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)

28,261 to 28,320 of 32,696

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
Grégoire Petit, Adrian Popescu, Hugo Schindler +2
cs.CVcs.AIcs.LGarXiv:2211.13131v22022
Repetition Improves Language Model Embeddings
Jacob Mitchell Springer, Suhas Kotha, Daniel Fried +2
cs.CLcs.LGarXiv:2402.15449v22024
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
X. Y. Han, Vardan Papyan, David L. Donoho
cs.LGcs.AImath.DGarXiv:2106.02073v42021
Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network
Sharath Adavanne, Archontis Politis, Tuomas Virtanen
cs.SDcs.LGeess.ASarXiv:1710.10059v22017
DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
Gabriele Corso, Hannes Stärk, Bowen Jing +2
q-bio.BMcs.LGphysics.bio-pharXiv:2210.01776v22022
FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models
Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas +1
cs.CVcs.LGarXiv:2412.08629v22024
Graph-based, Self-Supervised Program Repair from Diagnostic Feedback
Michihiro Yasunaga, Percy Liang
cs.SEcs.CLcs.LGarXiv:2005.10636v22020
In CEM, a World Model Is Also a Proposal Mechanism
Oliver Obst, Frieder Stolzenburg
cs.LGcs.ROarXiv:2610.00921v12026
Visual Diffusion Models are Geometric Solvers
Nir Goren, Shai Yehezkel, Omer Dahary +3
cs.CVcs.LGarXiv:2510.21697v22025
Gradient-based Adversarial Attacks against Text Transformers
Chuan Guo, Alexandre Sablayrolles, Hervé Jégou +1
cs.CLcs.AIcs.CRarXiv:2104.13733v12021
Efficient Continuous DEM Reconstruction under Limited Target-Resolution Supervision
Zekai Shi, Meng Zhang, Haokun Zhang +1
cs.CVcs.LGeess.IVarXiv:2609.29864v12026
Red-Teaming for Generative AI: Silver Bullet or Security Theater?
Michael Feffer, Anusha Sinha, Wesley Hanwen Deng +2
cs.CYcs.HCcs.LGarXiv:2401.15897v32024
MoFlow: An Invertible Flow Model for Generating Molecular Graphs
Chengxi Zang, Fei Wang
stat.MLcs.LGphysics.chem-pharXiv:2006.10137v12020
Federated Learning with Bayesian Differential Privacy
Aleksei Triastcyn, Boi Faltings
cs.LGcs.CRcs.DCarXiv:1911.10071v12019
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
Kewei Xu, Xiaoben Lu, Shuofei Qiao +4
cs.LGcs.AIcs.CLarXiv:2605.30434v12026
This Time is Different: An Observability Perspective on Time Series Foundation Models
Ben Cohen, Emaad Khwaja, Youssef Doubli +16
cs.LGcs.AIarXiv:2505.14766v22025
Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems
Tak Shing Au Yeung, Ka Chun Cheung, Hannah Potgieter +2
math.NAcs.LGarXiv:2609.30809v12026
Poisoning Attacks against Support Vector Machines
Battista Biggio, Blaine Nelson, Pavel Laskov
cs.LGcs.CRstat.MLarXiv:1206.6389v32012
A Robust Learning Approach to Domain Adaptive Object Detection
Mehran Khodabandeh, Arash Vahdat, Mani Ranjbar +1
cs.LGcs.CVstat.MLarXiv:1904.02361v32019
Symmetry-quotient Flatness and Generalization
Taiki Miyagawa
cs.LGstat.MLarXiv:2609.31634v12026
REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
Yassine El Ouahidi, Jonathan Lys, Philipp Thölke +5
cs.LGq-bio.NCarXiv:2510.21585v12025
On the Identifiability of the Post-Nonlinear Causal Model
Kun Zhang, Aapo Hyvarinen
stat.MLcs.LGarXiv:1205.2599v12012
Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data
Garrett Wilson, Janardhan Rao Doppa, Diane J. Cook
cs.LGstat.MLarXiv:2005.10996v12020
Toward Supervised Anomaly Detection
Nico Goernitz, Marius Micha Kloft, Konrad Rieck +1
cs.LGarXiv:1401.6424v12014
Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias
Stefan Stojanov, Anh Thai, James M. Rehg
cs.CVcs.LGarXiv:2101.07296v22021
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Shiyang Li, Xiaoyong Jin, Yao Xuan +4
cs.LGstat.MLarXiv:1907.00235v32019
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Zhijing Jin, Sydney Levine, Fernando Gonzalez +6
cs.CLcs.AIcs.CYarXiv:2210.01478v32022
RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States
Luca Herranz-Celotti, Vincent Guigue
cs.LGcs.AIarXiv:2609.12814v12026
pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
Tong Chen, Maximilian Holsman, Lin Zhao +1
cs.LGq-bio.BMarXiv:2610.01663v12026
Weakly supervised causal representation learning
Johann Brehmer, Pim de Haan, Phillip Lippe +1
stat.MLcs.LGarXiv:2203.16437v32022
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion
Satoshi Hayakawa
cs.LGcs.AImath.PRarXiv:2609.01043v12026
CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network
Cheng Zhao, Chenliang Li, Rong Xiao +2
cs.IRcs.LGarXiv:2005.10549v22020
The optimal information complexity of VC learning
Steve Hanneke, Juexiao Wang
stat.MLcs.ITcs.LGarXiv:2610.10600v12026
Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
Yuji Cao, Huan Zhao, Yuheng Cheng +7
cs.LGcs.AIcs.CLarXiv:2404.00282v32024
Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization
Shiyun Wa, Yifei Wang, Anna G. Green +2
cs.LGarXiv:2609.00189v12026
SatDL: Jointly Optimizing Data Redistribution and Training for Satellite-Based Distributed Learning
Hao Wu, Kin Whye Chew, Yizhan Han +2
cs.DCcs.LGarXiv:2608.24516v12026
Disaggregated Quantization: Specializing LLM Prefill and Decode
Andrei Panferov, Maximilian Kleinegger, Sweta Priyadarshi +2
cs.LGarXiv:2609.26333v12026
When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs
Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu +3
cs.ROcs.CVcs.LGarXiv:2610.10912v12026
Random Weight Factorization Improves the Training of Continuous Neural Representations
Sifan Wang, Hanwen Wang, Jacob H. Seidman +1
cs.LGarXiv:2210.01274v22022
Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
Kun Yi, Qi Zhang, Wei Fan +7
cs.LGcs.AIarXiv:2311.06184v12023
VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis
Mengzhe Geng
cs.SDcs.CLcs.LGarXiv:2609.03203v32026
Acoustic Scene Classification
Daniele Barchiesi, Dimitrios Giannoulis, Dan Stowell +1
cs.SDcs.LGarXiv:1411.3715v12014
Modulating early visual processing by language
Harm de Vries, Florian Strub, Jérémie Mary +3
cs.CVcs.CLcs.LGarXiv:1707.00683v32017
An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks
Keli Zhang, Marcus Kalander, Min Zhou +2
cs.LGcs.AIcs.SIarXiv:2105.03092v12021
A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks
Chenxi Wu, Min Zhu, Qinyang Tan +2
physics.comp-phcs.LGarXiv:2207.10289v12022
The Loss Floor of Denoising Score Matching: Fisher Geometry from Schrödinger Bridges
Avinash Raju, Kai Zhang
cs.LGcond-mat.stat-mecharXiv:2608.23916v12026
Base Models Can Reason By Taking a Cue From Training Data
Sophie L. Wang, Amil Dravid, Rulin Shao +3
cs.LGcs.AIcs.CLarXiv:2610.06851v12026
Learning Stochastic Recurrent Networks
Justin Bayer, Christian Osendorfer
stat.MLcs.LGarXiv:1411.7610v32014
SNLP: Layer-Parallel Inference via Structured Newton Corrections
Ligong Han, Kai Xu, Hao Wang +1
cs.LGarXiv:2605.17842v32026
Decoupling Exploration from Optimization in RLVR
Saif Punjwani, Micah Goldblum
cs.LGcs.AIcs.CLarXiv:2610.10536v12026
TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation
Feng Yu, Yanqiao Zhu, Qiang Liu +3
cs.IRcs.LGarXiv:2005.02844v12020
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Felix Friedrich, Manuel Brack, Lukas Struppek +4
cs.LGcs.AIcs.CVarXiv:2302.10893v32023
CONTRA: Conformal Prediction Region via Normalizing Flow Transformation
Zhenhan Fang, Aixin Tan, Jian Huang
stat.MLcs.LGarXiv:2605.08561v12026
Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
Luyu Gao, Yunyi Zhang, Jiawei Han +1
cs.LGcs.CLcs.IRarXiv:2101.06983v22021
The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow
Raphaël Berthier
cs.LGmath.OCstat.MLarXiv:2609.01034v12026
A Distributional Framework for Data Valuation
Amirata Ghorbani, Michael P. Kim, James Zou
cs.LGstat.MLarXiv:2002.12334v12020
Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks
Wenrui Zhang, Peng Li
cs.NEcs.LGarXiv:1908.06378v32019
Retrieval-Augmented Multimodal Language Modeling
Michihiro Yasunaga, Armen Aghajanyan, Weijia Shi +6
cs.CVcs.CLcs.LGarXiv:2211.12561v22022
Data Poisoning Attacks Against Federated Learning Systems
Vale Tolpegin, Stacey Truex, Mehmet Emre Gursoy +1
cs.LGcs.CRstat.MLarXiv:2007.08432v22020
Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein +4
cs.LGcond-mat.dis-nncs.ETarXiv:2104.13386v12021

Machine Learning

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning

Repetition Improves Language Model Embeddings

Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path

Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

In CEM, a World Model Is Also a Proposal Mechanism

Visual Diffusion Models are Geometric Solvers

Gradient-based Adversarial Attacks against Text Transformers

Efficient Continuous DEM Reconstruction under Limited Target-Resolution Supervision

Red-Teaming for Generative AI: Silver Bullet or Security Theater?

MoFlow: An Invertible Flow Model for Generating Molecular Graphs

Federated Learning with Bayesian Differential Privacy

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

This Time is Different: An Observability Perspective on Time Series Foundation Models

Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems

Poisoning Attacks against Support Vector Machines

A Robust Learning Approach to Domain Adaptive Object Detection

Symmetry-quotient Flatness and Generalization

REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects

On the Identifiability of the Post-Nonlinear Causal Model

Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data

Toward Supervised Anomaly Detection

Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment

RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States

pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows

Weakly supervised causal representation learning

From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion

CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network

The optimal information complexity of VC learning

Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods

Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization

SatDL: Jointly Optimizing Data Redistribution and Training for Satellite-Based Distributed Learning

Disaggregated Quantization: Specializing LLM Prefill and Decode

When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs

Random Weight Factorization Improves the Training of Continuous Neural Representations

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis

Acoustic Scene Classification

Modulating early visual processing by language

An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

The Loss Floor of Denoising Score Matching: Fisher Geometry from Schrödinger Bridges

Base Models Can Reason By Taking a Cue From Training Data

Learning Stochastic Recurrent Networks

SNLP: Layer-Parallel Inference via Structured Newton Corrections

Decoupling Exploration from Optimization in RLVR

TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation

Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness

CONTRA: Conformal Prediction Region via Normalizing Flow Transformation

Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup

The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow

A Distributional Framework for Data Valuation

Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks

Retrieval-Augmented Multimodal Language Modeling

Data Poisoning Attacks Against Federated Learning Systems

Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems