OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue Paper • 2609.21465 • Published 19 days ago • 151
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published 27 days ago • 707
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published Aug 15 • 452
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published Aug 4 • 54