GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published Sep 30 • 34
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published Sep 28 • 89
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 224