Machine Learning

CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation ICCV 2025 CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking NAACL 2025 Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge ACL 2025 Correcting Large Language Model Behavior via Influence Function AAAI 2025 Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization ICLR 2025 Correcting the Tamazight Portions of FLORES+ and OLDI Seed Datasets EMNLP 2025 Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models NAACL 2025 Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking ICLR 2025 Correlated Quantization for Faster Nonconvex Distributed Optimization UAI 2025 Correlation and Navigation in the Vocabulary Key Representation Space of Language Models ICLR 2025 Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data AAAI 2025 Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes EMNLP 2025 Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning CVPR 2025 Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild ICCV 2025 Correspondence-Free Fast and Robust Spherical Point Pattern Registration ICCV 2025 Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning EMNLP 2025 Corrupted Learning Dynamics in Games COLT 2025 Corruption Robust Offline Reinforcement Learning with Human Feedback AISTATS 2025 Corruption-Robust Variance-aware Algorithms for Generalized Linear Bandits under Heavy-tailed Rewards UAI 2025 COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation ICML 2025 CoSDA: Enhancing the Robustness of Inversion-based Generative Image Watermarking Framework AAAI 2025 COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework UAI 2025 COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation CVPR 2025 CoSMIC: Continual Self-supervised Learning for Multi-Domain Medical Imaging via Conditional Mutual Information Maximization ICCV 2025