I acknowledge that information asymmetry can significantly hinder research opportunities for junior students. If you’re interested in chatting about life, research, or potential collaborations, feel free to email me.
For undergrad and master's students at Oxford ONLY: If you are interested in an internship or 4YP at TVG working with me, please email me your current CV to discuss further. I usually take 1 or 2 interns per year and will provide some potential research ideas with hands-on guidance.
[11.2024] Two papers (3D-GPT and DreamBeast) were accepted to 3DV 2025. Congratulations to Chunyi and Runjia! 3D-GPT is pioneering work in large-scale 3D scene generation, and DreamBeast is a fascinating project generating fantastical 3D animals.
[07.2024] VFusion3D and Unicorns were accepted to ECCV 2024! VFusion3D is the first work exploring scalable 3D generative/reconstruction models as a step towards a 3D foundation. Check it out if you are interested in 3D generation.
[07.2023] Hyperbolic Audio-visual Zero-shot Learning was accepted to ICCV 2023!
[07.2023] Graduated from ANU with First-Class Honours.
[10.2022] Awarded as a top reviewer in NeurIPS 2022!
[07.2022] Blind Image Decomposition (BID) was accepted to ECCV 2022! A new low-level vision task that better adapts to complex real-world scenarios. Check our project page for more.
[05.2022] You Only Cut Once (YOCO) was accepted to ICML 2022! Check here for our work on how to perform data augmentation.
My research focuses on the entire data lifecycle—from creation to utilization and understanding—to build more powerful and efficient AI systems, especially those that can actually work in very large-scale. My work is organized around three main topics, which you can click on to expand:
(1) Generation and manipulation of image, video, and 3D content,
Selected projects: Image decomposition, LLM for 3D scene generation, High-quality 3D asset generation
(3) Understand how data influences model's learning, decision-making, and emergent properties in order to build AI systems that scale predictably.
Selected projects: Memorability of images
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), Transactions on Image Processing (TIP), Transactions on Geoscience and Remote Sensing (TGRS)