Search papers, labs, and topics across Lattice.
University of Chinese Academy of Sciences
2
0
5
9
Achieving softmax-level expressiveness at a fraction of the cost, SANA-Video 2.0 is 120x faster than its closest competitor while generating high-quality video.
Scaling diffusion model alignment just got a whole lot cheaper: Sol-RL uses FP4 rollouts to accelerate training convergence by up to 4.64x without sacrificing performance.
