Search papers, labs, and topics across Lattice.
3
0
8
Asynchronous RL for LLMs doesn't have to sacrifice convergence for speed: DORA achieves 2-4x faster training by cleverly managing multiple policy versions during rollout.
Stop retraining from scratch: WeiT lets you initialize models of *any* size with SOTA performance, adapting pre-trained knowledge to your specific compute budget.
Unleash creativity in text-to-image models with a single, reusable 64-token template, sidestepping costly iterative prompt engineering and reasoning.
