A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement Paper • 2610.38568 • Published 16 days ago • 74
LociArt: A Unified Paradigm for Free-Style Local Video Stylization Paper • 2610.36456 • Published 17 days ago • 37
WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control Paper • 2610.33135 • Published 21 days ago • 43
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding Paper • 2511.13026 • Published Nov 17, 2025 • 26