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)

121 to 180 of 19,911

Training Generative Adversarial Networks with Limited Data
Tero Karras, Miika Aittala, Janne Hellsten +3
cs.CVcs.LGcs.NEarXiv:2006.06676v22020
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
Sreyan Ghosh, Zhifeng Kong, Sonal Kumar +6
cs.SDcs.CLcs.LGarXiv:2503.03983v12025
Deep Learning is Not So Mysterious or Different
Andrew Gordon Wilson
cs.LGstat.MLarXiv:2503.02113v22025
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Patrick Lewis, Ethan Perez, Aleksandra Piktus +9
cs.CLcs.LGarXiv:2005.11401v42020
Summaries:한국어
Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
Shaobo Wang, Yicun Yang, Zhiyuan Liu +4
cs.CVcs.AIcs.LGarXiv:2502.20653v12025
Summaries:한국어
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
Harrish Thasarathan, Julian Forsyth, Thomas Fel +2
cs.CVcs.LGarXiv:2502.03714v22025
Maximum Density Divergence for Domain Adaptation
Li Jingjing, Chen Erpeng, Ding Zhengming +3
cs.CVcs.LGcs.MMarXiv:2004.12615v12020
Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
Junlin Fang, Do Nguyen-Thanh, Xiaogang Xu +2
cs.AIcs.LGarXiv:2607.22098v12026
Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman +3
cs.CVcs.LGarXiv:2001.03152v22020
Frontier Models are Capable of In-context Scheming
Alexander Meinke, Bronson Schoen, Jérémy Scheurer +3
cs.AIcs.LGarXiv:2412.04984v22024
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Zijian Zhang, Rizhen Hu, Athanasios Glentis +4
cs.LGcs.CLarXiv:2607.01232v22026
Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
Wensi Tang, Guodong Long, Lu Liu +3
cs.LGstat.MLarXiv:2002.10061v32020
Beyond IID: How General Are Tabular Foundation Models, Really?
Lennart Purucker, Andrej Tschalzev, Nick Erickson +7
cs.LGcs.AIarXiv:2606.30410v12026
Summaries:한국어
Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
Joseph D. Janizek, Pascal Sturmfels, Su-In Lee
cs.LGstat.MLarXiv:2002.04138v32020
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
Shaowei Liu, Zhongzheng Ren, Saurabh Gupta +1
cs.CVcs.AIcs.LGarXiv:2409.18964v12024
LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
Yijia Xiao, Edward Sun, Tianyu Liu +1
cs.AIcs.CLcs.CVarXiv:2407.04973v12024
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Xin Lai, Zhuotao Tian, Yukang Chen +3
cs.LGcs.AIcs.CLarXiv:2406.18629v12024
Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
Yuge Shi, N. Siddharth, Brooks Paige +1
stat.MLcs.LGarXiv:1911.03393v12019
The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
Benjamin Cramer, Yannik Stradmann, Johannes Schemmel +1
cs.NEcs.LGq-bio.NCarXiv:1910.07407v32019
CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression
Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt
cs.CLcs.AIcs.LGarXiv:2606.24083v12026
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich +10
cs.CLcs.AIcs.LGarXiv:2404.16710v42024
DeepGCNs: Making GCNs Go as Deep as CNNs
Guohao Li, Matthias Müller, Guocheng Qian +4
cs.CVcs.LGeess.IVarXiv:1910.06849v32019
InceptionTime: Finding AlexNet for Time Series Classification
Hassan Ismail Fawaz, Benjamin Lucas, Germain Forestier +7
cs.LGstat.MLarXiv:1909.04939v32019
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback
Ming Li, Taojiannan Yang, Huafeng Kuang +4
cs.CVcs.AIcs.LGarXiv:2404.07987v42024
Anomaly Detection in Video Sequence with Appearance-Motion Correspondence
Trong Nguyen Nguyen, Jean Meunier
cs.CVcs.LGcs.NEarXiv:1908.06351v12019
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking
Jiwan Chung, JiHyuk Byun, Vibhav Vineet +1
cs.AIcs.LGarXiv:2606.15673v22026
Local Differential Privacy for Deep Learning
M. A. P. Chamikara, P. Bertok, I. Khalil +3
cs.LGcs.CRarXiv:1908.02997v32019
Optuna: A Next-generation Hyperparameter Optimization Framework
Takuya Akiba, Shotaro Sano, Toshihiko Yanase +2
cs.LGstat.MLarXiv:1907.10902v12019
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
Zhichen Dong, Zhanhui Zhou, Chao Yang +2
cs.CLcs.AIcs.CYarXiv:2402.09283v32024
Hierarchically Structured Meta-learning
Huaxiu Yao, Ying Wei, Junzhou Huang +1
cs.LGstat.MLarXiv:1905.05301v22019
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
Dongyang Liu, Renrui Zhang, Longtian Qiu +16
cs.CVcs.AIcs.CLarXiv:2402.05935v32024
InstructIR: High-Quality Image Restoration Following Human Instructions
Marcos V. Conde, Gregor Geigle, Radu Timofte
cs.CVcs.LGeess.IVarXiv:2401.16468v52024
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
Anjie Liu, Jianhong Wang, Samuel Kaski +2
cs.AIcs.LGcs.MAarXiv:2510.17697v42025
Fair Transfer of Multiple Style Attributes in Text
Karan Dabas, Nishtha Madan, Vijay Arya +3
cs.CLcs.AIcs.LGarXiv:2001.06693v12020
Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration
Soham De, Anirbit Mukherjee, Enayat Ullah
cs.LGmath.OCstat.MLarXiv:1807.06766v32018
Training Language Models with Language Feedback
Jérémy Scheurer, Jon Ander Campos, Jun Shern Chan +3
cs.CLcs.AIcs.LGarXiv:2204.14146v42022
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis
Satoki Ishikawa, Makoto Yamada, Han Bao +1
cs.LGarXiv:2405.14650v22024
Brain-Inspired Stochastic Joint Embedding Representation Learning
Makoto Yamada, Kian Ming A. Chai, Ayoub Rhim +3
cs.CVcs.AIcs.LGarXiv:2505.11129v22025
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
Pratyaksh Rao, Wancong Zhang, Randall Balestriero +2
cs.ROcs.LGarXiv:2606.23444v22026
Siamese Masked Autoencoders
Agrim Gupta, Jiajun Wu, Jia Deng +1
cs.CVcs.LGarXiv:2305.14344v12023
Visual Representation Learning with Stochastic Frame Prediction
Huiwon Jang, Dongyoung Kim, Junsu Kim +3
cs.CVcs.AIcs.LGarXiv:2406.07398v22024
Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities
Tommi Vatanen, Tapani Raiko, Harri Valpola +1
cs.LGcs.CVstat.MLarXiv:1301.3476v32013
TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability
Tonglong Wei, Yan Lin, Zeyu Zhou +6
cs.LGarXiv:2505.12672v12025
Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
A. Martina Neuman, Dominik Dold, Philipp Christian Petersen
cs.NEcs.LGmath.FAarXiv:2404.04549v32024
Towards Automatic Concept-based Explanations
Amirata Ghorbani, James Wexler, James Zou +1
stat.MLcs.CVcs.LGarXiv:1902.03129v32019
Revisiting minimum description length complexity in overparameterized models
Raaz Dwivedi, Chandan Singh, Bin Yu +1
cs.LGcs.ITmath.STarXiv:2006.10189v42020
DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations
Rishikesh Ranade, Mohammad Amin Nabian, Kaustubh Tangsali +4
cs.LGphysics.comp-pharXiv:2501.13350v12025
TripNet: Learning Large-scale High-fidelity 3D Car Aerodynamics with Triplane Networks
Qian Chen, Mohamed Elrefaie, Angela Dai +1
physics.flu-dyncs.LGarXiv:2503.17400v22025
A Tropical Approach to Neural Networks with Piecewise Linear Activations
Vasileios Charisopoulos, Petros Maragos
stat.MLcs.LGarXiv:1805.08749v22018
AgentInstruct: Toward Generative Teaching with Agentic Flows
Arindam Mitra, Luciano Del Corro, Guoqing Zheng +11
cs.AIcs.CLcs.LGarXiv:2407.03502v12024
BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information
Mehran Kazemi, Quan Yuan, Deepti Bhatia +4
cs.CLcs.AIcs.LGarXiv:2306.07934v12023
Soft Tokens, Hard Truths
Natasha Butt, Ariel Kwiatkowski, Ismail Labiad +2
cs.CLcs.AIcs.LGarXiv:2509.19170v22025
Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles
Kulin Shah, Nishanth Dikkala, Xin Wang +1
cs.LGcs.CLarXiv:2409.10502v12024
Monitoring Latent World States in Language Models with Propositional Probes
Jiahai Feng, Stuart Russell, Jacob Steinhardt
cs.CLcs.LGarXiv:2406.19501v22024
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Jifan Zhang, Lalit Jain, Yang Guo +9
cs.LGcs.AIcs.CLarXiv:2406.10522v22024
Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
Bilal Chughtai, Alan Cooney, Neel Nanda
cs.LGcs.CLarXiv:2402.07321v12024
Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
Shahar Katz, Yonatan Belinkov, Mor Geva +1
cs.CLcs.AIcs.LGarXiv:2402.12865v12024
Measuring Semantic Similarity by Latent Relational Analysis
Peter D. Turney
cs.LGcs.CLcs.IRarXiv:cs/0508053v12005
SyGuS-Comp 2016: Results and Analysis
Rajeev Alur, Dana Fisman, Rishabh Singh +1
cs.SEcs.LGcs.LOarXiv:1611.07627v12016
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Zhangchen Xu, Yuetai Li, Fengqing Jiang +4
cs.LGcs.AIcs.CLarXiv:2505.14625v22025

Machine Learning

Training Generative Adversarial Networks with Limited Data

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities

Deep Learning is Not So Mysterious or Different

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Dataset Distillation with Neural Characteristic Function: A Minmax Perspective

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

Maximum Density Divergence for Domain Adaptation

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Frontier Models are Capable of In-context Scheming

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Beyond IID: How General Are Tabular Foundation Models, Really?

Explaining Explanations: Axiomatic Feature Interactions for Deep Networks

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

DeepGCNs: Making GCNs Go as Deep as CNNs

InceptionTime: Finding AlexNet for Time Series Classification

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

Anomaly Detection in Video Sequence with Appearance-Motion Correspondence

Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking

Local Differential Privacy for Deep Learning

Optuna: A Next-generation Hyperparameter Optimization Framework

Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

Hierarchically Structured Meta-learning

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

InstructIR: High-Quality Image Restoration Following Human Instructions

A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning

Fair Transfer of Multiple Style Attributes in Text

Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration

Training Language Models with Language Feedback

PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis

Brain-Inspired Stochastic Joint Embedding Representation Learning

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

Siamese Masked Autoencoders

Visual Representation Learning with Stochastic Frame Prediction

Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities

TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability

Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders

Towards Automatic Concept-based Explanations

Revisiting minimum description length complexity in overparameterized models

DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations

TripNet: Learning Large-scale High-fidelity 3D Car Aerodynamics with Triplane Networks

A Tropical Approach to Neural Networks with Piecewise Linear Activations

AgentInstruct: Toward Generative Teaching with Agentic Flows

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Soft Tokens, Hard Truths

Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles

Monitoring Latent World States in Language Models with Propositional Probes

Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space

Measuring Semantic Similarity by Latent Relational Analysis

SyGuS-Comp 2016: Results and Analysis

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning