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)

18,961 to 19,020 of 20,193

Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields
Yixuan Sun, Anirban Samaddar, Sandeep Madireddy
cs.LGphysics.comp-pharXiv:2608.18004v12026
Recirculation
Michael C. Mozer, Shoaib Ahmed Siddiqui, Danny Sawyer +2
cs.LGarXiv:2608.17981v12026
Summaries:한국어
MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models
Ya Wen, Jixuan Cai, Yulun Zhou +1
cs.LGcs.SIarXiv:2608.17848v12026
Spatially explicit feature importance for building height estimation using research-access high-resolution SAR and optical sensors
Guilherme Iablonovski, Pierre-Louis Frison, Tatiana Silva da Silva
physics.soc-phcs.LGstat.MLarXiv:2608.17822v12026
MoNe: Modular Neural Memory for Efficient Long Context Inference
Wonguk Cho, Kyubyung Chae, Tribhuvanesh Orekondy +6
cs.AIcs.CLcs.LGarXiv:2608.17616v12026
Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics
Zhikai Ding, Ziyi Ye
cs.LGcs.AIarXiv:2608.17268v12026
Task Specialization Fine-Tuning for Contextual Reinforcement Learning
Jianan Zhou, Jung-Hoon Cho, Tianyue Zhou +5
cs.LGcs.AIarXiv:2608.17180v12026
Summaries:한국어
SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version
Tuan-Binh Tran, Dat Nguyen Cong, Duc-Trong Le +2
cs.LGarXiv:2608.17164v12026
OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics
Mingyu Li, Guorui Song, Jing Lin +1
cs.LGarXiv:2608.17162v12026
RoBell-RVFL: A Robust Generalized Bell Random Vector Functional Link Network
A. Rahaman, A. Quadir, M. Tanveer
cs.LGarXiv:2608.16965v12026
ComNetX: Local Hierarchical Adaptation for Dynamic Community Detection
Aleksandr Konovalov, Anna Uporova, Alexander Drobyshev +2
cs.SIcs.AIcs.LGarXiv:2608.16906v12026
Q-based Variational Inverse Reinforcement Learning
Ondrej Bajgar, Peter Tisnikar, Alessandro Abate +2
cs.LGarXiv:2608.16888v12026
RadioVIL: Anomaly-Aware Diffusion Models for Radio Map Inpainting and Zero-Shot Vehicle Localization
Ruixin Zhao, Xiucheng Wang, Qiming Zhang +3
eess.SPcs.LGarXiv:2608.16167v12026
A Tree-Structured Approach for Phishing Template and Attacker Attribution Analysis
Unai Agirre, Imanol Jerico, Felipe Castaño +2
cs.LGcs.AIcs.ETarXiv:2608.16158v12026
Functional anatomy of Pythia-Herwig differences with Kolmogorov-Arnold networks
Arghya Chattopadhyay
hep-phcs.LGarXiv:2608.15952v12026
PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails
Satchit Chatterji, Shihan Wang, Giovanni Sileno +1
cs.LGcs.AIarXiv:2608.15673v12026
SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates
Ziming Yu, Shuyao Xiao, Xingyu Zhao +6
cs.LGarXiv:2608.15665v12026
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy
Qingyao Yang, Runming Yang, He Xiao +7
cs.LGcs.AIarXiv:2608.15602v12026
GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix
Jinhyun Jeon, Sungjoo Yoo
cs.LGcs.AIarXiv:2608.15584v12026
ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems
Rakesh Sharma, Sydney Pugh, Cameron Beeche +14
cs.MAcs.AIcs.LGarXiv:2608.15424v12026
FAST-DeepONet: Factor-Augmented Branch Representations for High-Dimensional PDE Inputs in the Small-Sample Regime
Jiyong Kwon, Bongseok Kim, Guang Lin
cs.LGarXiv:2608.15408v12026
No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage
Shiven Khurdi
cs.LGcs.AIarXiv:2608.15286v12026
Sufficient Dimesion Reduction via Generalized Stein's Lemma
Ye Tian
stat.MLcs.LGstat.MEarXiv:2608.15121v12026
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
Aman Singh Thakur, Rayan Khoury
cs.CLcs.LGarXiv:2608.14929v12026
STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation
Nawrin Tabassum, Yanzhao Wu
cs.CRcs.LGarXiv:2608.14861v12026
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
Tony Tu, Sayan Chakraborty, Ruomeng Xu +2
cs.AIcs.CLcs.LGarXiv:2608.14828v12026
A Vision Transformer for ECG-Based Detection of Left Ventricular Systolic Dysfunction Across Multiple Clinical Sites
Burcu Ozek, Aruna Mohan, David Vorchheimer +5
cs.CVcs.LGarXiv:2608.14723v12026
RouteTS: Frequency-Time Routing for Time Series Forecasting
Gaofeng Lin, Lei Duan
cs.LGstat.MLarXiv:2608.14682v12026
Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion
Zeyu Liu, Jinhao Zhang, Yunquan Zhang +4
cs.LGarXiv:2608.14664v12026
Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms
Xianzong Wu, Xiaohong Li, Yuejun Guo +4
cs.LGcs.AIarXiv:2608.14653v12026
BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials
An Vuong, Chen Zhao, Jin Hu +2
cs.LGcond-mat.mtrl-scics.AIarXiv:2608.14640v12026
Detecting Contaminated Code-Generation Prompt Batches via Influence Functions
Francesco Quinzan, Noor Munir, Yishun Lu +1
cs.LGarXiv:2608.14303v12026
Doubly Robust Estimation of Causal Effect on CVR with Targeted Regularization
Jiayi Dan, Bo Li, Lu Deng +1
cs.LGarXiv:2608.13461v12026
High-dimensional networks and mean squared error for possibly misspecified models
Lourens Waldorp
stat.MLcs.LGarXiv:2608.13171v12026
Summaries:简体中文
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
Kenta Watanabe, Atsuyuki Miyai, Mizuki Takenawa +2
cs.CVcs.AIcs.LGarXiv:2608.08814v12026
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
Bohai Gu, Yueyang Yuan, Taiyi Wu +9
cs.AIcs.LGarXiv:2608.04964v12026
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
Kejian Zhu, Zhuoran Jin, Shangqing Tu +5
cs.CLcs.LGarXiv:2608.03573v22026
Summaries:한국어
Verifier-Induced Support Reshaping in On-Policy Optimization
Shaohang Wei, Zikun Su, Feifan Song +4
cs.LGcs.CLarXiv:2608.00220v12026
Predictive Divergence Masks for LLM RL
Xiangxin Zhou, Jiarui Yao, Penghui Qi +4
cs.LGarXiv:2607.10848v12026
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Siyuan Li, Jiabao Pan, Yumou Liu +9
cs.LGcs.AIarXiv:2607.04033v12026
Summaries:한국어
Optimizing Visual Generative Models via Distribution-wise Rewards
Ruihang Li, Mengde Xu, Shuyang Gu +4
cs.LGcs.CVarXiv:2607.02291v12026
CausalMix: Data Mixture as Causal Inference for Language Model Training
Zinan Tang, Yukun Zhang, Shaomian Zheng +6
cs.LGcs.AIcs.CLarXiv:2607.01104v12026
Valdi: Value Diffusion World Models
Christopher Lindenberg, Kashyap Chitta
cs.LGcs.AIarXiv:2607.00917v12026
Semantic Browsing: Controllable Diversity for Image Generation
Sara Dorfman, Maya Vishnevsky, Omer Dahary +2
cs.CVcs.AIcs.GRarXiv:2606.23679v12026
Summaries:한국어
SkillHarness: Harnessing Safe Skills for Computer-Use Agents
Yurun Chen, Biao Yi, Keting Yin +1
cs.AIcs.CLcs.CRarXiv:2606.20636v12026
Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments
Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel +22
cs.LGarXiv:2606.14397v22026
Summaries:한국어
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li +13
cs.LGcs.CLarXiv:2606.12344v12026
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization
Xukun Zhu, Hang Yu, Peng Di +1
cs.LGcs.CLarXiv:2606.10768v12026
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi
cs.AIcs.CLcs.LGarXiv:2606.10740v22026
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
Jingbo Gong, Yikai Wang, Yushi Lan +6
cs.CVcs.AIcs.LGarXiv:2606.06601v12026
Unsupervised Skill Discovery for Agentic Data Analysis
Zhisong Qiu, Kangqi Song, Shengwei Tang +4
cs.AIcs.CLcs.LGarXiv:2606.06416v12026
Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation
Maxime Griot, Paul Steven Scotti, Tanishq Mathew Abraham
cs.LGcs.CLarXiv:2606.05988v12026
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Tao Chen, Gangwei Jiang, Pengyu Cheng +10
cs.LGcs.CLarXiv:2606.03980v12026
Policy and World Modeling Co-Training for Language Agents
Ning Lu, Baijiong Lin, Shengcai Liu +9
cs.LGcs.AIarXiv:2606.02388v12026
Trust Region On-Policy Distillation
Xingrun Xing, Haoqing Wang, Boyan Gao +2
cs.LGcs.CLarXiv:2606.01249v32026
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
Xinchen Zhang, Bowei Liu, Jiale Liu +7
cs.CLcs.AIcs.CVarXiv:2605.28805v12026
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
Sachin Kumar
cs.CLcs.AIcs.LGarXiv:2605.27958v12026
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Shihao Wang, Shilong Liu, Yuanguo Kuang +10
cs.CVcs.AIcs.LGarXiv:2605.27365v22026
When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges
Parth Darshan, Abhishek Divekar
cs.CLcs.AIcs.LGarXiv:2605.26046v22026
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM
Yubo Li, Yidi Miao
cs.LGcs.AIarXiv:2605.24786v12026

Machine Learning

Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields

Recirculation

MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models

Spatially explicit feature importance for building height estimation using research-access high-resolution SAR and optical sensors

MoNe: Modular Neural Memory for Efficient Long Context Inference

Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics

Task Specialization Fine-Tuning for Contextual Reinforcement Learning

SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version

OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics

RoBell-RVFL: A Robust Generalized Bell Random Vector Functional Link Network

ComNetX: Local Hierarchical Adaptation for Dynamic Community Detection

Q-based Variational Inverse Reinforcement Learning

RadioVIL: Anomaly-Aware Diffusion Models for Radio Map Inpainting and Zero-Shot Vehicle Localization

A Tree-Structured Approach for Phishing Template and Attacker Attribution Analysis

Functional anatomy of Pythia-Herwig differences with Kolmogorov-Arnold networks

PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails

SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates

FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy

GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix

ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems

FAST-DeepONet: Factor-Augmented Branch Representations for High-Dimensional PDE Inputs in the Small-Sample Regime

No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage

Sufficient Dimesion Reduction via Generalized Stein's Lemma

Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment

A Vision Transformer for ECG-Based Detection of Left Ventricular Systolic Dysfunction Across Multiple Clinical Sites

RouteTS: Frequency-Time Routing for Time Series Forecasting

Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion

Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms

BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials

Detecting Contaminated Code-Generation Prompt Batches via Influence Functions

Doubly Robust Estimation of Causal Effect on CVR with Targeted Regularization

High-dimensional networks and mean squared error for possibly misspecified models

360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents

WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Verifier-Induced Support Reshaping in On-Policy Optimization

Predictive Divergence Masks for LLM RL

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Optimizing Visual Generative Models via Distribution-wise Rewards

CausalMix: Data Mixture as Causal Inference for Language Model Training

Valdi: Value Diffusion World Models

Semantic Browsing: Controllable Diversity for Image Generation

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

Direct 3D-Aware Object Insertion via Decomposed Visual Proxies

Unsupervised Skill Discovery for Agentic Data Analysis

Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation

Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill

Policy and World Modeling Co-Training for Language Agents

Trust Region On-Policy Distillation

OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM