Lai Man Po
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1
Frequent co-authors
Research Timeline
2026
Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models
The paper introduces PRISM, a method for decoding preference signals from noisy latents using a lightweight Query-based Aggregation head and a frozen video diffusion backbone, achieving state-of-the-art preference accuracy and noise-robustness.
Highlighted terms show continued research focus across papers
Papers
cs.CVEmpiricalRecentJun 18, 2026
Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models
Haoxuan Wu, Lai Man Po, Mengyang Liu, Kun Li +2 more
The paper introduces PRISM, a method for decoding preference signals from noisy latents using a lightweight Query-based Aggregation head and a frozen video diffusion backbone, achieving state-of-the-a…
View →