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)

29,581 to 29,640 of 32,709

Training seeds and model-selection stability in recommender-system evaluation
Juan Manuel Rodriguez, Oleg Lesota, Antonela Tommasel
cs.IRcs.LGarXiv:2609.02499v12026
Driving on Memory
Christian Löwens, Thorben Funke, Alexandru Paul Condurache
cs.CVcs.LGcs.ROarXiv:2608.31029v12026
POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment
Burak Tamer, Wolfram Höpken, Zehui Wang
cs.IRcs.LGarXiv:2608.16407v12026
The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence
Genpei Zhang
cs.CVcs.CLcs.LGarXiv:2609.00868v12026
Beat the Counter First: A Baseline for Temporal-Graph Anomaly Detectors
Omair Shafi Ahmed, Zohair Shafi
cs.LGarXiv:2608.15965v12026
Comparing Classical and Quantum Machine Learning for Regression in High Energy Physics Collision Data
Tariq Mahmood, Zain ul Abidin, Itzel Luviano Soto +1
cs.LGhep-exhep-pharXiv:2608.28084v12026
Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors
Iyad Assaad Nekka, Hamida Seba, Walid Khaled Hidouci +1
cs.LGcs.AIarXiv:2608.15559v12026
Is Monte Carlo Tree Search Just Every-Visit Monte Carlo Control?
Xianyi Wu
cs.LGarXiv:2608.27985v12026
DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference
Xiaoyang Lu, Belthangady Akash Vi Narayana Pai, Xian-He Sun
cs.ARcs.LGarXiv:2609.00407v12026
Dr. Claw: An AI Scientist Workspace for Vibe Research
Dingjie Song, Hanrong Zhang, Dawei Liu +10
cs.AIcs.CLcs.CVarXiv:2609.00365v12026
Distribution-free false-alarm calibration and chance-corrected spatial evaluation for industrial anomaly detection
Jie Deng
cs.CVcs.LGarXiv:2608.15090v12026
A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients
Haoguang Wang, Huy Hoang Le, Akhila Kandivalasa +3
cs.LGeess.SYarXiv:2608.15051v12026
Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit
Anqi Peter Li
cs.LGarXiv:2608.25315v12026
Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters
Bernardo Modenesi, Jody Lin, Kimberly Kaphingst +4
cs.CLcs.AIcs.LGarXiv:2608.14792v12026
How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
Vedant Palit, Florent Draye, Terry Jingchen Zhang +2
cs.CLcs.LGarXiv:2608.27510v12026
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
Amit Kumar, Elnur Adl Zarabi, Suranjana Trivedy +4
cs.LGcs.AIstat.MEarXiv:2608.23660v12026
The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure
Kaiqiao Han, Yizhou Sun
cs.CLcs.LGarXiv:2608.25005v12026
Predicting Multiple Clinical Outcomes Related to Functional Recovery and Social Isolation Among Older Adults After Lower-Limb Fracture or Hip Replacement
Santosh Ray, Pratik K. Mishra, Ali Abedi +3
cs.CVcs.LGarXiv:2608.23531v12026
The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding
Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
cs.CLcs.LGarXiv:2609.10296v12026
Performance Foundations of Parallel & Distributed Reasoning Language Models
Maciej Besta, Leonard Schmidt, Lara Nonino +7
cs.LGcs.AIcs.DCarXiv:2608.27046v12026
Attributing Preprocessing Invariance in Spectral Foundation Models
Dongjun Wei, Hongyi Wu, Yinuo Zou
cs.AIcs.CEcs.LGarXiv:2608.14227v12026
Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation
Nikolai Röhrich, Isabell Hans, Felix Krause +1
cs.CVcs.AIcs.LGarXiv:2608.14172v12026
BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learning
Haocheng Sun, Mulai Tan
cs.MAcs.LGarXiv:2608.25419v12026
FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment
Xitong Zeng, Zhaoge Bi, Yitian Yang +2
cs.LGcs.AIarXiv:2608.24551v12026
AdaptAV: Continuous Adaption of Vision Models for Autonomous Vehicles Using Cloud-based Oracle
Yuheng Zhu, Dhruva Ungrupulithaya, Boluo Ge +1
cs.CVcs.LGarXiv:2608.28673v12026
FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
Prabhjot Singh, Somnath Luitel, Manmeet Singh +1
cs.CLcs.AIcs.LGarXiv:2608.26129v12026
Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence
Mohammadali Khodabandehlou, Bhaskar Krishnamachari
cs.CLcs.LGarXiv:2608.29934v12026
A Human-in-the-Loop Autonomous Agent for Industry Time Series Forecasting
Xiaoyu Tao, Mingyue Cheng, Ze Guo +4
cs.LGarXiv:2608.30976v12026
Virgil: Navigating Explainability for Transformer-based Language Models
Martino Ciaperoni, Sezer Kutluk, Benedetta Muscato +2
cs.CLcs.LGarXiv:2608.25555v12026
MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions
Christina X. Ji
cs.LGarXiv:2608.30636v12026
Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates
Romain Claret, Michael O'Neill, Paul Cotofrei +1
cs.NEcs.AIcs.LGarXiv:2608.27612v12026
Supraglacial Lake Fate Is Knowable Long Before the Season Ends
Emam Hossain, Md Osman Gani
cs.LGarXiv:2608.30113v12026
More Experts, Worse Dynamics: Inverse Scaling and Spectral Bias in Mixture-of-Experts State-Space Models
Chandresh Pandey
cs.LGarXiv:2608.21840v12026
Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement
Alessia Milo, Georg Götz, Steinar Guðjónsson +3
eess.AScs.LGphysics.comp-pharXiv:2608.20971v12026
Reaching the Tail: Calibration Diversity Drives Conformal Coverage under Data Scarcity
Donald Aadithiyan
cs.LGarXiv:2608.21591v12026
ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation
Eric Inae, Tim Gunn, Chris Bond +1
cs.LGarXiv:2608.21504v12026
Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Performance, Scale, and Resource Utility
Marvellous O. Ajala, Zainab Ashimiyu-Abdusalam, Comfort Adesina
q-bio.QMcs.AIcs.LGarXiv:2608.20418v12026
Interpretable statistical feature engineering for early disruption prediction in the short pulse ADITYA tokamak
Jyoti Agarwal, Kavit Patel, Bhaskar Chaudhury +3
physics.plasm-phcs.LGphysics.data-anarXiv:2608.22515v12026
Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES
Hunter Heidenreich
cs.CLcs.LGq-bio.BMarXiv:2607.05691v12026
The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs
Eric Yeats, Brendan Kennedy, Loc Truong +5
cs.LGcs.CLarXiv:2608.27750v12026
MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning
Ziyang Luo, Yan Yang, Xiangru Jian +5
cs.AIcs.LGarXiv:2608.22167v12026
FedCoRe: Target-Adaptive Completion for Missing Modalities in Healthcare Federated Learning
Holger R. Roth, Ziyue Xu, Peter Cnudde
cs.CVcs.AIcs.LGarXiv:2608.18311v12026
A Point-of-Prescription Safety-Check System for Adverse Drug Reactions in Rural Bangladeshi Hospitals: A Feasibility Study
Shahir Abdullah
cs.HCcs.LGarXiv:2608.27239v12026
Multimodal Injury Risk and Performance Prediction in Tennis Using Weighted Ensemble Learning
Weihao Qu, Dongyang Wang, Ling Zheng +3
cs.LGarXiv:2608.21530v12026
Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization
Junhao Cao, Hongyi Xia, Jianian Wu +3
cs.LGcs.AIarXiv:2608.27507v12026
Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection
Saifullah Shoaib, Akash Borigi, Rupendra Lekkala +5
cs.CVcs.LGarXiv:2608.26648v12026
A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models
Artem Safronov
cs.LGarXiv:2608.26926v12026
Bidirectional representational alignment between biological and artificial neural networks
Samuel Kostousov, Abhinn Kaushik, Brokoslaw Laschowski
cs.LGcs.AIarXiv:2608.18244v12026
Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models
Xiaoxiao Lu, Yunlong Dong, Jiahao Shi +1
cs.LGarXiv:2608.27259v12026
Distributed Training using an Intelligent Network
Nihar Shah, Ben Blier
cs.LGcs.DCcs.NIarXiv:2608.26453v12026
Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning
Shuting Xie, Nathaniel Lesperance, Graham W. Taylor
cs.LGcs.AIarXiv:2608.22839v12026
hLLM: Single Pass Decoding for Generative Reranking
Emil Laftchiev, Prachi Agrawal, Moe Kayali +7
cs.LGcs.AIcs.IRarXiv:2609.01807v12026
Counsel: A Meta-Evaluation Dataset for Agentic Tasks
Sashank Pisupati, Henry Broomfield, Eujeong Choi +5
cs.AIcs.LGarXiv:2606.21627v12026
Causal Analysis for Time Series Foundation Models
Mathis Jander, Wouter van Heeswijk, Martijn Mes
cs.LGarXiv:2608.24303v12026
TreeWY: Speculative Verification for Gated DeltaNet Hybrids
Sneha Murthy Ghantasala
cs.AIcs.CLcs.DCarXiv:2608.20961v12026
MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter
Vignesh Nagarajan, Sriram Venkatapathy
cs.CVcs.AIcs.LGarXiv:2608.16709v12026
Reinforcement Learning as (Discrete) Potential Theory
Christopher Connolly
cs.LGcs.GTarXiv:2608.17181v12026
Pretreatment DCE-MRI Resolves Response Quality Within Pathologic Endpoints in Neoadjuvant Breast Cancer
Dattatreya Kantha, Murray H. Loew
eess.IVcs.CVcs.LGarXiv:2608.22097v12026
EXAONE Tabular 1.0 : Technical Report
Moonjung Eo, Min-Kook Suh, Hye-Seung Cho +4
cs.LGarXiv:2608.25774v12026
Accelerating LLM Inference via Vector Index Based Output Embeddings
Martin Loretz, Sepp Hochreiter
cs.CLcs.LGarXiv:2608.27460v12026

Machine Learning

Training seeds and model-selection stability in recommender-system evaluation

Driving on Memory

POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment

The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence

Beat the Counter First: A Baseline for Temporal-Graph Anomaly Detectors

Comparing Classical and Quantum Machine Learning for Regression in High Energy Physics Collision Data

Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors

Is Monte Carlo Tree Search Just Every-Visit Monte Carlo Control?

DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference

Dr. Claw: An AI Scientist Workspace for Vibe Research

Distribution-free false-alarm calibration and chance-corrected spatial evaluation for industrial anomaly detection

A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients

Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit

Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters

How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution

From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers

The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure

Predicting Multiple Clinical Outcomes Related to Functional Recovery and Social Isolation Among Older Adults After Lower-Limb Fracture or Hip Replacement

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

Performance Foundations of Parallel & Distributed Reasoning Language Models

Attributing Preprocessing Invariance in Spectral Foundation Models

Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation

BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learning

FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment

AdaptAV: Continuous Adaption of Vision Models for Autonomous Vehicles Using Cloud-based Oracle

FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes

Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence

A Human-in-the-Loop Autonomous Agent for Industry Time Series Forecasting

Virgil: Navigating Explainability for Transformer-based Language Models

MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions

Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates

Supraglacial Lake Fate Is Knowable Long Before the Season Ends

More Experts, Worse Dynamics: Inverse Scaling and Spectral Bias in Mixture-of-Experts State-Space Models

Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement

Reaching the Tail: Calibration Diversity Drives Conformal Coverage under Data Scarcity

ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation

Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Performance, Scale, and Resource Utility

Interpretable statistical feature engineering for early disruption prediction in the short pulse ADITYA tokamak

Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES

The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs

MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning

FedCoRe: Target-Adaptive Completion for Missing Modalities in Healthcare Federated Learning

A Point-of-Prescription Safety-Check System for Adverse Drug Reactions in Rural Bangladeshi Hospitals: A Feasibility Study

Multimodal Injury Risk and Performance Prediction in Tennis Using Weighted Ensemble Learning

Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization

Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection

A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models

Bidirectional representational alignment between biological and artificial neural networks

Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models

Distributed Training using an Intelligent Network

Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning

hLLM: Single Pass Decoding for Generative Reranking

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

Causal Analysis for Time Series Foundation Models

TreeWY: Speculative Verification for Gated DeltaNet Hybrids

MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter

Reinforcement Learning as (Discrete) Potential Theory

Pretreatment DCE-MRI Resolves Response Quality Within Pathologic Endpoints in Neoadjuvant Breast Cancer

EXAONE Tabular 1.0 : Technical Report

Accelerating LLM Inference via Vector Index Based Output Embeddings