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 19,945

Real-Time Streamable Generative Speech Restoration with Flow Matching
Simon Welker, Bunlong Lay, Maris Hillemann +2
eess.SPcs.LGcs.SDarXiv:2512.19442v32025
An Analysis of Linear Time Series Forecasting Models
William Toner, Luke Darlow
cs.LGarXiv:2403.14587v22024
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
Zihan Guan, Mengxuan Hu, Ronghang Zhu +2
cs.LGcs.CLarXiv:2505.06843v22025
Beyond Outliers: A Study of Optimizers Under Quantization
Georgios Vlassis, Saleh Ashkboos, Alexandra Volkova +2
cs.LGarXiv:2509.23500v22025
TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
Hanshi Sun, Zhuoming Chen, Xinyu Yang +2
cs.CLcs.LGarXiv:2404.11912v32024
Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
Zachary Ankner, Rishab Parthasarathy, Aniruddha Nrusimha +3
cs.LGarXiv:2402.05109v22024
Cascade Speculative Drafting for Even Faster LLM Inference
Ziyi Chen, Xiaocong Yang, Jiacheng Lin +3
cs.LGcs.CLarXiv:2312.11462v52023
Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning
Yang Zou, Zhikun Zhang, Michael Backes +1
cs.CRcs.LGstat.MLarXiv:2009.04872v12020
Linear attention is (maybe) all you need (to understand transformer optimization)
Kwangjun Ahn, Xiang Cheng, Minhak Song +3
cs.LGcs.AImath.OCarXiv:2310.01082v22023
HABERTOR: An Efficient and Effective Deep Hatespeech Detector
Thanh Tran, Yifan Hu, Changwei Hu +4
cs.CLcs.AIcs.IRarXiv:2010.08865v12020
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Yongding Tao, Tian Wang, Yihong Dong +4
cs.CLcs.AIcs.LGarXiv:2510.09259v22025
LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
Yiming Wang, Da Yin, Yuedong Cui +8
cs.CLcs.AIcs.LGarXiv:2510.14969v12025
Gradient Boosting on Stochastic Data Streams
Hanzhang Hu, Wen Sun, Arun Venkatraman +2
cs.LGarXiv:1703.00377v12017
An Online Boosting Algorithm with Theoretical Justifications
Shang-Tse Chen, Hsuan-Tien Lin, Chi-Jen Lu
cs.LGstat.MLarXiv:1206.6422v12012
Agentic Knowledgeable Self-awareness
Shuofei Qiao, Zhisong Qiu, Baochang Ren +8
cs.CLcs.AIcs.CVarXiv:2504.03553v22025
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation
Jason Li, Ravi Gadde, Boris Ginsburg +1
cs.CLcs.LGcs.SDarXiv:1811.00707v12018
UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
Yuanshao Zhu, James Jianqiao Yu, Xiangyu Zhao +4
cs.ETcs.AIcs.LGarXiv:2411.03859v32024
AutoLike: Auditing Social Media Recommendations through User Interactions
Hieu Le, Salma Elmalaki, Zubair Shafiq +1
cs.LGarXiv:2502.08933v12025
Resource Management for Blockchain-enabled Federated Learning: A Deep Reinforcement Learning Approach
Nguyen Quang Hieu, Tran The Anh, Nguyen Cong Luong +3
cs.LGcs.DCcs.NIarXiv:2004.04104v22020
Intern-S1: A Scientific Multimodal Foundation Model
Lei Bai, Zhongrui Cai, Yuhang Cao +174
cs.LGcs.CLcs.CVarXiv:2508.15763v22025
Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches
Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini
cs.LGcs.CVcs.NEarXiv:1907.03799v32019
Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers
Krzysztof Choromanski, Valerii Likhosherstov, David Dohan +8
cs.LGcs.CLstat.MLarXiv:2006.03555v32020
TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
Yue Meng, Chuchu Fan
cs.ROcs.AIcs.FLarXiv:2505.00562v12025
GRAPE: Generalizing Robot Policy via Preference Alignment
Zijian Zhang, Kaiyuan Zheng, Zhaorun Chen +7
cs.ROcs.CVcs.LGarXiv:2411.19309v22024
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Dylan J. Foster, Adam Block, Dipendra Misra
cs.LGcs.AImath.STarXiv:2407.15007v22024
Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
Vincent Huang, Dami Choi, Daniel D. Johnson +2
cs.AIcs.CLcs.LGarXiv:2512.15712v12025
Building Better Activation Oracles
Jan Bauer, Celeste De Schamphelaere, Adam Karvonen +2
cs.LGcs.AIarXiv:2606.02609v22026
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Adam Karvonen, James Chua, Clément Dumas +8
cs.CLcs.AIcs.LGarXiv:2512.15674v22025
Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
Haiyan Zhao, Zirui He, Guanchu Wang +3
cs.CLcs.LGarXiv:2605.25903v22026
Generating Images Part by Part with Composite Generative Adversarial Networks
Hanock Kwak, Byoung-Tak Zhang
cs.AIcs.CVcs.LGarXiv:1607.05387v22016
Matching Normalizing Flows and Probability Paths on Manifolds
Heli Ben-Hamu, Samuel Cohen, Joey Bose +5
stat.MLcs.LGarXiv:2207.04711v12022
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer
cs.LGcs.AIcs.NEarXiv:2507.14172v22025
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur, Narutatsu Ri, Yinghui He +2
cs.AIcs.LGarXiv:2607.05184v12026
The Amazing Agent Race: Strong Tool Users, Weak Navigators
Zae Myung Kim, Dongseok Lee, Jaehyung Kim +2
cs.AIcs.CLcs.LGarXiv:2604.10261v22026
Structure-based Drug Design with Equivariant Diffusion Models
Arne Schneuing, Charles Harris, Yuanqi Du +10
q-bio.BMcs.LGarXiv:2210.13695v32022
Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Junbum Cha, Kyungjae Lee, Sungrae Park +1
cs.LGcs.CVarXiv:2203.10789v22022
MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
Yucheng Shi, Wenhao Yu, Zaitang Li +5
cs.LGcs.CLarXiv:2507.05720v12025
Contrastive Instruction Tuning
Tianyi Lorena Yan, Fei Wang, James Y. Huang +5
cs.CLcs.AIcs.LGarXiv:2402.11138v22024
A Fast Post-Training Pruning Framework for Transformers
Woosuk Kwon, Sehoon Kim, Michael W. Mahoney +3
cs.CLcs.LGarXiv:2204.09656v22022
Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
Xiang Chen, Ningyu Zhang, Lei Li +6
cs.CLcs.AIcs.CVarXiv:2205.02357v52022
From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun +4
cs.LGcs.AIarXiv:2206.03208v22022
The Role of Machine Learning in Cybersecurity
Giovanni Apruzzese, Pavel Laskov, Edgardo Montes de Oca +4
cs.CRcs.LGarXiv:2206.09707v12022
Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems
Jiajia Guo, Chao-Kai Wen, Shi Jin +1
eess.SPcs.ITcs.LGarXiv:2206.14383v12022
Can large language models reason about medical questions?
Valentin Liévin, Christoffer Egeberg Hother, Andreas Geert Motzfeldt +1
cs.CLcs.AIcs.LGarXiv:2207.08143v42022
Image sensing with multilayer, nonlinear optical neural networks
Tianyu Wang, Mandar M. Sohoni, Logan G. Wright +5
physics.opticscs.ETcs.LGarXiv:2207.14293v12022
General Intelligence Requires Reward-based Pretraining
Seungwook Han, Jyothish Pari, Samuel J. Gershman +1
cs.LGarXiv:2502.19402v32025
iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use
Yirong Zeng, Xiao Ding, Yuxian Wang +8
cs.CLcs.AIcs.LGarXiv:2501.09766v52025
Federated Learning on Non-IID Graphs via Structural Knowledge Sharing
Yue Tan, Yixin Liu, Guodong Long +3
cs.LGcs.AIcs.DCarXiv:2211.13009v12022
Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing
Shengchao Liu, Weili Nie, Chengpeng Wang +6
cs.LGcs.CLq-bio.QMarXiv:2212.10789v32022
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Song Lai, Haohan Zhao, Rong Feng +9
cs.LGcs.AIcs.CLarXiv:2507.05386v62025
Learning Performance-Improving Code Edits
Alexander Shypula, Aman Madaan, Yimeng Zeng +7
cs.SEcs.AIcs.LGarXiv:2302.07867v52023
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Renrui Zhang, Jiaming Han, Chris Liu +7
cs.CVcs.AIcs.CLarXiv:2303.16199v32023
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
Peng Gao, Jiaming Han, Renrui Zhang +9
cs.CVcs.AIcs.CLarXiv:2304.15010v12023
Enabling Large Language Models to Generate Text with Citations
Tianyu Gao, Howard Yen, Jiatong Yu +1
cs.CLcs.IRcs.LGarXiv:2305.14627v22023
Studying Large Language Model Generalization with Influence Functions
Roger Grosse, Juhan Bae, Cem Anil +14
cs.LGcs.CLstat.MLarXiv:2308.03296v12023
GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
Vicente Vivanco Cepeda, Gaurav Kumar Nayak, Mubarak Shah
cs.CVcs.LGarXiv:2309.16020v22023
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving
Yuhan Liu, Hanchen Li, Yihua Cheng +11
cs.NIcs.LGarXiv:2310.07240v62023
Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning
Yunlong Song, Angel Romero, Matthias Mueller +2
cs.ROcs.LGarXiv:2310.10943v22023
Linear Representations of Sentiment in Large Language Models
Curt Tigges, Oskar John Hollinsworth, Atticus Geiger +1
cs.LGcs.AIcs.CLarXiv:2310.15154v12023
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Xuan Li, Zhanke Zhou, Jianing Zhu +3
cs.LGcs.CRarXiv:2311.03191v52023

Machine Learning

Real-Time Streamable Generative Speech Restoration with Flow Matching

An Analysis of Linear Time Series Forecasting Models

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

Beyond Outliers: A Study of Optimizers Under Quantization

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Cascade Speculative Drafting for Even Faster LLM Inference

Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning

Linear attention is (maybe) all you need (to understand transformer optimization)

HABERTOR: An Efficient and Effective Deep Hatespeech Detector

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

Gradient Boosting on Stochastic Data Streams

An Online Boosting Algorithm with Theoretical Justifications

Agentic Knowledgeable Self-awareness

Training Neural Speech Recognition Systems with Synthetic Speech Augmentation

UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces

AutoLike: Auditing Social Media Recommendations through User Interactions

Resource Management for Blockchain-enabled Federated Learning: A Deep Reinforcement Learning Approach

Intern-S1: A Scientific Multimodal Foundation Model

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers

TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching

GRAPE: Generalizing Robot Policy via Preference Alignment

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants

Building Better Activation Oracles

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

Generating Images Part by Part with Composite Generative Adversarial Networks

Matching Normalizing Flows and Probability Paths on Manifolds

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

Rethinking On-Policy Self-Distillation for Thinking Models

The Amazing Agent Race: Strong Tool Users, Weak Navigators

Structure-based Drug Design with Equivariant Diffusion Models

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

Contrastive Instruction Tuning

A Fast Post-Training Pruning Framework for Transformers

Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation

The Role of Machine Learning in Cybersecurity

Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems

Can large language models reason about medical questions?

Image sensing with multilayer, nonlinear optical neural networks

General Intelligence Requires Reward-based Pretraining

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use

Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

Learning Performance-Improving Code Edits

LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

Enabling Large Language Models to Generate Text with Citations

Studying Large Language Model Generalization with Influence Functions

GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization

CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving

Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning

Linear Representations of Sentiment in Large Language Models

DeepInception: Hypnotize Large Language Model to Be Jailbreaker