Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation Paper • 2604.18168 • Published 25 days ago • 97
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published about 1 month ago • 119
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself Paper • 2604.14048 • Published about 1 month ago • 16
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation Paper • 2604.10030 • Published Apr 11 • 15