Machine Learning

Learning algorithms, neural networks, optimization and statistical learning theory.

Showing the latest 40 / 40 papers（All fields：Computation & Language Computer Vision Artificial Intelligence Sound Audio & Speech Processing）

Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching

Machine Learning · 2026-05 · arXiv:2605.30337

Alaa Khamis, Alaa Maalouf

Fairness-Aware Federated Learning with Trajectory Shapley Value

Machine Learning · 2026-05 · arXiv:2605.30336

Daniel Kuznetsov, Ziqi Wang

When, why, and how do diffusion posterior samplers fail? A finite-sample lens

Machine Learning · 2026-05 · arXiv:2605.30330

Benjamin A. Burns, Sara Fridovich-Keil

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?

Machine Learning · 2026-05 · arXiv:2605.30329

Sy-Tuyen Ho, Minghui Liu, Huy Nghiem, Furong Huang

Reasoning with Sampling: Cutting at Decision Points

Machine Learning · 2026-05 · arXiv:2605.30327

Felix Zhou, Anay Mehrotra, Quanquan C. Liu

In-Context Reward Adaptation for Robust Preference Modeling

Machine Learning · 2026-05 · arXiv:2605.30323

Zhenyu Sun, Zheng Xu, Ermin Wei

Gram: Assessing sabotage propensities via automated alignment auditing

Machine Learning · 2026-05 · arXiv:2605.30322

David Lindner, Victoria Krakovna, Sebastian Farquhar

Self-Trained Verification for Training- and Test-Time Self-Improvement

Machine Learning · 2026-05 · arXiv:2605.30290

Chen Henry Wu, Aditi Raghunathan

Statistical Embeddings for Similarity, Retrieval, and Interpretable Alignment of Numeric Tabular Datasets

Machine Learning · 2026-05 · arXiv:2605.30289

M. Ross Kunz, John Merickel, Keith Wilson

Neural Operator-Based Surrogate Model for CFD:Helical Coil Steam Generator in Small Modular Reactor

Machine Learning · 2026-05 · arXiv:2605.30277

Minseo Lee, Seongmin Oh, Chaehyeon Song, Bumjin Cho +4

Digitally enriching a screening population for pancreatic cancer using routine blood-based measures and clinical histories

Machine Learning · 2026-05 · arXiv:2605.30275

Chris Varghese, Leo Y. Li-Han, Richa Bisht, Ellen Larson +9

OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction

Machine Learning · 2026-05 · arXiv:2605.30247

Xin Wang, Linxin Xiao, Yang Yao, Wenwu Zhu

How's it going? Reinforcement learning in language models recruits a functional welfare axis

Machine Learning · 2026-05 · arXiv:2605.30232

Andy Q Han, David J. Chalmers, Pavel Izmailov

Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables

Machine Learning · 2026-05 · arXiv:2605.30229

Masaaki Imaizumi, Masanori Koyama, Noboru Isobe, Kohei Hayashi

ExDBSCAN: Explaining DBSCAN with Counterfactual Reasoning -- Additional Material

Machine Learning · 2026-05 · arXiv:2605.30225

Pernille Matthews, Lena Krieger, Tommaso Amico, Artur Zimek +2

TriSearch: Learning to Optimize Triangulations via Bistellar Flips

Machine Learning · 2026-05 · arXiv:2605.30220

Yiran Wang, Guido Montúfar

MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference

Machine Learning · 2026-05 · arXiv:2605.30218

Kexin Chu, Yang Zhou, Wei Zhang

Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs

Machine Learning · 2026-05 · arXiv:2605.30213

Benjamin Walker, Alexandre Bloch, Lingyi Yang, Sam Morley +1

HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime

Machine Learning · 2026-05 · arXiv:2605.30201

Mohamed Sana, Nicola Piovesan, Antonio De Domenico, Fadhel Ayed +1

Active Continual Learning with Metaplastic Binary Bayesian Neural Networks

Machine Learning · 2026-05 · arXiv:2605.30198

Kellian Cottart, Théo Ballet, Djohan Bonnet, Damien Querlioz

Mean-Field Diffuser: Scaling Offline MARL to Thousands of Agents

Machine Learning · 2026-05 · arXiv:2605.30190

Wenhao Li, Xiangfeng Wang, Bo Jin

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

Machine Learning · 2026-05 · arXiv:2605.30188

Eugène Berta, David Holzmüller, Francis Bach, Michael I. Jordan

Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts

Machine Learning · 2026-05 · arXiv:2605.30184

Fanny Lehmann, Firat Ozdemir, Yun Cheng, Torsten Hoefler +3

iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis

Machine Learning · 2026-05 · arXiv:2605.30179

Yang Song, Yixuan Zhang, Lingfa Meng, Tongyuan Hu +4

On Distributional Reinforcement Learning in Chaotic Dynamical Systems

Machine Learning · 2026-05 · arXiv:2605.30160

James Rudd-Jones, Mirco Musolesi, María Pérez-Ortiz

RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood

Machine Learning · 2026-05 · arXiv:2605.30154

Yifu Zheng

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies

Machine Learning · 2026-05 · arXiv:2605.30148

Kajetan Schweighofer, Conor F. Hayes, Roberto Dailey, Risto Miikkulainen +1

DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning

Machine Learning · 2026-05 · arXiv:2605.30135

Hyuck Lee, Taemin Park, Heeyoung Kim

Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation

Machine Learning · 2026-05 · arXiv:2605.30132

Adam Ousherovitch, Yixin Wang

Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression

Machine Learning · 2026-05 · arXiv:2605.30122

Gijs van Nieuwkoop, Siamak Mehrkanoon

Evolving Features vs Evolving Entire Trees with GP for Interpretable Survival Analysis

Machine Learning · 2026-05 · arXiv:2605.30119

Thalea Schlender, Peter A. N. Bosman, Tanja Alderliesten

Striding Across Reynolds Numbers: Representation Geometry in Neural PDE Generalisation

Machine Learning · 2026-05 · arXiv:2605.30112

Jianing Shi

Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability

Machine Learning · 2026-05 · arXiv:2605.30103

Santosh Premi Adhikari, Radu Timofte, Dmitry Ignatov

Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences

Machine Learning · 2026-05 · arXiv:2605.30100

Benjamin Walker, Terry Lyons

Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption

Machine Learning · 2026-05 · arXiv:2605.30089

Yankai Chen, Hanrong Zhang, Bowei He, Philip S. Yu +2

Q-ANCHOR: Federated Quantum Learning with ZNE-guided Correction

Machine Learning · 2026-05 · arXiv:2605.30075

Hoang M. Ngo, Quan Nguyen, Wanli Xing, My T. Thai

A Predictive Law for On-Policy Self-Distillation From World Feedback

Machine Learning · 2026-05 · arXiv:2605.30070

Tommy He, Jerome Sieber, Matteo Saponati

Ridge Regression from Poisson Resetting: A Renewal Perspective on Spectral Regularization

Machine Learning · 2026-05 · arXiv:2605.30059

Petar Jolakoski

Masked Diffusion Modeling for Anomaly Detection

Machine Learning · 2026-05 · arXiv:2605.30046

Lixing Zhang, Yuchen Liang, Liyan Xie

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

Machine Learning · 2026-05 · arXiv:2605.30038

Jaa-Yeon Lee, Yeobin Hong, Taesung Kwon, Jong Chul Ye