Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 220
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 • 104
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations Paper • 2510.23607 • Published Oct 27, 2025 • 133