(Taoyong Cui 崔涛镛)

Taoyong Cui · 崔涛镛

Reliable AI for scientific discovery.

Molecular and physical systems · world models · scientific agents.

Ph.D. student at CUHK CSE, working with the AI4LS Laboratory and MMLab; visiting Ph.D. researcher at Stanford University.

Contact Google Scholar GitHub MMLab
Taoyong Cui's profile illustration
From atomic-scale systems to macroscopic physical reality.

About

Learning how scientific systems change.

I develop predictive models for systems spanning atoms, molecules, cells, and physical environments. My work connects reliable simulation with world models that can guide interventions and testable scientific hypotheses.

At CUHK, I work with the AI4LS Laboratory and MMLab, co-supervised by Prof. Pheng Ann Heng and Prof. Wanli Ouyang. I also collaborate with Prof. Le Cong at Stanford.

AI for Physics

Interatomic potentials with uncertainty estimation and out-of-distribution adaptation.

World Models

Predictive models of dynamics and interventions across biological and physical systems.

Scientific Agents

Exploring agents that plan and use tools to support research workflows.

Background Master's in Biomedical Engineering, Tsinghua University; previously at Microsoft Research Asia and Shanghai AI Laboratory.

Academic service Reviewer for Nature Communications, AISTATS, ICML, ICLR, NeurIPS, and AAAI.

Selected publications

Selected work.

arXiv · 2026

JEPA-Anything: Learning Predictive Models across Different Worlds

Taoyong Cui, Zhongyao Wang, Xinyue Xu, Weiyang Liu, Zhaochen Yu, Yuying Zhang, Qiang Gao, Mengyue Yang, Wanli Ouyang, Pheng Ann Heng, Yingcheng Wu, Zhenfei Yin, Ling Yang

A shared predictive framework for world models across vision, biology, clinical trajectories, control, molecular dynamics, physical fields, and weather.

Read paper Code

Nature Communications · 2026

Evidential deep learning for interatomic potentials

Han Xu†, Taoyong Cui†, Chenyu Tang†, Jinzhe Ma, Dongzhan Zhou, Yuqiang Li, Xiang Gao, Xingao Gong, Wanli Ouyang, Shufei Zhang, Mao Su

Efficient uncertainty quantification for interatomic potentials.

Read paper

Nature Communications · 2025

Online test-time adaptation for better generalization of interatomic potentials to out-of-distribution data

Taoyong Cui, Chenyu Tang, Dongzhan Zhou, Yuqiang Li, Xingao Gong, Wanli Ouyang, Mao Su, Shufei Zhang

Test-time adaptation for out-of-distribution atomic structures.

Read paper

Nature Machine Intelligence · 2024

Geometry-enhanced pretraining on interatomic potentials

Taoyong Cui, Chenyu Tang, Mao Su, Shufei Zhang, Yuqiang Li, Lei Bai, Yuhan Dong, Xingao Gong, Wanli Ouyang

Geometry-aware pretraining for interatomic potentials.

WAIC 2024 Outstanding Thesis Award · GBA AI for Science Ph.D. Forum Best Paper
Read paper

News

News.

Scroll for earlier updates ↓

  1. JEPA-Anything released. Featured by QbitAI (量子位) ↗.

  2. Nature Communications paper accepted.

  3. Scientific Data paper accepted.

  4. Current Opinion in Structural Biology paper accepted.

  5. Advanced Science paper accepted.

  6. Nature Communications paper accepted.

  7. VLDB paper accepted.

  8. Nature Machine Intelligence paper accepted.

Talks

Selected talks.

Global Artificial Intelligence Technology Conference

Guangdong–Hong Kong–Macao Greater Bay Area AI for Science Ph.D. Forum

World Artificial Intelligence Conference

China Academic Forum on Interdisciplinary Innovation for Graduate Students in Materials Science

Contact

Open to research conversations.

AI for Science collaborations are welcome.

cty21@tsinghua.org.cn