Publications

Papers, workshop contributions, and technical reports. * denotes equal contribution.

ACM Multimedia 20262026

Tianxin Xie, Wentao Lei, Kai Jiang, …, Jiangshan He, …, Li Liu.

Evaluates whether generated sounds respond correctly to controlled changes in physical conditions.

ICML 2026 · AI4Math Workshop2026First author

Jiangshan He, Song Dai, Xiaolong Qiao, Jungang Li, Yibo Yan, Xuming Hu.

Uses matched controls to separate the effects of concept content from prompt format.

2025

MMM 20252025

Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo.

2025

Manuscript under revision · 修改中Manuscript2025

Zeyuan Zhang, Jiangshan He, Shiwei Feng, Gang Wu, Chunxia Xiao, Chao Liang.

2024

TRECVID 2024Technical report2024

Heng Liu, Jiangshan He, Zeyuan Zhang, Yuanyuan Xu, Chao Liang.

2024

MMM 20242024

Guihe Gu, Zhengqian Wu, Jiangshan He, Lin Song, Zhongyuan Wang, Chao Liang.

TRECVID 2023Technical report2023Co-first author

Jiangshan He*, Ruizhe Li*, Jiahao Guo*, Hong Zhang, Mingxi Li, Zhengqian Wu, Zhongyuan Wang, Bo Du, Chao Liang.

Combines vision-language models, generated image queries, and relevance feedback for video search.

MMM 20232023Co-first author

Weixi Song*, Jiangshan He*, Xinghan Li, Shiwei Feng, Chao Liang.

Refines multimodal video retrieval through user feedback on relevant and irrelevant clips.