DPhil in Computer Vision, University of Oxford
January 2024 – Present
Supervisor: Prof. Philip Torr
Junlin Han
Email: junlinhcv@gmail.com · junlinhan@meta.com · junlin.han@eng.ox.ac.uk
Profile
Welcome to my website.
- I am a researcher at FAIR, where I work on unified multimodal pre-training with Dr. Mike Lewis. I am also a final-year DPhil student in the Torr Vision Group at the University of Oxford, advised by Prof. Philip Torr.
- Previously, I worked as a research scientist at Cybever, a startup focused on 3D AIGC. I received my BSc from the Australian National University, where I was fortunate to be supervised by Dr. Lars Petersson, Prof. Hongdong Li, and Prof. Ian Reid.
News
- [03.2026] Released a large-scale exploration of unified multimodal pre-training, with practical insights into the next stage of pre-training.
- [02.2026] Two papers were accepted to CVPR 2026: EgoEdit and AuralSAM.
- [01.2026] Two papers were accepted to ICLR 2026: Learning to See Before Seeing and Kaleido.
- [11.2025] Joined FAIR to work with Mike Lewis on unified MLLM pre-training.
- [09.2025] Hallucination at a Glance was accepted to NeurIPS 2025.
- [07.2025] 3D2EP was accepted to SIGGRAPH 2025.
- [05.2025] Flex3D was accepted to ICML 2025.
- [03.2025] A paper on point-cloud segmentation was accepted to CVPR 2025.
- [12.2024] Our previous work on low-level vision received the Best Paper Award in Remote Sensing.
- [12.2024] We organized the 2nd Workshop on Foundation Models in the Wild at ICLR 2025.
- [11.2024] Two papers, 3D-GPT and DreamBeast, were accepted to 3DV 2025.
- [07.2024] VFusion3D and Unicorns were accepted to ECCV 2024.
Research Interests
My research focuses on multimodal foundation models, including multimodal large language models and generative models, as well as the interactions between them.
I am particularly interested in multimodal approaches to general intelligence, especially how vision can contribute to its development through large-scale pre-training.
Multimodal foundation models
Selected projects: Visual priors in LLM pre-training, Llama 4
Generative models, especially 3D and video
Selected projects: Scaling up 3D generation, High-quality 3D asset generation, Scaling neural rendering
Integration and interaction between modalities
Selected projects: Unified pre-training, LLMs for 3D world modeling
Education
BSc in Information Technology (Honours), Australian National University
February 2019 – July 2023
Research Experience
PhD Student Researcher, Meta
October 2023 – Present
- FAIR (December 2025 – Present), hosted by Dr. Mike Lewis — unified pre-training
- GenAI Llama Vision (August 2024 – December 2025), hosted by Dr. Filippos Kokkinos — MLLM post-training and pre-training
- GenAI RepliGen (October 2023 – July 2024), hosted by Dr. Filippos Kokkinos — 3D and video generation
Lead Research Scientist, Cybever
May 2023 – September 2023
Topic: Generative models for 3D world modeling
Visiting Researcher, AIML, University of Adelaide
December 2021 – May 2023
Advisor: Prof. Ian Reid
Topics: Data-centric AI, memorability
Research Student, Data61-CSIRO & Australian National University
August 2020 – May 2023
Advisors: Dr. Lars Petersson and Prof. Hongdong Li
Topics: Generative models, self-supervised learning
Publications
Recent representative papers are highlighted.
Academic Services
- Workshop organization: Foundation Models in the Wild at ICML 2024 and ICLR 2025
- Conference reviewing: CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR, COLM, SIGGRAPH Asia
- Journal reviewing: TPAMI, IJCV, TIP, TGRS
Awards
- Meta PhD Scholarship, 2023
- Best Paper Award, 2022, Remote Sensing
- Chancellor's Letter of Commendation, 2022, Australian National University
- Top Reviewer, 2022, NeurIPS
- Second Best Presentation Award, 2021, AIM Conference
- Top-up Scholarship, 2021, Data61-CSIRO
- Undergraduate Vacation Scholarship, 2020, Data61-CSIRO
Misc
- I was born and raised in Chengdu, a city known for its food and pandas.
- I have studied and lived in China, Singapore, Australia, and the UK.
- Outside research, I enjoy nature travel, cooking, gaming (e.g., Teamfight Tactics and Hearthstone; previously ranked top 50 worldwide), and swimming.