VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding Paper • 2412.02186 • Published 23 days ago • 22
BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation Paper • 2402.08712 • Published Feb 13 • 1
VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement Paper • 2411.15115 • Published Nov 22 • 9
Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion Paper • 2311.06318 • Published Nov 10, 2023 • 1