Zixian Liu

I am a first-year Ph.D. student at University of North Carolina at Chapel Hill, advised by Prof. Mingyu Ding. Previously, I did my undergraduate study at Yao Class, Tsinghua University. I was fortunate to work with Prof. Yunzhu Li at UIUC and Prof. Huazhe Xu at Tsinghua University.

Email  /  Scholar  /  Twitter/X  /  Github

RPG version of this page
profile photo

Research

I am interested in 'spatial intelligence' and 'physical intelligence'. Specifically, I am interested in the following questions:

1. How can models perceive, understand, and reason in 3D space?
2. How to equip models with physical common knowledge, and finally have them engage in the real world?

Preprints

Image OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding
Zixian Liu, Zhaoxi Chen, Liang Pan, Ziwei Liu
arXiv, 2026
Project Page / arXiv / Code

We introduce OnlineSI, a framework designed to understand 3D scenes in an online fashion and make detections from streaming video.

Publications

ViTaS: Visual Tactile Soft Fusion Contrastive Learning for Visuomotor Learning
Yufeng Tian*, Shuiqi Cheng*, Tianming Wei, Tianxing Zhou, Yuanhang Zhang, Zixian Liu, Qianwei Han, Zhecheng Yuan, Huazhe Xu
ICRA, 2026
Project Page / arXiv / Code

A simple yet effective framework that incorporates both visual and tactile information to guide the behavior of an agent.

Image KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulation
Zixian Liu*, Mingtong Zhang*, Yunzhu Li
ICRA, 2025
Best Paper Finalist (top 10%) @ CoRL 2024 Workshop
Project Page / arXiv / Code

KUDA is an open-vocabulary manipulation system that unifies the visual prompting of vision language models (VLMs) and dynamics modeling with keypoints.

Misc

In my spare time, I like playing soccer, watching anime, and playing video games. I am also an amateur game developer using Unity and RPG Maker. Most of the time I make games for my own entertainment.

This page also has a game version.

Maybe due to a little obsessive-compulsive personality disorder, coding awesome and structured projects gracefully can make me feel excellent.
In addition, I like to listen to Japanese music, including soundtracks of FF15, Xenoblade, Nier, etc, and music made by famous Japanese musicians, such as Joe Hisaishi and Hiroyuki Sawano.

Last updated: 2026-08-13