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)

5,521 to 5,580 of 20,063

Multiclass learnability and the ERM principle
Amit Daniely, Sivan Sabato, Shai Ben-David +1
cs.LGarXiv:1308.2893v22013
Robust Autonomy Emerges from Self-Play
Marco Cusumano-Towner, David Hafner, Alex Hertzberg +9
cs.LGcs.AIcs.ROarXiv:2502.03349v12025
TileLang: A Composable Tiled Programming Model for AI Systems
Lei Wang, Yu Cheng, Yining Shi +8
cs.LGarXiv:2504.17577v22025
Continuous and Discrete-Time Survival Prediction with Neural Networks
Håvard Kvamme, Ørnulf Borgan
stat.MLcs.LGstat.MEarXiv:1910.06724v12019
Graph Barlow Twins: A self-supervised representation learning framework for graphs
Piotr Bielak, Tomasz Kajdanowicz, Nitesh V. Chawla
cs.LGarXiv:2106.02466v32021
Soft-Argmax for the Projective Plane via the Veronese Embedding
Benjamin El-Zein, Dominik Eckert, Paul Zech +4
cs.CVcs.LGarXiv:2609.00521v12026
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Zhenyu Hou, Xin Lv, Rui Lu +6
cs.LGcs.CLarXiv:2501.11651v22025
ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
Zexi Liu, Yuzhu Cai, Xinyu Zhu +6
cs.AIcs.LGarXiv:2506.16499v12025
On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study
Chathurika S Abeykoon, Mathias Nthiani Muia, Mallory Goldstein
stat.MLcs.LGarXiv:2609.01410v12026
The Dormant Neuron Phenomenon in Deep Reinforcement Learning
Ghada Sokar, Rishabh Agarwal, Pablo Samuel Castro +1
cs.LGarXiv:2302.12902v22023
Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning
Jérôme Bolte, Edouard Pauwels
math.OCcs.AIcs.LGarXiv:1909.10300v42019
What Makes a Reward Model a Good Teacher? An Optimization Perspective
Noam Razin, Zixuan Wang, Hubert Strauss +3
cs.LGcs.AIcs.CLarXiv:2503.15477v42025
Can Large Reasoning Models Self-Train?
Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov +2
cs.LGarXiv:2505.21444v22025
Vid2World: Crafting Video Diffusion Models to Interactive World Models
Siqiao Huang, Jialong Wu, Qixing Zhou +2
cs.CVcs.LGarXiv:2505.14357v32025
Agent Learning via Early Experience
Kai Zhang, Xiangchao Chen, Bo Liu +27
cs.AIcs.CLcs.IRarXiv:2510.08558v32025
Impact of Pretraining Term Frequencies on Few-Shot Reasoning
Yasaman Razeghi, Robert L. Logan, Matt Gardner +1
cs.CLcs.LGarXiv:2202.07206v22022
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
Pan Lu, Bowen Chen, Sheng Liu +3
cs.LGcs.CLcs.CVarXiv:2502.11271v22025
A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis
Maria Chiara Fiorentino, Francesca Pia Villani, Mariachiara Di Cosmo +2
eess.IVcs.CVcs.LGarXiv:2201.12260v12022
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Tomáš Holeček, Viliam Lisý
cs.LGarXiv:2609.01549v12026
Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training
Guangqi Li, Yongxin Li
cs.LGarXiv:2609.01170v12026
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola +6
cs.LGcs.CLarXiv:2501.19309v12025
DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement
Pancheng Niu, Jun Guo, Qiaolin He +2
cs.LGarXiv:2609.00530v12026
InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
Hongkai Zheng, Wenda Chu, Bingliang Zhang +9
cs.LGarXiv:2503.11043v22025
Comprehensive Comparative Study of Multi-Label Classification Methods
Jasmin Bogatinovski, Ljupčo Todorovski, Sašo Džeroski +1
cs.LGcs.AIcs.CCarXiv:2102.07113v22021
Stock Price Prediction Using Machine Learning and LSTM-Based Deep Learning Models
Sidra Mehtab, Jaydip Sen, Abhishek Dutta
q-fin.STcs.LGarXiv:2009.10819v12020
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
Bartosz Cywiński, Kamil Deja
cs.LGcs.AIarXiv:2501.18052v32025
How to use and interpret activation patching
Stefan Heimersheim, Neel Nanda
cs.LGarXiv:2404.15255v12024
Attention Interpretability Across NLP Tasks
Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar +1
cs.CLcs.LGarXiv:1909.11218v12019
Auditing language models for hidden objectives
Samuel Marks, Johannes Treutlein, Trenton Bricken +32
cs.AIcs.CLcs.LGarXiv:2503.10965v22025
Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading
Fatemeh Javadian, Zhu Chen, Zahra Aminparast +1
cs.CVcs.AIcs.LGarXiv:2609.01426v12026
Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity
Sinjini Banerjee, Tim Marrinan, Anand D. Sarwate
stat.MLcs.AIcs.LGarXiv:2609.01397v12026
One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Tao Liu, Kai Wang, Senmao Li +6
cs.CVcs.AIcs.LGarXiv:2501.13554v32025
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
Nicholas Watters, Loic Matthey, Christopher P. Burgess +1
cs.LGcs.CVstat.MLarXiv:1901.07017v22019
DualStake: Dual-Path Confidence Calibration in Deep Research Agents
Yinuo Xu, Yuwei Liang, Jianjie Cheng +4
cs.CLcs.AIcs.LGarXiv:2609.00935v12026
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning
Martin Mundt, Yongwon Hong, Iuliia Pliushch +1
cs.LGstat.MLarXiv:2009.01797v32020
Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
Miso Kim, Georu Lee, Seungwon Jeong +1
cs.LGcs.AIcs.CLarXiv:2609.00605v12026
A Study of Hidden-State Optimization Order in Predictive Coding Networks
Xueyuan Li, Danilo Vasconcellos Vargas
cs.LGcs.AIarXiv:2609.00686v12026
Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
Siddhartha Chandra, Iasonas Kokkinos
cs.CVcs.LGarXiv:1603.08358v42016
Universal Model Routing for Efficient LLM Inference
Wittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat +9
cs.CLcs.LGarXiv:2502.08773v22025
ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives
Nikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos +1
cs.CVcs.AIcs.LGarXiv:2609.01041v12026
Sparse Autoencoders Do Not Find Canonical Units of Analysis
Patrick Leask, Bart Bussmann, Michael Pearce +5
cs.LGcs.AIarXiv:2502.04878v12025
Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images
Xiaocong Chen, Lina Yao, Tao Zhou +2
eess.IVcs.CVcs.LGarXiv:2006.13276v12020
SMART: Self-Aware Agent for Tool Overuse Mitigation
Cheng Qian, Emre Can Acikgoz, Hongru Wang +5
cs.AIcs.CLcs.LGarXiv:2502.11435v22025
Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos
Annie S. Chen, Suraj Nair, Chelsea Finn
cs.ROcs.AIcs.CVarXiv:2103.16817v12021
On the Doubt about Margin Explanation of Boosting
Wei Gao, Zhi-Hua Zhou
cs.LGarXiv:1009.3613v52010
Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches
Marco Simnacher, Georg Keilbar, Benjamin König +2
stat.MLcs.AIcs.LGarXiv:2609.00946v12026
TimeNet: Pre-trained deep recurrent neural network for time series classification
Pankaj Malhotra, Vishnu TV, Lovekesh Vig +2
cs.LGarXiv:1706.08838v12017
Learning the Travelling Salesperson Problem Requires Rethinking Generalization
Chaitanya K. Joshi, Quentin Cappart, Louis-Martin Rousseau +1
cs.LGstat.MLarXiv:2006.07054v62020
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
Yuhang Li, Ruokai Yin, Donghyun Lee +2
cs.LGarXiv:2504.02692v32025
FlexiViT: One Model for All Patch Sizes
Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov +7
cs.CVcs.AIcs.LGarXiv:2212.08013v22022
Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
Masatoshi Uehara, Yulai Zhao, Chenyu Wang +4
cs.AIcs.LGq-bio.QMarXiv:2501.09685v22025
Learning-Theoretic Foundation for General Coded Computing: The Straggler Setting
Parsa Moradi, Behrooz Tahmasebi, Mohammad Ali Maddah-Ali
cs.LGarXiv:2608.28910v12026
FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing
Yi Luo, Enea Ceolini, Cong Han +2
eess.AScs.LGcs.SDarXiv:1909.13387v22019
Reconstructing Training Data from Trained Neural Networks
Niv Haim, Gal Vardi, Gilad Yehudai +2
cs.LGcs.CRcs.CVarXiv:2206.07758v32022
Not All Language Model Features Are One-Dimensionally Linear
Joshua Engels, Eric J. Michaud, Isaac Liao +2
cs.LGarXiv:2405.14860v32024
One Token to Fool LLM-as-a-Judge
Yulai Zhao, Haolin Liu, Dian Yu +4
cs.LGcs.CLarXiv:2507.08794v32025
HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
Zhilin Wang, Jiaqi Zeng, Olivier Delalleau +6
cs.CLcs.AIcs.LGarXiv:2505.11475v22025
Convergence issues in Relational Concept Analysis based on AOC-posets
Xavier Dolques, Agnès Braud, Alain Gutierrez +2
cs.LGarXiv:2609.00054v12026
AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training
Chia-Yu Chen, Jungwook Choi, Daniel Brand +3
cs.LGstat.MLarXiv:1712.02679v12017
GSPMD: General and Scalable Parallelization for ML Computation Graphs
Yuanzhong Xu, HyoukJoong Lee, Dehao Chen +13
cs.DCcs.LGarXiv:2105.04663v22021

Machine Learning

Multiclass learnability and the ERM principle

Robust Autonomy Emerges from Self-Play

TileLang: A Composable Tiled Programming Model for AI Systems

Continuous and Discrete-Time Survival Prediction with Neural Networks

Graph Barlow Twins: A self-supervised representation learning framework for graphs

Soft-Argmax for the Projective Plane via the Veronese Embedding

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning

On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning

What Makes a Reward Model a Good Teacher? An Optimization Perspective

Can Large Reasoning Models Self-Train?

Vid2World: Crafting Video Diffusion Models to Interactive World Models

Agent Learning via Early Experience

Impact of Pretraining Term Frequencies on Few-Shot Reasoning

OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning

A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement

InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

Comprehensive Comparative Study of Multi-Label Classification Methods

Stock Price Prediction Using Machine Learning and LSTM-Based Deep Learning Models

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

How to use and interpret activation patching

Attention Interpretability Across NLP Tasks

Auditing language models for hidden objectives

Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading

Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs

DualStake: Dual-Path Confidence Calibration in Deep Research Agents

A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning

Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning

A Study of Hidden-State Optimization Order in Predictive Coding Networks

Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs

Universal Model Routing for Efficient LLM Inference

ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives

Sparse Autoencoders Do Not Find Canonical Units of Analysis

Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images

SMART: Self-Aware Agent for Tool Overuse Mitigation

Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos

On the Doubt about Margin Explanation of Boosting

Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches

TimeNet: Pre-trained deep recurrent neural network for time series classification

Learning the Travelling Salesperson Problem Requires Rethinking Generalization

GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration

FlexiViT: One Model for All Patch Sizes

Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review

Learning-Theoretic Foundation for General Coded Computing: The Straggler Setting

FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing

Reconstructing Training Data from Trained Neural Networks

Not All Language Model Features Are One-Dimensionally Linear

One Token to Fool LLM-as-a-Judge

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Convergence issues in Relational Concept Analysis based on AOC-posets

AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training

GSPMD: General and Scalable Parallelization for ML Computation Graphs