CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sat, 13 Dec 2025 12:41:45 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"693d5f09-368d" expires: Mon, 29 Dec 2025 09:40:41 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 6430:2685F2:883D09:992D9F:69524A41 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 09:30:41 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210066-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767000641.499798,VS0,VE230 vary: Accept-Encoding x-fastly-request-id: 5e4f81aa4b53be50df52e7e761e5d975a19f3228 content-length: 3408 Tianlin Pan

Tianlin Pan

I'm currently a third-year undergraduate at University of Chinese Academy of Sciences (UCAS). I'm actively exploring various topics in computer vision as a research intern at WeChat Vision, Tencent Inc. I also work as a research assistant at PRLab@NJU and previously MMLab@NTU, fortunately advised by Prof. Chenyang Si.

My research interests focus on visual generative models, especially in text-to-image/video generation, diffusion models, and model optimization.

I'm looking for PhD positions starting from Fall 2027. Please feel free to reach out to me if you have any opportunities or suggestions!

News

[2025.10] 🎉 I'm awarded Chinese National Scholarship.
[2025.10] ✈️️ I'm attending ICCV 2025 in Hawaii in person.
[2025.06] 🎉 Two papers are accepted by ICCV 2025.

Publications

* Denotes Equal Contribution. First-author and co-first-author papers are highlighted.

Boosting Diversity in Bitwise Autoregressive Image Generation

Ying Yang^*, Zhengyao Lv^*, Tianlin Pan, Haofan Wang, Binxing Yang, Hubery Yin, Chen Li, Chenyang Si,

ArXiv Preprint

Project arXiv Code

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

Zhengyao Lv*, Tianlin Pan*, Chenyang Si, Zhaoxi Chen, Wangmeng Zuo, Ziwei Liu, Kwan-Yee K. Wong

ICCV 2025

Project arXiv Code

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

Zhengyao Lv^*, Chenyang Si^*, Tianlin Pan, Zhaoxi Chen, Kwan-Yee K. Wong, Yu Qiao, Ziwei Liu

ICCV 2025

Project arXiv Code

Education

University of Chinese Academy of Sciences (UCAS)

2023 - 2027 (Expected)

B.E. in Artificial Intelligence

Beijing, China | GPA: 3.96/4.00, Rank: 2/85

Experience

WeChat Vision@Tencent Inc.

2025.08 - Present

Research Intern

Beijing, China | Working on video editing projects

PRLab@Nanjing University

2025.03 - Present

Research Assistant

Suzhou, China | Advised by Prof. Chenyang Si

MMLab@Nanyang Technological University

2024.11 - 2025.03

Research Assistant

Singapore (Remote) | Advised by Chenyang Si

Awards and Honors

2025 National Scholarship, Ministry of Education, China
2025 Undergraduate "Qiyan" Program Grant, Project Leader, Funded by Beijing Natural Science Foundation
2025 First-Level Scholarship (Top 5%), University of Chinese Academy of Sciences

Services

Teaching Assistant Introduction to Computer Sciences, 25 Spring, UCAS
Reviewer CVPR 2026

Original Source | Taken Source