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)

1 to 60 of 28,991

SurFree: a fast surrogate-free black-box attack
Thibault Maho, Teddy Furon, Erwan Le Merrer
cs.CRcs.AIcs.CVarXiv:2011.12807v12020
Online Learning via Sequential Complexities
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
cs.LGstat.MLarXiv:1006.1138v32010
When Generative Models Act as Simulators
Sevan Brodjian, Michael Hobley, Pietro Perona
cs.LGcs.AIarXiv:2610.12847v12026
The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels
Austin Stone, Oscar Ramirez, Kurt Konolige +1
cs.ROcs.AIcs.CVarXiv:2101.02722v12021
Diffusion-Based Generation of Gait Trajectories
Damian Benasco, Juan Carballeira-Lopez, Jaime Ramos-Rojas +4
cs.AIcs.LGcs.ROarXiv:2609.14642v12026
When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems
Seyed Morteza Emadi
cs.AIcs.LGarXiv:2609.14500v12026
Monarch-MoE: Structured Experts for Multimodal Continual Instruction Tuning
Xi Zhang, Boyu Diao, Zesen Chen +3
cs.LGarXiv:2610.13215v12026
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura +3
cs.LGcs.AIcs.CVarXiv:2201.12296v12022
Digital Persuasion: Understanding the Impact of Online Influencers on Public Opinion
Omran Berjawi, Rida Khatoun, Giuseppe Fenza
cs.SIcs.LGarXiv:2609.16062v12026
HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
Jingxuan Fan, Sarah Martinson, Erik Y. Wang +6
cs.LGcs.AIarXiv:2410.09988v22024
REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning
Ziju Shen, Naohao Huang, Fanyi Yang +11
cs.CLcs.AIcs.LGarXiv:2505.20613v32025
NucleoNet: A Nuclear-Aware Determinant Ansatz for Multi-Geometry Neural Variational Monte Carlo
Qiao Gao, Yang Huang, Enze Hou +3
physics.chem-phcs.LGarXiv:2610.12985v12026
EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction
Michelle Espranita Liman, Ioana Ionac, Alexander Müller +3
cs.LGarXiv:2610.13599v12026
Inference-Time Steering Across Scaffolds and Epitopes for Sample-Efficient De Novo Nanobody Design
Mason Minot, Simon Friedensohn, Cédric R. Weber
cs.LGarXiv:2610.13844v12026
Pseudo-Label Augmentation for Affect Sensing in Small Collaborative Groups
Meisam Jamshidi Seikavandi, Tanya Ignatenko, Fabricio Batista Narcizo +3
cs.LGcs.AIcs.HCarXiv:2609.16077v12026
ARB: Advanced Reasoning Benchmark for Large Language Models
Tomohiro Sawada, Daniel Paleka, Alexander Havrilla +6
cs.CLcs.LGarXiv:2307.13692v22023
ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation
Xiaohuan Jia, Renzhe Xu, Xiao Wang +2
cs.LGcs.AIarXiv:2610.13225v12026
Taking Tokenization off the Host for Agentic LLM Serving
Mohammad Siavashi, Pascal Schwinte, Ali Banaei +3
cs.DCcs.CLcs.LGarXiv:2610.13325v12026
TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps
Rohit Patel, Susil Kumar Mohanty, Jeenal Chaudhary
cs.DCcs.AIcs.CRarXiv:2609.14762v22026
Shortcut-Stacked Sentence Encoders for Multi-Domain Inference
Yixin Nie, Mohit Bansal
cs.CLcs.AIcs.LGarXiv:1708.02312v22017
Carryover Drafting: Recycling Rejected States for Speculative Decoding
Jahyun Koo, Sunghyeon Woo, Jaeeun Kil +4
cs.LGcs.AIarXiv:2609.14717v12026
Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels
Weiqi Sun, Qianyue Wu, Wenjia Wang +1
stat.MLcs.AIcs.LGarXiv:2610.13674v12026
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families
Orion Reblitz-Richardson
cs.LGcs.AIcs.CLarXiv:2609.14759v12026
LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup
Qiao Gu, Guanzhi Wang, Mang Tik Chiu +2
cs.CVcs.AIcs.LGarXiv:1904.11272v22019
WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians
Johann Birnick, Rayan Saab
cs.LGcs.AIarXiv:2609.14706v22026
RayProNet: A Neural Point Field Framework for Radio Propagation Modeling in 3D Environments
Ge Cao, Zhen Peng
eess.SPcs.LGarXiv:2406.16907v12024
CV-OPD: Contrastive Vision On-policy Distillation
Haowei Wang, Hao Lin, Qi Zhu +4
cs.CVcs.LGcs.MMarXiv:2610.13264v12026
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo +2
cs.LGcs.AIstat.MLarXiv:1910.07072v22019
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Michal Rolínek, Paul Swoboda, Dominik Zietlow +3
cs.LGstat.MLarXiv:2003.11657v22020
Model Inversion Networks for Model-Based Optimization
Aviral Kumar, Sergey Levine
cs.LGstat.MLarXiv:1912.13464v12019
ECG-FM: An Open Electrocardiogram Foundation Model
Kaden McKeen, Sameer Masood, Augustin Toma +2
cs.LGarXiv:2408.05178v22024
A small cognitive core explains human behavior at scale
Marcel Binz, Eric Schulz
cs.LGarXiv:2610.13603v12026
A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
Jiawei Zhang, Peijun Xiao, Ruoyu Sun +1
math.OCcs.LGarXiv:2010.15768v32020
Task-Specific Skill Localization in Fine-tuned Language Models
Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao +1
cs.CLcs.LGarXiv:2302.06600v22023
adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection
Xuhong Wang, Ying Du, Shijie Lin +3
cs.LGcs.AIstat.MLarXiv:1903.00904v32019
Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR
Thai Quoc On, Homayoon Beigi
eess.AScs.CLcs.LGarXiv:2610.13432v12026
Dream to Remember: Continual Steering of Generalist Robot Policies with World Models
Bahey Tharwat, Iman Nematollahi, Marvin Alles +3
cs.ROcs.CVcs.LGarXiv:2610.13816v12026
JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels
Efstathios Chatziloizos, Konstantinos Vandikas, Aneta Vulgarakis Feljan +2
eess.SPcs.ITcs.LGarXiv:2610.13315v12026
The Dawn of Quantum Natural Language Processing
Riccardo Di Sipio, Jia-Hong Huang, Samuel Yen-Chi Chen +2
cs.CLcs.AIcs.CVarXiv:2110.06510v12021
On the Quality of the Initial Basin in Overspecified Neural Networks
Itay Safran, Ohad Shamir
cs.LGstat.MLarXiv:1511.04210v32015
ETC: Encoding Long and Structured Inputs in Transformers
Joshua Ainslie, Santiago Ontanon, Chris Alberti +7
cs.LGstat.MLarXiv:2004.08483v52020
Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization
Preksha Nema, Shreyas Shetty, Parag Jain +3
cs.CLcs.AIcs.LGarXiv:1804.07789v12018
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
Qipeng Guo, Zhijing Jin, Xipeng Qiu +3
cs.CLcs.AIcs.LGarXiv:2006.04702v32020
Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning
Fei Wang, Zhewei Xu, Pedro Szekely +1
cs.CLcs.AIcs.LGarXiv:2205.03972v12022
CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness
Jiayi Liu, Tinghan Yang, Jennifer Neville
cs.CLcs.AIcs.LGarXiv:2402.14833v12024
BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching
Peizhuang Cong, Qizhi Chen, Haochen Zhao +1
cs.LGarXiv:2410.18701v12024
MoonCast: High-Quality Zero-Shot Podcast Generation
Zeqian Ju, Dongchao Yang, Jianwei Yu +7
eess.AScs.AIcs.CLarXiv:2503.14345v22025
Sonic-AMG: Streaming Human Motion Generation from Spatial Audio
Jingcheng Ni, Zekun Li, Zhiyang Dou +6
cs.CVcs.GRcs.LGarXiv:2610.13300v12026
Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces
George C. Alexandropoulos, Kyriakos Stylianopoulos, Chongwen Huang +3
cs.ITcs.ETcs.LGarXiv:2205.03793v12022
Diversity-Aware Ensemble of Quantum-Classical Models via Combinatorial Fusion
Jingyan Xu, Yuanhong Wu, Samuel Yen-Chi Chen +3
quant-phcs.LGarXiv:2610.13808v12026
Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media
Burla Nur Korkmaz, Petro Moilanen, Ari Salmi +2
cs.LGarXiv:2610.13258v12026
Review of automated time series forecasting pipelines
Stefan Meisenbacher, Marian Turowski, Kaleb Phipps +4
cs.LGarXiv:2202.01712v12022
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
Zhining Liu, Ze Yang, Xiao Lin +6
cs.LGcs.AIarXiv:2505.18442v12025
Transformer-based In-Context Score Operator Learning for Diffusion Models
Wuzhe Xu, Zhaiming Shen, Yulong Lu +2
cs.LGarXiv:2610.13690v12026
TabMF: Learning Dataset Representations with Tabular Foundation Models
Rafiq Kamel, Nicolas Atienza, Aziz Fouché +2
cs.LGarXiv:2610.13818v12026
Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
Egor Cherepanov, Nikita Kachaev, Alexey K. Kovalev +1
cs.LGcs.AIcs.ROarXiv:2502.10550v32025
Rationally Linearized MLPs
Arijit Sehanobish, Byeongchan Kim, Avinava Dubey +2
cs.LGarXiv:2610.13568v12026
Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control
Bert J. Claessens, Peter Vrancx, Frederik Ruelens
cs.LGcs.SYeess.SYarXiv:1604.08382v22016
What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
Yuxuan Gu, Kequan Niu, Xiaocheng Feng +3
cs.CLcs.AIcs.LGarXiv:2610.12995v12026
Majority Vote of Diverse Classifiers for Late Fusion
Emilie Morvant, Amaury Habrard, Stéphane Ayache
stat.MLcs.LGcs.MMarXiv:1404.7796v22014

Machine Learning

SurFree: a fast surrogate-free black-box attack

Online Learning via Sequential Complexities

When Generative Models Act as Simulators

The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels

Diffusion-Based Generation of Gait Trajectories

When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems

Monarch-MoE: Structured Experts for Multimodal Continual Instruction Tuning

Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

Digital Persuasion: Understanding the Impact of Online Influencers on Public Opinion

HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics

REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning

NucleoNet: A Nuclear-Aware Determinant Ansatz for Multi-Geometry Neural Variational Monte Carlo

EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction

Inference-Time Steering Across Scaffolds and Epitopes for Sample-Efficient De Novo Nanobody Design

Pseudo-Label Augmentation for Affect Sensing in Small Collaborative Groups

ARB: Advanced Reasoning Benchmark for Large Language Models

ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation

Taking Tokenization off the Host for Agentic LLM Serving

TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps

Shortcut-Stacked Sentence Encoders for Multi-Domain Inference

Carryover Drafting: Recycling Rejected States for Speculative Decoding

Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels

Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families

LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup

WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians

RayProNet: A Neural Point Field Framework for Radio Propagation Modeling in 3D Environments

CV-OPD: Contrastive Vision On-policy Distillation

Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Model Inversion Networks for Model-Based Optimization

ECG-FM: An Open Electrocardiogram Foundation Model

A small cognitive core explains human behavior at scale

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems

Task-Specific Skill Localization in Fine-tuned Language Models

adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection

Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels

The Dawn of Quantum Natural Language Processing

On the Quality of the Initial Basin in Overspecified Neural Networks

ETC: Encoding Long and Structured Inputs in Transformers

Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization

CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning

CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness

BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching

MoonCast: High-Quality Zero-Shot Podcast Generation

Sonic-AMG: Streaming Human Motion Generation from Spatial Audio

Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces

Diversity-Aware Ensemble of Quantum-Classical Models via Combinatorial Fusion

Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media

Review of automated time series forecasting pipelines

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

Transformer-based In-Context Score Operator Learning for Diffusion Models

TabMF: Learning Dataset Representations with Tabular Foundation Models

Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning

Rationally Linearized MLPs

Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control

What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training

Majority Vote of Diverse Classifiers for Late Fusion