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)

6,061 to 6,120 of 20,199

Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods
Zohaib Salahuddin, Henry C Woodruff, Avishek Chatterjee +1
eess.IVcs.AIcs.CVarXiv:2111.02398v12021
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
Yizheng Huang, Wenjun Zeng, Aditi Kumaresan +1
cs.LGcs.AIstat.MLarXiv:2604.23099v22026
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
Sijia Cui, Pengyu Cheng, Jiajun Song +6
cs.LGcs.AIcs.CLarXiv:2603.10101v12026
The spatial anatomy of urban wildfire vulnerability: a spatially validated GeoAI framework reveals the roles of building density and vegetation moisture in structure loss during the 2025 Palisades Fire
Parastoo Farajpoor, Mohammadreza Narimani
physics.geo-phcs.LGeess.IVarXiv:2608.22293v12026
Video models are zero-shot learners and reasoners
Thaddäus Wiedemer, Yuxuan Li, Paul Vicol +6
cs.LGcs.AIcs.CVarXiv:2509.20328v22025
World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali +87
cs.CVcs.AIcs.LGarXiv:2511.00062v22025
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Junxiang Xu, Ruisi Wang, Fanyi Pu +49
cs.CVcs.AIcs.LGarXiv:2608.26105v12026
Stitched Value Model for Diffusion Alignment
Hyojun Go, Hyungjin Chung, Prune Truong +8
cs.CVcs.AIcs.LGarXiv:2605.19804v12026
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Fan Jiang, Zhaoxu Sun, Mengchao Wang +38
cs.CVcs.AIcs.LGarXiv:2607.19191v12026
Pretraining Large Language Models with NVFP4
NVIDIA, Felix Abecassis, Anjulie Agrusa +87
cs.CLcs.AIcs.LGarXiv:2509.25149v22025
Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts
Daniel Garces, Sara Castro, Adrian Haimovich +2
cs.ROcs.LGcs.MAarXiv:2608.21554v12026
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
cs.LGcs.AIcs.CLarXiv:2604.12374v12026
Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings
Evelyn Ma, Rama Kumar Pasumarthi, Kishwar Shafin +25
cs.AIcs.LGarXiv:2608.26088v12026
Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networks
Jiuyun Sun, Yong Zhang
cs.LGarXiv:2608.24970v12026
A Very Big Video Reasoning Suite
Maijunxian Wang, Ruisi Wang, Juyi Lin +53
cs.CVcs.AIcs.LGarXiv:2602.20159v22026
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
Selim Kuzucu, Alessio Tonioni, Vasile Lup +3
cs.CVcs.AIcs.CLarXiv:2605.30126v12026
Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Niket Agarwal +76
cs.CVcs.AIcs.LGarXiv:2501.03575v32025
Building an Efficient Intrusion Detection System Based on Feature Selection and Ensemble Classifier
Yuyang Zhou, Guang Cheng, Shanqing Jiang +1
cs.CRcs.LGarXiv:1904.01352v42019
Parallel Decoding Distillation for Fast Image and Video Generation
Neta Shaul, Chao Liu, Arash Vahdat +1
cs.CVcs.LGarXiv:2607.26004v12026
Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation
Miguel Morona-Mínguez, Fernando Pérez-González, Alberto Pedrouzo-Ulloa
cs.CRcs.LGarXiv:2609.01945v12026
Learning Humanoid Standing-up Control across Diverse Postures
Tao Huang, Junli Ren, Huayi Wang +6
cs.ROcs.AIcs.LGarXiv:2502.08378v22025
Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO
Prakhar Gupta, Vaibhav Gupta
cs.CLcs.AIcs.LGarXiv:2609.00925v12026
Effectiveness of IoT and Deep Learning for Detection and Severity Assessment of Postelectrotermes militaris in Tea Plantations
D. K. C. Senevirathna, A. A. E. Nanayakkara, H. M. C. K. Kulathunga +7
cs.AIcs.LGcs.SDarXiv:2608.27480v12026
Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity
Ethan Manilow, Gordon Wichern, Prem Seetharaman +1
cs.SDcs.LGeess.ASarXiv:1909.08494v12019
wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
Xiaohang Tang, Rares Dolga, Sangwoong Yoon +1
cs.LGcs.AIstat.MLarXiv:2507.08838v22025
A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications
Siyuan Mu, Sen Lin
cs.LGcs.AIarXiv:2503.07137v42025
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Alex Fang, Gabriel Ilharco, Mitchell Wortsman +4
cs.CVcs.CLcs.LGarXiv:2205.01397v22022
Deep learning for cardiac image segmentation: A review
Chen Chen, Chen Qin, Huaqi Qiu +4
eess.IVcs.CVcs.LGarXiv:1911.03723v12019
Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space
Josephine Maria Thomas, Alessandro Muscoloni, Sara Ciucci +2
cond-mat.dis-nncs.AIcs.LGarXiv:1602.06522v12016
Provably Safe Sim-to-Real Transfer
Tingting Ni, Maryam Kamgarpour
cs.LGcs.AIarXiv:2609.01418v12026
Bandits in Prod: Hyperparameter Optimization at Inference Time
Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine
cs.LGcs.AIarXiv:2609.01335v22026
Superposed Latent Autoencoder
Quanling Zhao, Jiaying Yang, Tianqi Zhang +4
cs.LGcs.AIarXiv:2609.01158v12026
Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
Yixuan Even Xu, Yash Savani, Fei Fang +1
cs.LGcs.AIcs.CLarXiv:2504.13818v52025
Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula
Jean Barbier, Mohamad Dia, Nicolas Macris +3
cs.ITcond-mat.dis-nncs.LGarXiv:1606.04142v12016
Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks
Junkai Sun, Junbo Zhang, Qiaofei Li +3
cs.CVcs.LGarXiv:1903.07789v22019
Learning ReLUs via Gradient Descent
Mahdi Soltanolkotabi
cs.LGcs.ITmath.OCarXiv:1705.04591v22017
Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification
Pinlong Zhaoa, Linlin Houb, Ou Wua
cs.CLcs.LGarXiv:1906.04501v12019
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Samuel Miserendino, Michele Wang, Tejal Patwardhan +1
cs.LGcs.SEarXiv:2502.12115v42025
Neural Rough Differential Equations for Long Time Series
James Morrill, Cristopher Salvi, Patrick Kidger +2
cs.LGcs.AImath.DSarXiv:2009.08295v42020
CTAB-GAN+: Enhancing Tabular Data Synthesis
Zilong Zhao, Aditya Kunar, Robert Birke +1
cs.LGarXiv:2204.00401v12022
On the Adversarial Robustness of Vision Transformers
Rulin Shao, Zhouxing Shi, Jinfeng Yi +2
cs.CVcs.AIcs.LGarXiv:2103.15670v32021
Towards Efficient Model Compression via Learned Global Ranking
Ting-Wu Chin, Ruizhou Ding, Cha Zhang +1
cs.CVcs.LGarXiv:1904.12368v22019
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot +2
cs.CVcs.AIcs.LGarXiv:2504.02821v32025
PointVLA: Injecting the 3D World into Vision-Language-Action Models
Chengmeng Li, Junjie Wen, Yan Peng +3
cs.ROcs.CVcs.LGarXiv:2503.07511v12025
Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
Eddie Conti, Claudio Daka, Álvaro Parafita +3
cs.LGcs.AIarXiv:2609.00090v12026
On the Reliable Detection of Concept Drift from Streaming Unlabeled Data
Tegjyot Singh Sethi, Mehmed Kantardzic
stat.MLcs.AIcs.LGarXiv:1704.00023v12017
iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making
Preethi Lahoti, Krishna P. Gummadi, Gerhard Weikum
cs.LGcs.IRstat.MLarXiv:1806.01059v22018
Unsupervised Control Through Non-Parametric Discriminative Rewards
David Warde-Farley, Tom Van de Wiele, Tejas Kulkarni +3
cs.LGcs.AIstat.MLarXiv:1811.11359v12018
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian +6
cs.LGarXiv:2503.02819v22025
Contrastive learning, multi-view redundancy, and linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
cs.LGstat.MLarXiv:2008.10150v22020
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
Deniz Bayazit, Badr AlKhamissi, Antoine Bosselut
cs.CLcs.AIcs.LGarXiv:2609.00155v12026
mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
Marc Marone, Orion Weller, William Fleshman +3
cs.CLcs.IRcs.LGarXiv:2509.06888v12025
Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs
Lei Cai, Zhengzhang Chen, Chen Luo +4
cs.LGcs.SIstat.MLarXiv:2005.07427v22020
PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings
Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt +4
cs.LGcs.AIstat.MLarXiv:2007.14175v22020
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
Subhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan +2
cs.LGcs.AIarXiv:2502.16681v12025
Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting
Wei Fan, Pengyang Wang, Dongkun Wang +3
cs.LGcs.AIarXiv:2302.14829v32023
Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach
Dohyung Park, Anastasios Kyrillidis, Constantine Caramanis +1
stat.MLcs.ITcs.LGarXiv:1609.03240v22016
RL Token: Bootstrapping Online RL with Vision-Language-Action Models
Charles Xu, Jost Tobias Springenberg, Michael Equi +4
cs.LGcs.ROarXiv:2604.23073v22026
BACON: Band-limited Coordinate Networks for Multiscale Scene Representation
David B. Lindell, Dave Van Veen, Jeong Joon Park +1
cs.CVcs.GRcs.LGarXiv:2112.04645v22021
Sequence Parallelism: Long Sequence Training from System Perspective
Shenggui Li, Fuzhao Xue, Chaitanya Baranwal +2
cs.LGcs.DCarXiv:2105.13120v32021

Machine Learning

Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods

ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation

CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR

The spatial anatomy of urban wildfire vulnerability: a spatially validated GeoAI framework reveals the roles of building density and vegetation moisture in structure loss during the 2025 Palisades Fire

Video models are zero-shot learners and reasoners

World Simulation with Video Foundation Models for Physical AI

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Stitched Value Model for Diffusion Alignment

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Pretraining Large Language Models with NVFP4

Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings

Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networks

A Very Big Video Reasoning Suite

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding

Cosmos World Foundation Model Platform for Physical AI

Building an Efficient Intrusion Detection System Based on Feature Selection and Ensemble Classifier

Parallel Decoding Distillation for Fast Image and Video Generation

Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation

Learning Humanoid Standing-up Control across Diverse Postures

Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO

Effectiveness of IoT and Deep Learning for Detection and Severity Assessment of Postelectrotermes militaris in Tea Plantations

Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity

wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models

A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

Deep learning for cardiac image segmentation: A review

Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space

Provably Safe Sim-to-Real Transfer

Bandits in Prod: Hyperparameter Optimization at Inference Time

Superposed Latent Autoencoder

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula

Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks

Learning ReLUs via Gradient Descent

Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Neural Rough Differential Equations for Long Time Series

CTAB-GAN+: Enhancing Tabular Data Synthesis

On the Adversarial Robustness of Vision Transformers

Towards Efficient Model Compression via Learned Global Ranking

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

PointVLA: Injecting the 3D World into Vision-Language-Action Models

Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence

On the Reliable Detection of Concept Drift from Streaming Unlabeled Data

iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

Unsupervised Control Through Non-Parametric Discriminative Rewards

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts

Contrastive learning, multi-view redundancy, and linear models

Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning

Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs

PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting

Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach

RL Token: Bootstrapping Online RL with Vision-Language-Action Models

BACON: Band-limited Coordinate Networks for Multiscale Scene Representation

Sequence Parallelism: Long Sequence Training from System Perspective