Some personal news: I will be joining Oxford Comp Sci University of Oxford as @DeepMind chair in #AI and Fellow at Exeter College, Oxford I owe this honour to the amazing students and collaborators with whom I have had the privilege to work during my career

V nice application paper! It's not just about clocks - love to see how different data sources (and their pros/cons) interact sensibly for the final system - some human data, some sim data, some "offline tracker" data. Same for Autopilot, and I expect many other applied problems.

Have an idea for DALL·E? Reply with a caption. I'll generate 20 or so!

Temporal Alignment Networks for Long-term Video abs: arxiv.org/abs/2204.02968

Congratulations to charig yang who won best presentation and @jacksonmattt @shreshthmalik for best poster at the Joint CDT student conference with Bristol, Lincoln and Edinburgh CDTs Autonomous Intelligent Machines & Systems @Oxford University of Oxford

no lights, because attention is all you need @ transformers for vision workshop #cvpr2022 (jokes aside, great talks!)

This quote from Demis Hassabis is my favourite take on the "engineering vs science" debates in AI yet: AI is an engineering science: unlike in natural sciences, the phenomenon you're studying doesn't exist in nature, so you have to build it first, and then you can study.

SAM + Optical Flow = FlowSAM FlowSAM can discover and segment moving objects in a video and outperforms all previous approaches by a considerable margin in both single and multi-object benchmarks 🔥 robots.ox.ac.uk/~vgg/research/…

Many Congratulations to Jianyuan#CVPR2025 2025, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht and David Novotny for winning the Best Paper Award @CVPR for "VGGT: Visual Geometry Grounded Transformer" 🥇🎉 🙌🙌 #CVPR2025!!!!!!

Reading Recognition in the Wild: A Dataset for Understanding Human Behaviors During Reading from an Egocentric Sensor Suite This large multimodal dataset features video, eye gaze, and head pose sensor outputs, created to help solve the task of reading recognition from wearable

I'm in San Diego for #NeurIPS! I'll be around to chat anything Isomorphic Labs, at Google booth [Thursday 15:45], and will be presenting a paper from my past life with Project Aria @Meta on reading with smart glasses [Poster on Friday 16:30]. See you around! projectaria.com/datasets/readi…

The Iso team has cooked something incredible: our new technical report unveils the latest results from our drug design engine, the IsoDDE, progressing far beyond AlphaFold 3. This breaks new ground compared to AF and other similar methods by a significant degree across all key