Jiting Liu

刘纪霆

Robot Learning & Embodied AI Undergraduate in Mathematics

JL
GitHubGoogle Scholar iconGoogle ScholarEmail

About

I am an undergraduate in Mathematics at Sichuan Agricultural University, expecting to graduate in 2028. My research focuses on robot learning and embodied AI, with an emphasis on general-purpose robot policies, spatial representation learning, and cross-embodiment generalization.

My research experience includes work in Taku Komura’s group at The University of Hong Kong, where I focus on cross-embodiment action retargeting for dexterous robot manipulation. I have completed the School of Computing and Data Science’s Summer Research Internship Programme 2026. Previously, I worked in Bo Zhao’s group at Shanghai Jiao Tong University from June 2025 to April 2026, studying vision-language-action models.

My work includes Evo-Depth (co-first author; model design and experiments) and Evo-1 (CVPR 2026). More details are available in my CV.

Latest News

2026

Completed the HKU CDS Summer Research Internship Programme

Project: Data-Driven Cross-Embodiment Action Retargeting for Dexterous Robot Manipulation.

2026

Evo-1 · CVPR 2026

Selected Projects

Check out my latest work

Evo-Depth

A lightweight depth-enhanced vision-language-action model. Co-first author; model design and experiments.

Co-first author
Preprint
Paper

Evo-1

A lightweight vision-language-action model with preserved semantic alignment.

CVPR 2026
Paper

Cross-Embodiment Action Retargeting

Data-driven cross-embodiment action retargeting for dexterous robot manipulation. Responsible for converting standardized interaction representations into executable robot behavior while preserving task intent, object motion, and contact structure.

Research

Publications

View the full list of my publications on Google Scholar

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

CVPR 2026, pp. 13397–13406.

Authors: Tao Lin, Yilei Zhong, Yuxin Du, Jingjing Zhang, Jiting Liu, et al.

CVPR 2026
Paper

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

Preprint, arXiv:2605.14950. Co-first author; primarily responsible for model design and experiments.

Authors: Tao Lin, Yuxin Du, Jiting Liu, et al.

Preprint
Co-first author
Paper

Focusable Monocular Depth Estimation

Preprint, arXiv:2605.11756.

Authors: Yuxin Du, Tao Lin, Zile Zhong, Runting Li, Xiyao Chen, Jiting Liu, et al.

Preprint
Paper

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining

Preprint, arXiv:2606.27295.

Authors: Tao Lin, Yuxin Du, Yiran Mao, Zewei Ye, Yilei Zhong, Bing Cheng, Yiming Wang, Jiting Liu, et al.

Preprint
Paper

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding

Preprint, arXiv:2507.00416.

Authors: Tao Lin, Gen Li, Yilei Zhong, Yanwen Zou, Yuxin Du, Jiting Liu, et al.

Preprint
Paper

Skills

To completeThis section is retained; add the following material to replace this prompt.

  • Skill name, proficiency, and a verifiable project or outcome
  • Prioritize robotics, machine learning, programming, and tooling

Education

S

Sichuan Agricultural University

2024 - 2028 (expected)
Undergraduate in Mathematics · Major rank: 7/180

Internship & Work Experience

T

The University of Hong Kong · School of Computing and Data Science

2026 -
Research Assistant · Taku Komura’s group
Cross-embodiment action retargeting for dexterous robot manipulation. Responsible for converting standardized interaction representations into executable robot behavior. Completed the Summer Research Internship Programme 2026.
S

Shanghai Jiao Tong University

2025.06 - 2026.04
Research Assistant · Bo Zhao’s group
Embodied AI and vision-language-action models. Representative work: Evo-Depth (co-first author) and Evo-1 (CVPR 2026).

Awards & Honors

To completeThis section is retained; add the following material to replace this prompt.

  • Year, full award title, and awarding organization
  • Add a certificate, announcement, or project link when available

Academic Services

To completeThis section is retained; add the following material to replace this prompt.

  • Conference or journal reviewing: venue, year, and role
  • Teaching or course service: course, institution, dates, and responsibilities

Invited Talks

To completeThis section is retained; add the following material to replace this prompt.

  • Date, host, and talk title
  • Talk, slide, or video link, plus an optional logo
Contact

Get in Touch

Want to chat? Feel free to reach out via email →

  • • Ask questions
  • • Explore collaboration opportunities