Jiashen Hua (华佳燊)

Email: jiashenhzju@gmail.com / jiashen.hjs@alibaba-inc.com

I am currently a Senior Algorithm Expert at Alibaba Cloud’s Apsara and Tongyi Labs. I obtained my M.S. and B.S. degrees from Zhejiang University in 2019 and 2016. There, I was a member of the Machine Vision and Navigation Lab led by Prof. Zhiyu Xiang (项志宇), advised by Assoc. Prof. Xiaojin Gong (龚小谨).

My current research focuses on multimodal large language models, especially multimodal representation, multimodal reasoning, and agentic vision. Prior to this, I contributed to the deployment of the City Brain Project across China, leveraging AI to enhance urban governance. I have published several papers in top-tier venues such as ICLR, CVPR, IJCAI, ACM MM, TCSVT, and TMM.

🔥 I am always looking for self-motivated interns tailored to these topics. Feel free to reach out!

GitHub / Google Scholar

WeChat / Xiaohongshu / Twitter

News

[2026/02] One papers accepted by CVPR 2026.
[2026/01] One papers accepted by ICLR 2026 oral, top 1.18%.
[2025/08] One papers accepted by TMM 2025.
[2024/10] One papers accepted by ACM MM 2024.
[2022/03] One papers accepted by CVPR 2022.
[2021/12] One papers accepted by CVPR 2021 RVSU Workshop.
[2019/04] Joined Alibaba Damo Academy as a Research Scientist.

Selected Publications

(*Corresponding Author, †Project Lead)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs

Zhiyu Pan, Yizheng Wu, Jiashen Hua*†, Junyi Feng, Shaotian Yan, Bing Deng, Zhiguo Cao and Jieping Ye.
International Conference on Learning Representations (ICLR, oral presentation, 223/18949), 2026

Paper | Code

Illuminating Visual Identity in Universal Multimodal Embeddings

Jiawei Cao, Junyi Feng, Jiashen Hua*†, Ziheng Huang, Bing Deng, Kaijie Wu, Chaochen Gu, Jieping Ye.
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Paper | Code

Online convolutional re-parameterization

Mu Hu, Junyi Feng, Jiashen Hua†, Baisheng Lai, Jianqiang Huang, Xiaojin Gong and Xian-Sheng Hua.
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Paper (153 citations) | Code (184⭐)

A normalized convolutional neural network for guided sparse depth upsampling

Jiashen Hua and Xiaojing Gong.
International Joint Conference on Artificial Intelligence (IJCAI), 2018

Paper (58 citations)

Additional Publications

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance. Shengyang Sun, Jiashen Hua, et al. IEEE Transactions on Multimedia (TMM), 2025.

TDSD: Text-Driven Scene-Decoupled Weakly Supervised Video Anomaly Detection. Shengyang Sun, Jiashen Hua, et al. ACM International Conference on Multimedia (ACM MM), 2024.

Delving into Instance Modeling for Weakly Supervised Video Anomaly Detection. Shengyang Sun, Jiashen Hua, et al. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.

RobTrack: A Robust Tracker Baseline towards Real-World Robustness in Multi-Object Tracking and Segmentation. Dongxu Wei, Jiashen Hua, et al. Computer Vision and Pattern Recognition Workshop (CVPRW), 2021.

Honors & Awards

🏅 Future City Awards, "Novel Perception and Simulation Platform Driven by Urban Digital Twins". 2023

🏆 Winner, CVPR 2021 Robust Video Scene Understanding (RVSU) Challenge. 2021

🏆 Winner, CVPR 2019 The 1st Learning from Imperfect Data (LID) Challenge. 2019

Outstanding Graduate Student, Zhejiang University. 2017

This webpage template is stolen from Jon Barron