Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach Paper โข 2512.02834 โข Published 29 days ago โข 39
Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation Paper โข 2507.08441 โข Published Jul 11 โข 61
Physical AI Collection Collection of open, commercial-grade datasets for physical AI developers โข 23 items โข Updated 8 days ago โข 103
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models Paper โข 2502.06608 โข Published Feb 10 โข 39