profile1.png

Jianhao Yuan

I am a DPhil (PhD) student of University of Oxford, supervised by Prof. Daniele De Martini, Prof. Paul Newman, and Prof. Philip Torr. I also closely work with Prof. Lars Kunze and Dr. Matt Gadd. Prior to this, I completed my undergraduate studies in Engineering Science also at University of Oxford. Previously, I worked as research intern at Meta FAIR, Amazon, and Oxa.

My research focuses on building unified world models that ground perception, language, and action in the physical world. These are models that learn how scenes evolve, how they are described, and how they can be acted upon. Current directions include Vision‑Language(‑Action) Models, Video World Models, and World Action Models.

News

Jun 1, 2026 Excited to start as a Research Scientist Intern again at FAIR Meta!
Feb 22, 2026 WMReward has been accepted to CVPR 2026 as a Highlight!
Jan 28, 2026 LikePhys has been accepted to ICLR 2026!
Nov 1, 2025 Our solution WMReward won first place in the ICCV 2025 Physics-IQ Challenge!
Jun 16, 2025 Excited to start as a Research Scientist Intern at FAIR Meta!
Sep 2, 2024 Excited to start as a Applied Scientist Intern at Amazon!
Jun 17, 2024 Excited to start as a Research Engineer Intern at Oxa!
May 14, 2024 RAG-Driver Accepted to RSS 2024!
May 2, 2024 Not Just Pretty Pictures Accepted to ICML 2024!
Jan 17, 2024 RealFake Accepted to ICLR 2024!
Oct 1, 2023 Incoming PhD student University of Oxford
Aug 6, 2023 First Update on my personal website :sparkles: :smile:
Show more ▼

Selected Publications

  1. Inference-time Physics Alignment of Video Generative Models with Latent World Models preview
    Inference-time Physics Alignment of Video Generative Models with Latent World Models
    Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, and 7 more authors
    CVPR, 2026 Highlight
  2. LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference preview
    LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
    Jianhao Yuan, Fabio Pizzati, Francesco Pinto, and 5 more authors
    ICLR, 2026
  3. Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators preview
    Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
    Jianhao Yuan, Francesco Pinto, Adam Davies, and 1 more author
    ICML, 2024
  4. Real-Fake: Effective Training Data Synthesis Through Distribution Matching preview
    Real-Fake: Effective Training Data Synthesis Through Distribution Matching
    Jianhao Yuan, Jie Zhang, Shuyang Sun, and 2 more authors
    ICLR, 2024
  5. RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model preview
    RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model
    Jianhao Yuan, Shuyang Sun, Daniel Omeiza, and 4 more authors
    RSS, 2024

Experience

Meta FAIR

Research Scientist Intern
2026

Meta FAIR

Research Scientist Intern
2025

Amazon

Applied Scientist Intern
2024 – 2025

Oxa

Research Intern
2024

Academic Service

Conference Reviewer:ICLR, ECCV, RSS, CoRL, ICRA, IROS
Journal Reviewer:IJCV, TMLR, RA-L