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)

4,141 to 4,200 of 20,222

AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark
Sören Becker, Johanna Vielhaben, Marcel Ackermann +3
cs.SDcs.AIcs.LGarXiv:1807.03418v32018
Federated Unlearning with Knowledge Distillation
Chen Wu, Sencun Zhu, Prasenjit Mitra
cs.LGcs.CRarXiv:2201.09441v12022
From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy
Petro Shulzhenko, Gabriele Spadaro, Enzo Tartaglione
cs.LGarXiv:2609.04881v12026
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU
Di Chai, Leye Wang, Zeshen Su +2
cs.LGarXiv:2609.04852v12026
Solution-space heterogeneity shapes federated learning dynamics across partial differential equations
Ping Luo, Jiahuan Wang, Ziqing Wen +2
cs.LGcs.DCarXiv:2609.05012v12026
Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
Kazuki Yano, Shun Kiyono, Sosuke Kobayashi +2
cs.CLcs.LGarXiv:2603.16127v12026
Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks
Abdessamed Qchohi, Jessica Moysen Cortes, Matteo Zecchin
cs.LGcs.NIeess.SParXiv:2609.05073v12026
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Rui Yang, Xiaoman Pan, Feng Luo +4
cs.LGcs.AIcs.CLarXiv:2402.10207v62024
Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
Huanyu Li, Kun Lei, Sheng Zang +5
cs.ROcs.AIcs.LGarXiv:2601.07821v12026
Physics-Aware Random Walk Fingerprints for Scalable Power Grid Graph Classification
Adnan Anwar
cs.LGeess.SYarXiv:2609.04943v12026
Fast Gauss Sums via Flash Attention
Nicolaj Rux, Sebastian Neumayer
cs.LGmath.NAarXiv:2609.04910v12026
Adaptive Milestone Reward for GUI Agents
Congmin Zheng, Xiaoyun Mo, Xinbei Ma +10
cs.LGcs.AIcs.CLarXiv:2602.11524v12026
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
Shenggui Li, Chao Wang, Yikai Zhu +14
cs.LGcs.AIcs.CLarXiv:2603.18567v12026
ML-Decoder: Scalable and Versatile Classification Head
Tal Ridnik, Gilad Sharir, Avi Ben-Cohen +2
cs.CVcs.LGarXiv:2111.12933v22021
When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation
Susu Hu, Preetam Gattogi, Jens Lehmann +3
cs.LGarXiv:2609.04861v12026
Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting
Jean Kossaifi, Nikola Kovachki, Morteza Mardani +15
cs.LGcs.AIarXiv:2601.18111v12026
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov +2
cs.CVcs.LGarXiv:2203.10833v22022
PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning
Ruizhe Huang, Chengran Li, Xiaochuan Shi
cs.LGarXiv:2609.04832v12026
Semi-parametric Image Synthesis
Xiaojuan Qi, Qifeng Chen, Jiaya Jia +1
cs.CVcs.AIcs.GRarXiv:1804.10992v12018
Deep Partition Aggregation: Provable Defense against General Poisoning Attacks
Alexander Levine, Soheil Feizi
cs.LGstat.MLarXiv:2006.14768v22020
Locating and Steering Refusal Beyond Attention
Preethi Carmel Bosco, Gopalakrishnan Srinivasan
cs.LGarXiv:2609.04721v12026
Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression
Francis Bach
math.STcs.LGmath.OCarXiv:1303.6149v32013
Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications
Hailiang Zhao, Peng Chen, Xueyan Tang +2
cs.LGcs.DSarXiv:2609.04787v12026
A Second-order Bound with Excess Losses
Pierre Gaillard, Gilles Stoltz, Tim Van Erven
stat.MLcs.LGmath.STarXiv:1402.2044v12014
Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization
Nir Shlezinger, Yonina C. Eldar, Stephen P. Boyd
eess.SPcs.LGeess.SYarXiv:2205.02640v22022
Communication-Efficient Personalized Federated Learning via Layer-Wise Multi-Threshold Random Sketching
Xu Zhang, Xingyu Hou, Jiacheng Cheng +2
cs.LGarXiv:2609.04830v12026
Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
Wengong Jin, Jeremy Wohlwend, Regina Barzilay +1
q-bio.BMcs.LGarXiv:2110.04624v32021
Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates
Manuel Röder, Bibin Babu, Frank-Michael Schleif
cs.LGcs.CRarXiv:2609.04815v12026
Compositionality and Generalization in Emergent Languages
Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt +2
cs.CLcs.AIcs.LGarXiv:2004.09124v12020
How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study
Glib Kechyn
cs.LGarXiv:2609.04797v12026
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Muhammad Khalifa, Zohaib Khan, Omer Tafveez +2
cs.LGcs.AIcs.CLarXiv:2603.07084v22026
A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification
Han Zhang, Yan Wang, Guanfeng Liu +3
cs.LGarXiv:2609.04772v12026
Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning
Ming Xiang, Stratis Ioannidis, Edmund Yeh +2
cs.LGcs.DCmath.OCarXiv:2609.04763v12026
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye +1
cs.CVcs.LGarXiv:2403.12030v12024
ATOM3D: Tasks On Molecules in Three Dimensions
Raphael J. L. Townshend, Martin Vögele, Patricia Suriana +10
cs.LGphysics.bio-phphysics.comp-pharXiv:2012.04035v42020
Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem
Alexandra Carpentier, Andrea Locatelli
stat.MLcs.LGarXiv:1605.09004v12016
Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations
Litu Rout, Yujia Chen, Nataniel Ruiz +3
cs.LGcs.CVstat.MLarXiv:2410.10792v12024
A Fairness Audit of the Duckworth-Lewis-Stern Method: Format-Specific and Gender-Differential Bias, with an Interpretable Calibration Layer for Cricket Target Revision
Soumyadeep Roy
cs.LGarXiv:2609.04754v12026
When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift
Max Fomin
cs.LGarXiv:2602.14161v22026
SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
Hwaran Lee, Jinsik Lee, Tae-Yoon Kim
cs.CLcs.LGarXiv:1907.07421v12019
Open World Compositional Zero-Shot Learning
Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian +1
cs.CVcs.LGarXiv:2101.12609v32021
Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling
Frank Hu, Shriram Chennakesavalu, Zichen Wang +5
cs.LGarXiv:2609.04735v12026
WEECFP-SuRGE: Wide Embedded Extended Connectivity Fingerprint with Substructure Rotary Graph-distance Encoding
Robert Epps
cs.LGarXiv:2609.04672v12026
Limits of End-to-End Learning
Tobias Glasmachers
cs.LGstat.MLarXiv:1704.08305v12017
Interpretability for Turing Machines
Billy Snikkers, Rumi Salazar, Daniel Murfet +1
cs.LGcs.FLstat.MLarXiv:2609.04661v12026
Optimizer Memory Schedules for Outscaling the Overtraining Axis
Katie Everett, Shikai Qiu
cs.LGarXiv:2609.04577v12026
R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
Weijie Shi, Yanxi Chen, Zexi Li +5
cs.LGcs.AIarXiv:2601.03715v22026
SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery
Mansooreh Montazerin, Antonio Ortega, Ajitesh Srivastava
cs.LGarXiv:2609.04639v12026
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
cs.AIcs.CLcs.LGarXiv:2601.03905v22026
Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator
Sumaiya Islam
cs.LGarXiv:2609.04635v12026
Artificial Intelligence in Drug Discovery: Applications and Techniques
Jianyuan Deng, Zhibo Yang, Iwao Ojima +2
cs.LGcs.AIarXiv:2106.05386v42021
GNN-Guided Graph Coarsening and Adaptive QUBO Penalties for the Capacitated Vehicle Routing Problem with Time Windows on a Quantum Annealer
Youssef Kamel Rezk, Paweł Gora
cs.LGarXiv:2609.04593v12026
Representation Redundancy and Structural Complexity in Finite-Field Inversion
Zheng Zhang, Na Zhang
cs.LGmath.RAarXiv:2609.04583v12026
Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges
Edgar Galván, Peter Mooney
cs.NEcs.CVcs.LGarXiv:2006.05415v12020
Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis
Shengye Hu, Baiying Lei, Yong Wang +3
eess.IVcs.LGarXiv:2008.03483v12020
Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling
Zhixiang Liang, Beichen Huang, Zheng Wang +1
cs.LGarXiv:2601.09093v22026
Combining Optimal Control and Learning for Visual Navigation in Novel Environments
Somil Bansal, Varun Tolani, Saurabh Gupta +2
cs.ROcs.AIcs.CVarXiv:1903.02531v22019
Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
Yair Schiff, Omer Belhasin, Roy Uziel +6
cs.LGarXiv:2602.11590v32026
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Janghyeon Kim, Minsoo Kim, Kyuhong Shim +1
cs.LGcs.CLarXiv:2609.04971v12026
PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
Vignesh Kothapalli, Rishabh Ranjan, Valter Hudovernik +4
cs.DBcs.AIcs.LGarXiv:2602.04029v22026

Machine Learning

AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark

Federated Unlearning with Knowledge Distillation

From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy

KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU

Solution-space heterogeneity shapes federated learning dynamics across partial differential equations

Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning

Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation

Physics-Aware Random Walk Fingerprints for Scalable Power Grid Graph Classification

Fast Gauss Sums via Flash Attention

Adaptive Milestone Reward for GUI Agents

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

ML-Decoder: Scalable and Versatile Classification Head

When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation

Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning

Semi-parametric Image Synthesis

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks

Locating and Steering Refusal Beyond Attention

Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression

Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications

A Second-order Bound with Excess Losses

Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization

Communication-Efficient Personalized Federated Learning via Layer-Wise Multi-Threshold Random Sketching

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates

Compositionality and Generalization in Emergent Languages

How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR

A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification

Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning

ATOM3D: Tasks On Molecules in Three Dimensions

Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem

Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations

A Fairness Audit of the Duckworth-Lewis-Stern Method: Format-Specific and Gender-Differential Bias, with an Interpretable Calibration Layer for Cricket Target Revision

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

Open World Compositional Zero-Shot Learning

Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling

WEECFP-SuRGE: Wide Embedded Extended Connectivity Fingerprint with Substructure Rotary Graph-distance Encoding

Limits of End-to-End Learning

Interpretability for Turing Machines

Optimizer Memory Schedules for Outscaling the Overtraining Axis

R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification

SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery

Current Agents Fail to Leverage World Model as Tool for Foresight

Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator

Artificial Intelligence in Drug Discovery: Applications and Techniques

GNN-Guided Graph Coarsening and Adaptive QUBO Penalties for the Capacitated Vehicle Routing Problem with Time Windows on a Quantum Annealer

Representation Redundancy and Structural Complexity in Finite-Field Inversion

Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges

Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis

Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling

Combining Optimal Control and Learning for Visual Navigation in Novel Environments

Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models