh, Nikita Sorokin, Valentin Malykh
cs.LGcs.CLarXiv:2604.02340v22026
A Temporally Augmented Graph Attention Network for Affordance Classification
Ami Chopra, Supriya Bordoloi, Shyamanta M. Hazarika
cs.LGcs.AIarXiv:2604.10149v12026
Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models
Md Tanvirul Alam
cs.CVcs.LGarXiv:2604.12119v12026
ADD for Multi-Bit Image Watermarking
An Luo, Jie Ding
stat.MLcs.AIcs.LGarXiv:2604.11491v12026
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Gregory N. Frank
cs.CLcs.AIcs.LGarXiv:2604.04385v52026
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Hanqi Xiao, Vaidehi Patil, Zaid Khan +3
cs.CLcs.AIcs.LGarXiv:2604.11666v22026
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation
Sandro Andric
cs.LGcs.AIcs.CYarXiv:2604.11840v32026
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
Haolin Li, Shuyang Jiang, Ruipeng Zhang +3
cs.LGcs.CLarXiv:2604.11547v12026
Continuous Adversarial Flow Models
Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2
cs.LGcs.CVarXiv:2604.11521v12026
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
Mihir Prabhudesai, Aryan Satpathy, Yangmin Li +6
cs.LGcs.AIcs.CVarXiv:2604.11805v12026
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Yuzhen Mao, Qitong Wang, Martin Ester +1
cs.LGcs.AIarXiv:2604.10539v12026
Rethinking the Diffusion Model from a Langevin Perspective
Candi Zheng, Yuan Lan
cs.LGcs.AIcs.CVarXiv:2604.10465v12026
PokeRL: Reinforcement Learning for Pokemon Red
Dheeraj Mudireddy, Sai Patibandla
cs.LGarXiv:2604.10812v12026
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
Zhipeng Chen, Tao Qian, Wayne Xin Zhao +1
cs.LGcs.AIcs.CLarXiv:2604.11446v12026
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Yang Liu, Enxi Wang, Yufei Gao +6
cs.LGcs.AIcs.CLarXiv:2604.11297v12026
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Junxiao Yang, Haoran Liu, Jinzhe Tu +9
cs.LGcs.AIcs.CLarXiv:2604.12710v22026
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
Fei Tang, Zhiqiong Lu, Boxuan Zhang +4
cs.LGcs.AIcs.CLarXiv:2604.11784v12026
Towards Autonomous Mechanistic Reasoning in Virtual Cells
Yunhui Jang, Lu Zhu, Jake Fawkes +3
cs.LGcs.AIarXiv:2604.11661v32026
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization
Zhengxi Lu, Fei Tang, Guangyi Liu +8
cs.LGarXiv:2604.13822v12026
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Andrei Atanov, Jesse Allardice, Roman Bachmann +6
cs.CVcs.LGarXiv:2604.12887v12026
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Jiacheng Liu, Xiaohan Zhao, Xinyi Shang +1
cs.SEcs.AIcs.CLarXiv:2604.14228v22026
Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
Eun Woo Im, Dhruv Madhwal, Vivek Gupta
cs.LGarXiv:2604.13313v12026
TIP: Token Importance in On-Policy Distillation
Yuanda Xu, Hejian Sang, Zhengze Zhou +3
cs.LGcs.AIarXiv:2604.14084v42026
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
Yuqiao Tan, Minzheng Wang, Bo Liu +5
cs.LGcs.AIcs.CLarXiv:2604.14142v12026
C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
Akira Kawabata, Saku Sugawara
cs.CLcs.LGarXiv:2604.13618v12026
Three-Phase Transformer
Mohammad R. Abu Ayyash
cs.CLcs.AIcs.LGarXiv:2604.14430v12026
(1D) Ordered Tokens Enable Efficient Test-Time Search
Zhitong Gao, Parham Rezaei, Ali Cy +7
cs.CVcs.AIcs.LGarXiv:2604.15453v12026
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang, Shaowei Zhu, Anjiang Wei +6
cs.LGcs.CLarXiv:2511.15915v22025
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
cs.LGarXiv:2604.13602v12026
Where does output diversity collapse in post-training?
Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras
cs.CLcs.AIcs.LGarXiv:2604.16027v12026
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Wangjie Gan, Miao Pan, Linbo Xi +4
cs.AIcs.LGarXiv:2604.14258v32026
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
Quyen Tran, Hai Nguyen, Hoang Phan +6
cs.LGcs.CVarXiv:2211.16780v42022
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
Bowen Ping, Zijun Chen, Tingfeng Hui +4
cs.LGcs.CLarXiv:2604.14922v12026
PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
Tingjia Miao, Wenkai Jin, Muhua Zhang +19
cs.LGcs.AIphysics.data-anarXiv:2604.15411v12026
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
Ido Galil, Moshe Kimhi, Ran El-Yaniv
cs.LGcs.AIcs.CVarXiv:2502.07408v22025
PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction
Yoshitaka Inoue, Minoh Jeong, Alfred Hero +2
q-bio.QMcs.LGarXiv:2608.21349v12026
TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation
Tristan Kirscher, Alexandra Ertl, Klaus Maier-Hein +3
cs.LGarXiv:2604.15950v22026
Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints
Xinge Liu, Terry Jingchen Zhang, Bernhard Schölkopf +2
cs.LGcs.AIarXiv:2604.15664v22026
Structured Scaling of AI Discovery Across Diverse Scientific Domains
Haotian Ye, Haowei Lin, Jingyi Tang +30
cs.LGcs.AIarXiv:2604.19341v22026
Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
Victorita Dolean, Jemima Tabeart
math.NAcs.LGarXiv:2608.21234v12026
The Exceedance Design Effect: Effective Sample Size for Thresholds under Clustering
Adam Noonan
stat.MLcs.LGarXiv:2608.21262v12026
EasyVideoR1: Easier RL for Video Understanding
Chuanyu Qin, Chenxu Yang, Qingyi Si +6
cs.CVcs.LGarXiv:2604.16893v12026
Truthful Calibration Measures for Sequential Prediction
Anagha Gokul, Jason Hartline, Lunjia Hu +2
cs.DScs.GTcs.LGarXiv:2608.21348v12026
Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts
Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng Sun
cs.LGcs.AIeess.SParXiv:2604.16926v22026
Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
Leon Engländer, Sophia Althammer, Ahmet Üstün +2
cs.CLcs.LGarXiv:2604.17609v12026
Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection
Kadir-Kaan Özer, René Ebeling, Markus Enzweiler
cs.LGcs.AIarXiv:2604.17388v32026
On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift
Nikhilesh Prabhakar, Pranuthi Tenali, Wilfredo Abudeye Fernandez +5
cs.CVcs.LGarXiv:2608.21254v12026
When Can LLMs Learn to Reason with Weak Supervision?
Salman Rahman, Jingyan Shen, Anna Mordvina +3
cs.LGcs.AIarXiv:2604.18574v12026
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
Shaden Alshammari, Kevin Wen, Abrar Zainal +5
cs.AIcs.DLcs.IRarXiv:2604.18584v22026

Machine Learning

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

Envisioning the Future, One Step at a Time

MixFlow: Mixed Source Distributions Improve Rectified Flows

DMax: Aggressive Parallel Decoding for dLLMs

Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video

Efficient RL Training for LLMs with Experience Replay

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types

ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models

A Temporally Augmented Graph Attention Network for Affordance Classification

Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models

ADD for Multi-Bit Image Watermarking

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation

Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach

Continuous Adversarial Flow Models

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators

IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs

Rethinking the Diffusion Model from a Langevin Perspective

PokeRL: Reinforcement Learning for Pokemon Red

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents

Towards Autonomous Mechanistic Reasoning in Virtual Cells

UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding

TIP: Token Importance in On-Policy Distillation

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space

C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences

Three-Phase Transformer

(1D) Ordered Tokens Enable Efficient Test-Time Search

AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Where does output diversity collapse in post-training?

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning

PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips

PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction

TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation

Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints

Structured Scaling of AI Discovery Across Diverse Scientific Domains

Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)

The Exceedance Design Effect: Effective Sample Size for Thresholds under Clustering

EasyVideoR1: Easier RL for Video Understanding

Truthful Calibration Measures for Sequential Prediction

Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts

Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity

Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection

On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift

When Can LLMs Learn to Reason with Weak Supervision?

MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval