Liang Li

Researcher, Alibaba Group

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization

#4713 · Zhenpeng Huang, Jiaqi Li, Zihan Jia, Xinhao Li, Desen Meng, Lingxue Song, Xi Chen, Liang Li, Limin Wang

A novel two‑stage Direct Preference Optimization framework that enables short‑context vision‑language models to robustly understand ultra‑long videos without any long‑video annotations.