Search papers, labs, and topics across Lattice.
Institue of Foundation Models
2
0
6
Auxiliary draft models are no longer necessary for speculative decoding: distilling lightweight diffusion heads directly into standard LLMs yields lossless 3脳 generation speedups even at peak batch sizes.
Training on compound reasoning traces yields better generalization than isolated atomic modules, reshaping our understanding of how LLMs can learn to reason.
