CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning Paper • 2606.24636 • Published 1 day ago • 2 • 1
Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO Paper • 2511.16669 • Published Nov 20, 2025 • 31 • 3
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning? Paper • 2505.21374 • Published May 27, 2025 • 29 • 2
AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction Paper • 2504.01014 • Published Apr 1, 2025 • 70 • 2