Search papers, labs, and topics across Lattice.
3
2
6
11
A compact 4B model using DuoMem achieves a staggering 77.9% task success rate, rivaling a 72B teacher model while being over 3x faster in execution.
Minimizing variance of importance weights in diffusion models elegantly unifies existing alignment methods and opens doors to novel, non-KL optimization strategies.
On-device LLMs can now tackle complex tasks like generating translated summaries thanks to a new benchmark and calibration method tailored for compositional multi-tasking.
