Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zejun MA

Zejun MA

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Vision×1AI×1Sound×1

Frequent co-authors

Yixuan Li1×
Guangzhi Sun1×
Yudong Yang1×
Wei Li1×
Chao Zhang1×

Research Timeline

2026
video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding

This paper presents video-SALMONN-R$^3$, an end-to-end video-LLM that enables re-watch through reinforcement learning, improving question answering performance with a two-stage paradigm.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.SD