Search papers, labs, and topics across Lattice.
3
0
6
Z-Reward achieves nearly 90% human preference accuracy by transforming subjective visual preferences into nuanced score distributions, outperforming traditional reward models.
Achieve up to 2.5X faster video object removal by focusing DiT computations only on the essential tokens dictated by the mask.
Current image quality metrics struggle to articulate *why* one high-quality image is better than another, but this challenge shows MLLMs are closing the gap by providing expert-level explanations.
