VideoNSA: Native Sparse Attention Scales Video Understanding Paper β’ 2510.02295 β’ Published Oct 2, 2025 β’ 9
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation Paper β’ 2506.09991 β’ Published Jun 11, 2025 β’ 55
RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy Paper β’ 2503.24388 β’ Published Mar 31, 2025 β’ 29
MovieChat Collection The data of MovieChat-1K and the checkpoint of MovieChat β’ 6 items β’ Updated Nov 21, 2024 β’ 1
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis Paper β’ 2410.08261 β’ Published Oct 10, 2024 β’ 52
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding Paper β’ 2307.16449 β’ Published Jul 31, 2023 β’ 16
