Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published 7 days ago • 695
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 • 447
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI Paper • 2607.11562 • Published Jul 13 • 82
JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation Paper • 2606.03168 • Published Jun 2 • 47
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation Paper • 2505.20292 • Published May 26, 2025 • 53