HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 10 Dec 2025 00:32:17 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6938bf91-564f" expires: Sun, 28 Dec 2025 19:30:43 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 1F7F:318CF6:7DE80A:8D5698:6951830B accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 19:20:43 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210056-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766949643.485306,VS0,VE212 vary: Accept-Encoding x-fastly-request-id: 62d87898906ea349c0e5d33ef983a87d9805666e content-length: 4033

Runjia Li I am a DPhil Student (generously funded by Clarendon Scholarship) of University of Oxford, supervised by Prof. Andrea Vedaldi and Prof. Philip Torr. Prior to this, I completed my undergraduate studies in Engineering Science also at University of Oxford. I am fortunate to collaborate with Dr. Tomas Jakab. My research interest lies in consistent, physically-plausible, and interactive video generation. Email  /  Google Scholar  /  Twitter  /  Github Publications  (show selected / show all by date) EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing Runjia Li, Moayed Haji Ali, Ashkan Mirzaei, Chaoyang Wang, Arpit Sahni, Ivan Skorokhodov, Aliaksandr Siarohin, Tomas Jakab, Junlin Han, Sergey Tulyakov, Philip Torr, Willi Menapace Preprint, 2025 project page / arXiv / code VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory Runjia Li, Philip Torr, Andrea Vedaldi, Tomas Jakab ICCV, 2025 highlight project page / arXiv / code / Demo CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor Runjia Li*, Shuyang Sun*, Philip Torr, Xiuye Gu, Siyang Li CVPR, 2024 project page / arXiv / code EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing Runjia Li, Moayed Haji Ali, Ashkan Mirzaei, Chaoyang Wang, Arpit Sahni, Ivan Skorokhodov, Aliaksandr Siarohin, Tomas Jakab, Junlin Han, Sergey Tulyakov, Philip Torr, Willi Menapace Preprint, 2025 project page / arXiv / code VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory Runjia Li, Philip Torr, Andrea Vedaldi, Tomas Jakab ICCV, 2025 highlight project page / arXiv / code / Demo DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer Runjia Li, Junlin Han, Luke Melas-Kyriazi, Chunyi Sun, Zhaochong An, Zhongrui Gui, Shuyang Sun, Philip Torr Tomas Jakab 3DV, 2025 project page / arXiv / code CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor Runjia Li*, Shuyang Sun*, Philip Torr, Xiuye Gu, Siyang Li CVPR, 2024 project page / arXiv / code OxfordTVG-HIC: Can Machine Make Humorous Captions from Images? Runjia Li*, Shuyang Sun*, Mohamed Elhoseiny, Philip Torr ICCV, 2023 project page / arXiv / code Thank Jon Barron for sharing his website's source code.