World Editing: Intervening on Executable Worlds at Increasing Depth Paper • 2610.02331 • Published 10 days ago • 30
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining Paper • 2609.33419 • Published 14 days ago • 19
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding Paper • 2609.07941 • Published Sep 7 • 19
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining Paper • 2609.33419 • Published 14 days ago • 19
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining Paper • 2609.33419 • Published 14 days ago • 19
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF Image-Text-to-Text • 27B • Updated 1 day ago • 2.17M • 1.26k