robustness

Learning Fused State Representations for Control from Multi-View Observations ICML 2025 Lightweight-Mark: Rethinking Deep Learning-Based Watermarking ICML 2025 MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations ICML 2025 Non-parametric Conditional Independence Testing for Mixed Continuous-Categorical Variables: A Novel Method and Numerical Evaluation CLeaR 2025 Novelty Detection in Reinforcement Learning with World Models ICML 2025 Optimizing Adaptive Attacks against Watermarks for Language Models ICML 2025 Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting ICML 2025 Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness ICML 2025 Pixel-level Certified Explanations via Randomized Smoothing ICML 2025 Point-Level Topological Representation Learning on Point Clouds ICML 2025 PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data ICML 2025 Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption ICML 2025 Probably Approximately Global Robustness Certification ICML 2025 Quadratic Upper Bound for Boosting Robustness ICML 2025 RAGGED: Towards Informed Design of Scalable and Stable RAG Systems ICML 2025 Reinforcement Learning for Quantum Control under Physical Constraints ICML 2025 Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks ICML 2025 Robust and Conjugate Spatio-Temporal Gaussian Processes ICML 2025 Robust Autonomy Emerges from Self-Play ICML 2025 RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control ICML 2025 Robust Multi-bit Text Watermark with LLM-based Paraphrasers ICML 2025 Robust random graph matching in Gaussian models via vector approximate message passing COLT 2025 Robust Reward Alignment via Hypothesis Space Batch Cutting ICML 2025 Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability ICML 2025 Robust Sparsification via Sensitivity ICML 2025