Yufan Wei

About me#

I am Yufan Wei.

I am a second year Ph.D. student at University of California, San Diego, advised by Prof. Biwei Huang and working close with Dr. Kun Zhou. My research focuses on causal intelligence and embodied ai, with a particular interest in representation level across policy model and world model.

I obtained my Bachelor’s degree in Computer Science at University of Minnesota while spend my first 2 years at Beijing University of Posts and Telecommunications.

Research Interests#

  • World Model / Representation Learning
  • Embodied AI / VLA
  • Causal AI

What’s New#

Research Experience#

I’ve been honored to work with:

Work Experience#

  • I’ve worked at Aether AI as an AI Research Intern in summer 2026
  • I’ve worked at Apple Inc. @Beijing as a Data Analyst Intern in 2023
Figure for CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model
CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model

Ziming Xu, Shuang Liang, Ruobing Han, Ziqiao Xi, Mingxing Rao, Kun Zhou, Zijun Zhang, Yuchen Yan, Yufan Wei, Junbo Huang, Yifei Shao, Fang Nan, Biwei Huang

A 16B embodied world model that makes physical reasoning explicit — predicting optical flow, then 3D pointmaps, then future video, with each step reused as context for the next. Top-1 on the TriWorldBench leaderboard.
391 words / 2 minutes
Figure for CD-LAM: Causally Debiased Latent Action Model for Embodied Action Conditioned World Models
CD-LAM: Causally Debiased Latent Action Model for Embodied Action Conditioned World Models

Yufan Wei, Kun Zhou, Lingjun Mao, Zijun Zhang, Ziming Xu, Ziqiao Xi, Shuang Liang, Ruobing Han, Yuchen Yan, Xinyue Wang, Fan Feng, Biwei Huang

A LAM-side causal debiasing method for continuous latent actions — removing action-irrelevant confounders before world-model training. −42%/−26% action-following error and >12× fewer training updates vs. DreamDojo.
295 words / 1 minutes
1