Dr. Brandon Han

Senior AI Research Scientist

About Me

I am a Senior AI Research Scientist at Meta in London, specializing in generative AI for creative advertising. My research focuses on developing multi-modal AI systems that bridge vision and language for real-world applications, with cutting-edge technologies including diffusion models, large language models (LLMs), and vision-language models (VLMs).

I received my Ph.D. in Computer Science from University of Surrey in 2024, where I was advised by Prof. Tao Xiang and Prof. Yi-Zhe Song. I completed my Bachelor's degree in Information Engineering in 2020 at Zhejiang University.

You can download my full CV here.

Education

Doctor of Philosophy (Ph.D.) My research topic was mainly focusing on "Fine-Grained Vision-Language Learning".
University of Surrey
Guildford, UK (Jan. 2021 - Jul. 2024)
Bachelor of Engineering (BEng) Major in Information Engineering with Cumulative GPA: 3.92 / 4.00 (88.13 / 100).
Zhejiang University
Hangzhou, China (Sep. 2016 - Jun. 2020)
Academic Visits
Fudan University, Shanghai, China (Winter 2020)
Westlake University, Hangzhou, China (2019-2020)
University of Michigan, Ann Arbor, MI, USA (Summer 2019)
University of Notre Dame, South Bend, IN, USA (Summer 2018)

Employment

Senior AI Research Scientist Developing creative Ads with Generative AI (diffusion models + LLMs/VLMs) and managing AI Research Scientist interns.
Meta (Facebook UK Limited)
London, UK (Jul. 2025 - Present)
AI Research Scientist
Meta (Facebook UK Limited)
London, UK (Oct. 2023 - Jul. 2025)
Postgraduate Researcher
University of Surrey
Guildford, UK (Jan. 2021 - Oct. 2023)
Computer Vision Algorithm Intern
PixelShift.AI
Shanghai, China (May 2020 - Sep. 2020)

Research

I am broadly interested in the field of Deep Learning. My research goal is to build multi‑modal AI systems that can be used in real‑world applications. My expertise includes both discriminative tasks (e.g., uni‑modal/cross‑modal/compositional retrieval) and generative tasks (e.g., 2D/3D/video contents generation/editing).

Selected Publications

Learning Flow Field in Attention for Controllable Person Image Generation
In Computer Vision and Pattern Recognition Conference (CVPR) 2025

HeadSculpt: Crafting 3D Head Avatars with Text
In Neural Information Processing Systems (NeurIPS) 2023

FAME‑ViL: Multi‑Tasking Vision‑Language Model for Heterogeneous Fashion Tasks This paper was a highlight paper with 3 strong acceptance among the top 2.5% of submissions.
In Computer Vision and Pattern Recognition Conference (CVPR) 2023

FashionViL: Fashion‑Focused Vision‑and‑Language Representation Learning
In European Conference on Computer Vision (ECCV) 2022

Contact

Email: brandon.hxiao@gmail.com

Google Scholar | GitHub | LinkedIn | X

This website uses Tufte CSS and is fully generated by Claude 3.7 Sonnet. Last updated: