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)

4,861 to 4,920 of 20,012

Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
Saffron Huang, Esin Durmus, Miles McCain +7
cs.CLcs.AIcs.CYarXiv:2504.15236v12025
Stability and Generalization of Graph Convolutional Neural Networks
Saurabh Verma, Zhi-Li Zhang
cs.LGcs.AIstat.MLarXiv:1905.01004v22019
The Dynamics of Continuous Mixture Collapse in Language Models
Ali Backour
cs.LGcs.CLarXiv:2609.02049v12026
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
cs.CLcs.AIcs.DCarXiv:2509.01322v22025
Estimating Mutual Information for Discrete-Continuous Mixtures
Weihao Gao, Sreeram Kannan, Sewoong Oh +1
cs.ITcs.LGarXiv:1709.06212v32017
EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
Yushun Dong, Ninghao Liu, Brian Jalaian +1
cs.LGarXiv:2108.05233v22021
Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts
Kirill Labzin, Stepan Kulibaba, Artem Dzhalilov +1
cs.LGcs.AIarXiv:2609.02404v12026
VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback
Jianxin Bi, Kevin Yuchen Ma, Ce Hao +2
cs.ROcs.LGarXiv:2507.17294v22025
Heterogeneous-Agent Reinforcement Learning
Yifan Zhong, Jakub Grudzien Kuba, Xidong Feng +3
cs.LGcs.AIcs.MAarXiv:2304.09870v22023
GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories
Arpita Joshi
cs.LGcs.AIarXiv:2609.02160v12026
Mutation-Guided LLM-based Test Generation at Meta
Christopher Foster, Abhishek Gulati, Mark Harman +5
cs.SEcs.AIcs.LGarXiv:2501.12862v12025
Weakly supervised causal representation learning
Johann Brehmer, Pim de Haan, Phillip Lippe +1
stat.MLcs.LGarXiv:2203.16437v32022
High probability generalization bounds for uniformly stable algorithms with nearly optimal rate
Vitaly Feldman, Jan Vondrak
cs.LGcs.DSstat.MLarXiv:1902.10710v22019
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning
Chenjia Bai, Lingxiao Wang, Zhuoran Yang +4
cs.LGarXiv:2202.11566v12022
Sinkhorn-Drifting Generative Models
Ping He, Om Khangaonkar, Hamed Pirsiavash +2
cs.LGarXiv:2603.12366v22026
Maximum Likelihood Reinforcement Learning
Fahim Tajwar, Guanning Zeng, Yueer Zhou +7
cs.LGarXiv:2602.02710v32026
Adversarial Robustness vs Model Compression, or Both?
Shaokai Ye, Kaidi Xu, Sijia Liu +6
cs.CVcs.CRcs.LGarXiv:1903.12561v52019
Forecasting directional movements of stock prices for intraday trading using LSTM and random forests
Pushpendu Ghosh, Ariel Neufeld, Jajati Keshari Sahoo
cs.LGq-fin.STstat.MLarXiv:2004.10178v22020
Polis: 3D Self-Supervision at City Scale
Alexander Rusnak, Sophia Kovalenko, Jingru Wang +3
cs.CVcs.AIcs.LGarXiv:2608.29426v12026
Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
Elham Kiyani, Khemraj Shukla, Jorge F. Urbán +2
cs.LGcs.AImath.OCarXiv:2501.16371v62025
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu +5
cs.CVcs.LGarXiv:2111.08644v32021
On Symmetric and Asymmetric LSHs for Inner Product Search
Behnam Neyshabur, Nathan Srebro
stat.MLcs.DScs.IRarXiv:1410.5518v32014
Circulant Binary Embedding
Felix X. Yu, Sanjiv Kumar, Yunchao Gong +1
stat.MLcs.LGarXiv:1405.3162v12014
A Finite Time Analysis of Two Time-Scale Actor Critic Methods
Yue Wu, Weitong Zhang, Pan Xu +1
cs.LGmath.OCstat.MLarXiv:2005.01350v32020
The Impact of Feature Scaling In Machine Learning: Effects on Regression and Classification Tasks
João Manoel Herrera Pinheiro, Suzana Vilas Boas de Oliveira, Thiago Henrique Segreto Silva +5
cs.LGstat.MLarXiv:2506.08274v52025
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
Nicklas Hansen, Hao Su, Xiaolong Wang
cs.LGcs.CVcs.ROarXiv:2107.00644v22021
Hierarchical Planning with Latent World Models
Wancong Zhang, Basile Terver, Artem Zholus +8
cs.LGarXiv:2604.03208v22026
nPINNs: nonlocal Physics-Informed Neural Networks for a parametrized nonlocal universal Laplacian operator. Algorithms and Applications
Guofei Pang, Marta D'Elia, Michael Parks +1
math.APcs.LGmath.OCarXiv:2004.04276v12020
DeepSeek vs. ChatGPT vs. Claude: A Comparative Study for Scientific Computing and Scientific Machine Learning Tasks
Qile Jiang, Zhiwei Gao, George Em Karniadakis
cs.LGcs.AIarXiv:2502.17764v22025
Spurious Forgetting in Continual Learning of Language Models
Junhao Zheng, Xidi Cai, Shengjie Qiu +1
cs.LGarXiv:2501.13453v12025
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
Kun Xu, Lingfei Wu, Zhiguo Wang +3
cs.AIcs.CLcs.LGarXiv:1804.00823v42018
REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
Qian Zhang, Yaoming Li, Zhewen Tan +9
cs.LGcs.AIarXiv:2609.00049v12026
Meta Flow Maps enable scalable reward alignment
Peter Potaptchik, Adhi Saravanan, Abbas Mammadov +3
stat.MLcs.LGarXiv:2601.14430v22026
A Functional Taxonomy of Music Generation Systems
Dorien Herremans, Ching-Hua Chuan, Elaine Chew
cs.SDcs.LGeess.ASarXiv:1812.04186v12018
DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
Wenqi Huang, Charley Lee, Leonard Tng +1
cs.SEcs.LGarXiv:2607.07946v12026
TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation
Reza Azad, Moein Heidari, Moein Shariatnia +4
eess.IVcs.CVcs.LGarXiv:2208.00713v12022
Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series
Yuxiao Hu, Qian Li, Dongxiao Zhang +2
cs.LGcs.CLstat.AParXiv:2501.03747v32025
GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning
Rishabh Tiwari, Krishnateja Killamsetty, Rishabh Iyer +1
cs.LGcs.AIarXiv:2111.11210v32021
BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities
Yunfan Jiang, Ruohan Zhang, Josiah Wong +7
cs.ROcs.AIcs.CVarXiv:2503.05652v22025
Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport
Lu Lu, Raphael Pestourie, Steven G. Johnson +1
physics.comp-phcs.LGarXiv:2204.06684v12022
Pomegranate: fast and flexible probabilistic modeling in python
Jacob Schreiber
cs.AIcs.LGstat.MLarXiv:1711.00137v22017
MolecularRNN: Generating realistic molecular graphs with optimized properties
Mariya Popova, Mykhailo Shvets, Junier Oliva +1
cs.LGcs.AIq-bio.MNarXiv:1905.13372v12019
Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach
Zhao Chen, Xiaodong Wang
cs.LGeess.SPmath.OCarXiv:1812.07394v12018
All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality
William Timkey, Marten van Schijndel
cs.CLcs.LGarXiv:2109.04404v12021
Do Sparse Autoencoders Capture Concept Manifolds?
Usha Bhalla, Thomas Fel, Can Rager +9
cs.LGcs.AIarXiv:2604.28119v12026
Convolutional-Recurrent Neural Networks for Speech Enhancement
Han Zhao, Shuayb Zarar, Ivan Tashev +1
cs.SDcs.CLcs.LGarXiv:1805.00579v12018
Deep Learning for Procedural Content Generation
Jialin Liu, Sam Snodgrass, Ahmed Khalifa +3
cs.AIcs.LGarXiv:2010.04548v12020
Not too little, not too much: a theoretical analysis of graph (over)smoothing
Nicolas Keriven
stat.MLcs.LGarXiv:2205.12156v22022
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference
Ismail Erbas, Xavier Intes, Vikas Pandey
cs.AIcs.LGphysics.opticsarXiv:2609.04490v12026
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators
Yinhong Liu, Han Zhou, Zhijiang Guo +4
cs.CLcs.AIcs.LGarXiv:2403.16950v52024
A Framework for Evaluating Approximation Methods for Gaussian Process Regression
Krzysztof Chalupka, Christopher K. I. Williams, Iain Murray
stat.MLcs.LGstat.COarXiv:1205.6326v22012
PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
Xutao Wang, Hanting Chen, Tianyu Guo +1
cs.LGarXiv:2607.13428v12026
Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide
Taejong Joo, Diego Klabjan
cs.AIcs.LGarXiv:2608.30051v12026
POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
Yuxiao Qu, Amrith Setlur, Virginia Smith +2
cs.LGcs.AIcs.CLarXiv:2601.18779v12026
MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
Lili Yu, Dániel Simig, Colin Flaherty +3
cs.LGarXiv:2305.07185v22023
Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
Ruiqian Nai, Boyuan Zheng, Junming Zhao +8
cs.ROcs.AIcs.LGarXiv:2602.06643v22026
Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks
Namyong Park, Andrey Kan, Xin Luna Dong +2
cs.LGcs.IRstat.MLarXiv:1905.08865v22019
POLYGLOT-NER: Massive Multilingual Named Entity Recognition
Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi +1
cs.CLcs.LGarXiv:1410.3791v12014
A Modern Take on the Bias-Variance Tradeoff in Neural Networks
Brady Neal, Sarthak Mittal, Aristide Baratin +4
cs.LGstat.MLarXiv:1810.08591v42018
Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting
Yuqi Li, Chuanguang Yang, Hansheng Zeng +5
cs.LGcs.AIcs.CVarXiv:2507.02939v22025

Machine Learning

Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions

Stability and Generalization of Graph Convolutional Neural Networks

The Dynamics of Continuous Mixture Collapse in Language Models

LongCat-Flash Technical Report

Estimating Mutual Information for Discrete-Continuous Mixtures

EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks

Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts

VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback

Heterogeneous-Agent Reinforcement Learning

GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories

Mutation-Guided LLM-based Test Generation at Meta

Weakly supervised causal representation learning

High probability generalization bounds for uniformly stable algorithms with nearly optimal rate

Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning

Sinkhorn-Drifting Generative Models

Maximum Likelihood Reinforcement Learning

Adversarial Robustness vs Model Compression, or Both?

Forecasting directional movements of stock prices for intraday trading using LSTM and random forests

Polis: 3D Self-Supervision at City Scale

Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks

UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection

On Symmetric and Asymmetric LSHs for Inner Product Search

Circulant Binary Embedding

A Finite Time Analysis of Two Time-Scale Actor Critic Methods

The Impact of Feature Scaling In Machine Learning: Effects on Regression and Classification Tasks

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation

Hierarchical Planning with Latent World Models

nPINNs: nonlocal Physics-Informed Neural Networks for a parametrized nonlocal universal Laplacian operator. Algorithms and Applications

DeepSeek vs. ChatGPT vs. Claude: A Comparative Study for Scientific Computing and Scientific Machine Learning Tasks

Spurious Forgetting in Continual Learning of Language Models

Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent

Meta Flow Maps enable scalable reward alignment

A Functional Taxonomy of Music Generation Systems

DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks

TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation

Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series

GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning

BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities

Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport

Pomegranate: fast and flexible probabilistic modeling in python

MolecularRNN: Generating realistic molecular graphs with optimized properties

Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach

All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality

Do Sparse Autoencoders Capture Concept Manifolds?

Convolutional-Recurrent Neural Networks for Speech Enhancement

Deep Learning for Procedural Content Generation

Not too little, not too much: a theoretical analysis of graph (over)smoothing

When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

A Framework for Evaluating Approximation Methods for Gaussian Process Regression

PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference

Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations

Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks

POLYGLOT-NER: Massive Multilingual Named Entity Recognition

A Modern Take on the Bias-Variance Tradeoff in Neural Networks

Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting