Jiacheng Hua
Contact:
hjc21 AT mails.tsinghua.edu.cn
Greetings 👋!
I am a Ph.D. student from the College of AI at Tsinghua University, where I currently work with Prof. Miao Liu.
Previously, I received my B.Eng. degree from the Department of Computer Science and Technology, also at Tsinghua University.
My research interests are primarily in computer vision and multimodal modeling, with a recent focus on spatial reasoning and video generation.
During my undergraduate studies, I had the privilege of working with Prof. Shi-Min Hu, Dr. Tai-Jiang Mu, Prof. Sabine Süsstrunk, Prof. Qixing Huang, and Prof. Li Yi.
If you are interested in collaborating on projects, discussing ideas, or simply want to connect for any other reason, please feel free to drop me an email!
News
- [06/2026] I am honored to have been awarded the title of Merit Student by Tsinghua University.
- [04/2026] I will join Tencent Hunyuan as a research intern (Qingyun Program).
- [04/2026] TRACE is accepted to ACL 2026 main conference as an oral presentation. Hope to see you in San Diego!
- [06/2025] I graduated with honors from the Department of Computer Science and Technology at Tsinghua University with a B.Eng. degree.
- [04/2025] I will join the Shanghai AI Lab as a research intern in the Embodied AI Center. See you in Shanghai this summer!
- [11/2024] I am flattered to have been recognized as the "9# Star" Person of the Year by the Department.
- [11/2024] I am honored to have been awarded the Cai Xiong Scholarship, a Comprehensive Excellence Scholarship, by Tsinghua University.
- [09/2024] I am fortunate to have been admitted to the Ph.D. program at the College of AI at Tsinghua University.
Education
Publications / Preprints
* indicates equal contribution
|
ORAV: Benchmarking Audio-Video Generation from Multimodal Contexts
under review /
arXiv
|
|
EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning
under review /
arXiv
|
|
EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding
|
|
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
|
|
In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting
|
|
A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts
|
|
FragmentDiff: A Diffusion Model for Fractured Object Assembly
|
Industrial Experience
- Tencent Computer Systems • Apr. 2026 – Present
Research Intern, Foundation Model Team, Multimodal Model Department, TEG - Shanghai Artificial Intelligence Laboratory • Apr. 2025 – Apr. 2026
Research Intern, Embodied AI Center - Kuaishou Technology • July 2024 – Aug. 2024
Research Intern, Audio & Video Technology Department
Teaching Experience
- Multimodal Generative AI System Design • CAI, Tsinghua University
Teaching Assistant, Spring 2026 - Fundamentals of Programming • DCST, Tsinghua University
Teaching Assistant, Fall 2023, Fall 2024, Fall 2025 - Foundation of Object-Oriented Programming • DCST, Tsinghua University
Teaching Assistant, Spring 2025
Miscellaneous
I am a photophile, currently contributing to Tsinghua University's official account. With a broad interest in sports, I've won multiple medals and championships in track and field at the John Ma Cup. I am also fond of travelling and take pleasure in exploring the world. Additionally, I was a member of the Tsinghua Ballroom Dance Team.