Search papers, labs, and topics across Lattice.
3
0
7
9
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.
DisagFusion unlocks up to 20x higher throughput for diffusion model serving by intelligently splitting the workload across heterogeneous GPUs and dynamically adapting to workload shifts.
Industrial code generation gets a reasoning boost: InCoder-32B-Thinking leverages error-driven feedback and a code world model to achieve top-tier performance on complex hardware-aware tasks.
