3 papers
cs.CV2026
LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
Zhenpeng Huang, Jiaqi Li, Zihan Jia +6
We present LongVPO, a novel two-stage Direct Preference Optimization framework that enables short-context vision-language models to robustly understand ultra-long videos without an…
cs.CV2025
Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
Zizheng Huang, Haoxing Chen, Jiaqi Li +4
Recent Vision Mamba (Vim) models exhibit nearly linear complexity in sequence length, making them highly attractive for processing visual data. However, the training methodologies…
cs.CV2025
Online Video Understanding: OVBench and VideoChat-Online
Zhenpeng Huang, Xinhao Li, Jiaqi Li +7
Multimodal Large Language Models (MLLMs) have significantly progressed in offline video understanding. However, applying these models to real-world scenarios, such as autonomous dr…