Search papers, labs, and topics across Lattice.
Huazhong University of Science and Technology
3
0
9
Token-oriented inference optimizations can cut production costs and boost efficiency, transforming large model services from merely callable to fully operable.
Moebius achieves high-fidelity image inpainting with less than 2% of the parameters of leading models, setting a new benchmark for efficiency.
Autonomous vehicles can now navigate complex urban environments with significantly improved safety and smoothness thanks to a novel generator-discriminator framework that stabilizes diffusion-based motion planning.
