Embodied AI · Robotics

Liuhaichen Yang杨刘海晨

4th year MEng student
Intern at Shanghai Artificial Intelligence Laboratory
Member of ERL

I study how intelligent systems perceive, reason and act in the physical world. My current interests include Embodied AI, Vision-Language-Action models, World Action Models and RL post-training.

Portrait of Liuhaichen Yang
UCL · Shanghai AI Lab
About me

I’m a fourth-year MEng Robotics & AI student at University College London (UCL), and I’m proud to be part of the first cohort of the programme. Before joining UCL, I studied Engineering at The University of Hong Kong (HKU) from 2022 to 2023, before leaving the programme to continue my studies at UCL. I joined Shanghai Artificial Intelligence Laboratory as an intern earlier this year and am currently working there.

I’m interested in Embodied AI, reinforcement learning, and robotics and AI more broadly, and I’m open to conversations and collaborations in these areas. Before UCL, I studied International A-Levels at Xi’an Tieyi International Curriculum Centre (西安铁一中国际部). Beyond research, I serve as Vice Captain of the UCL Men’s Basketball 2nd Team.

Research interests
Embodied AIReinforcement LearningRobotics
Present

MEng student

University College London

MEng Robotics & AI · fourth-year student
Activities

UCL Men's Basketball Team — 2nd Team Vice Captain (2026–27)

2022–2023

BEng programme

The University of Hong Kong

Studied BEng from 2022 to 2023; left the programme in 2023.
Programme

BEng

Period

2022–2023

Note

Left the programme in 2023.

2019–2022

International A-Level

Xi'an Tieyi International Curriculum Centre

Mathematics and science-focused international secondary education.
Courses

Maths · Further Maths · Physics · Chemistry

Activities

Basketball · Fencing

Academic focus

Mathematics, physics, chemistry and interdisciplinary problem solving.

Selected awards
  • American Regions Mathematics League — Power Round II, National Gold, Global Top 10
  • UKMT Senior Mathematical Challenge — Gold Award
  • Canadian Open Mathematics Challenge — National Gold Award
  • MATH KANGAROO CHINA, Year 11 Level 6 — Top Gold
  • UKChO, 53rd Chemistry Olympiad UK (Round I) — Gold Award
  • Australian Chemistry Olympiad — Distinction
  • BPhO Senior Physics Challenge — Gold Award (Global Ranking)
  • International Linguistics Olympiad China (Senior) — 2nd Prize

Experience

research & engineering
2026

Research Intern

Shanghai Artificial Intelligence Laboratory

AgiBot Genie G2 · mobile manipulation · VLA/WAM deployment
2025

Industry Project

Johnson & Johnson

COMP0216 Industry Project

02 / Selected publications

papers & work in progress
2026
Preprint · arXiv preprint

Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies

Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng, Zezhi Tang

VLAFlow MatchingRobotics
2026
Preprint · arXiv preprint

SignVLA: Real-Time Sign Language-Guided Robotic Manipulation via Attention LSTM and Vision-Language-Action Models

Ningwei Bai, Xinyu Tan, Harry Gardner, Zhengyang Zhong, Liuhaichen Yang, Luoyu Zhang, Zhekai Duan, Monkgogi Galeitsiwe, Zezhi Tang

VLASign LanguageLSTM
2026
Preprint · arXiv preprint

SignVLA: A Gloss-Free Vision-Language-Action Framework for Real-Time Sign Language-Guided Robotic Manipulation

Xinyu Tan, Ningwei Bai, Harry Gardener, Zhengyang Zhong, Luoyu Zhang, Liuhaichen Yang, Zhekai Duan, Monkgogi Galeitsiwe, Zezhi Tang

VLASign LanguageRobotic Manipulation

03 / Projects

open source & research tools
Open source↗

ERL Research Skills

An open-source research operating system for Robotics & AI. I develop and maintain it within ERL, connecting literature discovery, research planning, paper writing, scientific review and robotics engineering workflows. Open for everyone to use.

Robotics & AIResearch ToolsOpen Source

04 / Beyond

the rest of the practice
Beyond Academic Coming soon. ↗
Let’s talk about robotics and embodied AI ↗