Xiao Wang is 2nd-year PhD student from the Harbin Institute of Technology, Shenzhen. His research interests include Multi-modal Large Language Models, Video Understanding, and Video Generation. He has interned at JD, Huawei, and Kuaishou, where he closely integrated research with real-world applications, and has published many top-tier international conference papers and journal articles in his research area.

Education

• PhD. in Computer Science, Harbin Institute of Technology, Shenzhen (2023–Present)
• Master in Computer Science, Shandong University (2020–2023)
• Bachelor in Physics, Shandong University (2016–2020)

Selected Publications

• AdaReTaKe: Flexible Redundancy Reduction to Perceive Longer for Video-language Understanding. Xiao Wang, Qingyi Si, Jianlong Wu, Li Cao, Liqiang Nie. ACL’25. [paper], Reported by Synced

• ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding. Xiao Wang, Qingyi Si, Jianlong Wu, Shiyu Zhu, Li Cao, Liqiang Nie. Under review. [paper]

• HAIC: Improving Human Action Understanding with Better Captions. Xiao Wang, Jingyun Hua, Weihong Lin, Yuanxing Zhang, Fuzheng Zhang, Jianlong Wu, Di Zhang, Liqiang Nie. ACL’25. [paper]

• Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding. Xiao Wang, Jianlong Wu, Zijia Lin, Fuzheng Zhang, Di Zhang, Liqiang Nie. TPAMI’25. [paper]

• RTQ: Rethinking Video-language Understanding Based on Image-text Model. Xiao Wang, Yaoyu Li, Tian Gan, Zheng Zhang, Jingjing Lv, Liqiang Nie. MM’23 Oral. [paper]

• Micro-video Tagging via Jointly Modeling Social Influence and Tag Relation. Xiao Wang, Tian Gan, Yinwei Wei, Jianlong Wu, Dai Meng, Liqiang Nie. MM’22. [paper]