2 papers
cs.CV2025
Unhackable Temporal Rewarding for Scalable Video MLLMs
En Yu, Kangheng Lin, Liang Zhao +8
In the pursuit of superior video-processing MLLMs, we have encountered a perplexing paradox: the "anti-scaling law", where more data and larger models lead to worse performance. Th…
cs.AI2025
PerPO: Perceptual Preference Optimization via Discriminative Rewarding
Zining Zhu, Liang Zhao, Kangheng Lin +7
This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained mul…