Mario Tuci, Caner Korkmaz, Umut \c{S}im\c{s}ekli, Tolga Birdal: Generalization at the Edge of Stability https://arxiv.org/abs/2604.19740 https://arxiv.org/pdf/2604.19740 https://arxiv.org/html/2604.19740

Austin Coursey, Abel Diaz-Gonzalez, Marcos Quinones-Grueiro, Gautam Biswas: Safe Continual Reinforcement Learning in Non-stationary Environments https://arxiv.org/abs/2604.19737 https://arxiv.org/pdf/2604.19737 https://arxiv.org/html/2604.19737

Perry Dong, Alexander Swerdlow, Dorsa Sadigh, Chelsea Finn: FASTER: Value-Guided Sampling for Fast RL https://arxiv.org/abs/2604.19730 https://arxiv.org/pdf/2604.19730 https://arxiv.org/html/2604.19730

Abdulmoneam Ali, Ahmed Arafa: FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning https://arxiv.org/abs/2604.19729 https://arxiv.org/pdf/2604.19729 https://arxiv.org/html/2604.19729

Jiaming Zhang, Meng Ding, Shaopeng Fu, Jingfeng Zhang, Di Wang: Benign Overfitting in Adversarial Training for Vision Transformers https://arxiv.org/abs/2604.19724 https://arxiv.org/pdf/2604.19724 https://arxiv.org/html/2604.19724

Jake Lee: Adaptive MSD-Splitting: Enhancing C4.5 and Random Forests for Skewed Continuous Attributes https://arxiv.org/abs/2604.19722 https://arxiv.org/pdf/2604.19722 https://arxiv.org/html/2604.19722

Mihailo Stojnic: Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection https://arxiv.org/abs/2604.19712 https://arxiv.org/pdf/2604.19712 https://arxiv.org/html/2604.19712

Guillaume Gautier, R\'emi Bardenet, Michal Valko: On two ways to use determinantal point processes for Monte Carlo integration https://arxiv.org/abs/2604.19698 https://arxiv.org/pdf/2604.19698 https://arxiv.org/html/2604.19698

Jean-Bastien Grill, Omar Darwiche Domingues, Pierre M\'enard, R\'emi Munos, Michal Valko: Planning in entropy-regularized Markov decision processes and games https://arxiv.org/abs/2604.19695 https://arxiv.org/pdf/2604.19695 https://arxiv.org/html/2604.19695

Salvatore Greco, Jacek Karolczak, Roman S{\l}owi\'nski, Jerzy Stefanowski: PREF-XAI: Preference-Based Personalized Rule Explanations of Black-Box Machine Learning Models https://arxiv.org/abs/2604.19684 https://arxiv.org/pdf/2604.19684 https://arxiv.org/html/2604.19684

Pierre Perrault, Jennifer Healey, Zheng Wen, Michal Valko: Budgeted Online Influence Maximization https://arxiv.org/abs/2604.19672 https://arxiv.org/pdf/2604.19672 https://arxiv.org/html/2604.19672

Andrea Goertzen, Kaveh Alim, Navid Azizan: HardNet++: Nonlinear Constraint Enforcement in Neural Networks https://arxiv.org/abs/2604.19669 https://arxiv.org/pdf/2604.19669 https://arxiv.org/html/2604.19669

Xudong Jian, Charikleia Stoura, Simon Scandella, Eleni Chatzi: Disentangling Damage from Operational Variability: A Label-Free Self-Supervised Representation Learning Framework for Output-Onl... https://arxiv.org/abs/2604.19658 https://arxiv.org/pdf/2604.19658 https://arxiv.org/html/2604.19658

Inhyeok Choi, Hyuncheol Park: SAGE: Training-Free Semantic Evidence Composition for Edge-Cloud Inference under Hard Uplink Budgets https://arxiv.org/abs/2604.19623 https://arxiv.org/pdf/2604.19623 https://arxiv.org/html/2604.19623

Gabriele Farina, Juan Carlos Perdomo: An Efficient Black-Box Reduction from Online Learning to Multicalibration, and a New Route to $\Phi$-Regret Minimization https://arxiv.org/abs/2604.19592 https://arxiv.org/pdf/2604.19592 https://arxiv.org/html/2604.19592

Donghwan Lee: Lyapunov-Certified Direct Switching Theory for Q-Learning https://arxiv.org/abs/2604.19569 https://arxiv.org/pdf/2604.19569 https://arxiv.org/html/2604.19569

Carles Navarro, Philipp Tholke, Gianni de Fabritiis: Structure-guided molecular design with contrastive 3D protein-ligand learning https://arxiv.org/abs/2604.19562 https://arxiv.org/pdf/2604.19562 https://arxiv.org/html/2604.19562

Maxim Raginsky, Benjamin Recht: Separating Geometry from Probability in the Analysis of Generalization https://arxiv.org/abs/2604.19560 https://arxiv.org/pdf/2604.19560 https://arxiv.org/html/2604.19560

Akash Yadav, Taiwo A. Adebiyi, Ruda Zhang: Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention https://arxiv.org/abs/2604.19530 https://arxiv.org/pdf/2604.19530 https://arxiv.org/html/2604.19530

Gao, Gou, Xu, Shi, Yang, Li, Wong, Long: Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments https://arxiv.org/abs/2604.19528 https://arxiv.org/pdf/2604.19528 https://arxiv.org/html/2604.19528

Ziqin Chen, Zuang Wang, Yongqiang Wang: Accelerating Optimization and Machine Learning through Decentralization https://arxiv.org/abs/2604.19518 https://arxiv.org/pdf/2604.19518 https://arxiv.org/html/2604.19518

Saket Maganti: When Graph Structure Becomes a Liability: A Critical Re-Evaluation of Graph Neural Networks for Bitcoin Fraud Detection under Temporal Distribution Shift https://arxiv.org/abs/2604.19514 https://arxiv.org/pdf/2604.19514 https://arxiv.org/html/2604.19514

Pan, Liu, Lin, Zhu, Zhang, Dou, Gao, Han, Wang, Zheng, Huang, Gui, Feng: EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training https://arxiv.org/abs/2604.19485 https://arxiv.org/pdf/2604.19485 https://arxiv.org/html/2604.19485

Suvinava Basak: ZC-Swish: Stabilizing Deep BN-Free Networks for Edge and Micro-Batch Applications https://arxiv.org/abs/2604.19453 https://arxiv.org/pdf/2604.19453 https://arxiv.org/html/2604.19453

Yuhan Hu, Xiaolei Fang: Heterogeneity-Aware Personalized Federated Learning for Industrial Predictive Analytics https://arxiv.org/abs/2604.19451 https://arxiv.org/pdf/2604.19451 https://arxiv.org/html/2604.19451

Thomas Zollo, Jimmy Wang, Richard Zemel: Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation https://arxiv.org/abs/2604.19444 https://arxiv.org/pdf/2604.19444 https://arxiv.org/html/2604.19444

Gerard Pons, Carlos Escolano, Besim Bilalli, Anna Queralt: Revisiting Catastrophic Forgetting in Continual Knowledge Graph Embedding https://arxiv.org/abs/2604.19401 https://arxiv.org/pdf/2604.19401 https://arxiv.org/html/2604.19401

Yi Zhao, Di Yuan, Tao Deng, Suzhi Cao, Ying Dong: Optimal Routing for Federated Learning over Dynamic Satellite Networks: Tractable or Not? https://arxiv.org/abs/2604.19399 https://arxiv.org/pdf/2604.19399 https://arxiv.org/html/2604.19399

Vasiliki Papanikou, Evaggelia Pitoura: TACENR: Task-Agnostic Contrastive Explanations for Node Representations https://arxiv.org/abs/2604.19372 https://arxiv.org/pdf/2604.19372 https://arxiv.org/html/2604.19372

Rudolf Debelak: FairTree: Subgroup Fairness Auditing of Machine Learning Models with Bias-Variance Decomposition https://arxiv.org/abs/2604.19357 https://arxiv.org/pdf/2604.19357 https://arxiv.org/html/2604.19357