Search papers, labs, and topics across Lattice.
University of California, Los Angeles (UCLA)
4
0
10
Shifting the focus from token likelihood to target distribution design reveals a more effective framework for supervised fine-tuning that consistently outperforms traditional methods.
One-Forcing achieves state-of-the-art one-step video generation while slashing training costs to a third of previous methods.
Forget training costly reward models for text-to-image alignment – AutoRubric-T2I learns interpretable rubrics that outperform them using less than 0.01% of the data.
Forget hand-crafted environments: ClawEnvKit lets you automatically generate diverse, verified environments for claw-like agents from natural language, slashing costs by 13,800x.
