Search papers, labs, and topics across Lattice.
China Telecom (TeleAI), Shanghai Jiao Tong University
2
0
5
Uncertainty-guided feedback can dramatically improve the reliability of reward models in visual diffusion, leading to superior optimization and quality outcomes.
Imagine turning any single-view video into a fully explorable, dynamic 4D scene – this paper gets us closer with a novel diffusion-based approach and a new large-scale dataset.
