Search papers, labs, and topics across Lattice.
5
0
5
7
MeanFlowNFT achieves superior few-step generation performance, outperforming traditional multi-step RL-tuned methods while maintaining efficiency.
FlowBP redefines reward backpropagation by transforming the backward trajectory into a design object, leading to significant improvements in model alignment with human preferences.
Distilling video diffusion models just got a whole lot faster and better at capturing motion, thanks to a new method that directly optimizes score gradients.
Forget slow, complex training: you can now distill diffusion models to just 4 steps and still beat the state-of-the-art in preference alignment, aesthetics, and composition.
Real-time video generation gets a boost: Salt achieves sharper, more dynamic videos at extremely low inference budgets by explicitly enforcing consistency across denoising steps.
