Tao Lin 林涛

I’m Tao Lin (Leo), a first-year master’s student at Beijing Jiaotong University, advised by Prof. Yuhui Wen. Previously, I completed my undergraduate studies at Kunming University of Science and Technology, advised by Prof. Qingwang Wang.

My research focuses on representations for robot learning and generative action modeling. I aim to connect vision and language models with real-world interactive systems. To this end, I plan to explore and deepen my understanding of long-horizon automation and self-supervised reinforcement learning.

I’ve also worked on AI and SaaS investment research at a buyout fund. More on my business reflections.

Email Google Scholar GitHub WeChat

Education

Beijing Jiaotong University

Computer Technology

2026 — PresentBeijing

Kunming University of Science and Technology

Artificial Intelligence

2022 — 2026Kunming

Selected Publications

Full list on Google Scholar →

Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning

Qiwei Liang^†, Boyang Cai^†, Minghao Lai^†, Sitong Zhuang^†, Tao Lin, Yan Qin, Yixuan Ye, Jiaming Liang, Renjing Xu

CVPR 2026IEEE/CVF Conference on Computer Vision and Pattern Recognition

Paper Project Code

Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?

Boyang Cai^†, Qiwei Liang^†, Jiawei Li^†, Shihang Weng^†, Zhaoxin Zhang^†, Tao Lin, Xiangyu Chen, Wenjie Zhang, Jiaqi Mao, Weisheng Xu, Bin Yang, Jiaming Liang, Junhao Cai, Renjing Xu

arXiv 2026Manuscript

Paper Project Code

FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors

Tao Lin, Qingwang Wang, Qiwei Liang, Minghua Tang, Yuxuan Sun

arXiv 2025Manuscript

Paper Code

Experience

Vita Dynamics

Algorithm Intern

Tinkering with robot dogs 🤖🔧

CHIMER AI & GAP Lab, CUHK, Shenzhen

Algorithm Intern

Feb 2025 — May 2025

Westlake Xinchen

Algorithm Intern

Jul 2023 — Aug 2023

Personal Vision

The first time I watched Iron Man, I was genuinely stunned by Jarvis. It felt like magic and honestly, it still does. So I figured, why not take a shot at making something like that actually happen in my lifetime. Long term, I want to build things that actually help people. Not in a grandiose changing the world way, but in a real, everyday sense. Making life a little easier, a little safer, a little more accessible. If research can lead to products that do that, then I am in. And if startups are the way to get there, then that is the road I will take.