🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Text-to-image diffusion models seem to have a good idea of geometry. Can we extract that geometry? Or maybe we can nudge these models to create large 3D consistent environments? Here's a blog summarizing some ideas in this space :) akosiorek.github.io/geometry_in_im…

Very happy to announce that our latest paper on Neural data compression with INRs, Meta Learning & Sparse Subnetwork selection has been accepted to #ICML2023 (Scores 7, 7, 7). 1/N Paper: arxiv.org/abs/2301.09479

Drop by our #ICLR2023 workshop tmrw (Thurs) on "Neural Fields Across Fields: Methods and Applications of INRs"! Schedule: sites.google.com/view/neural-fi… Accepted Papers: sites.google.com/view/neural-fi… In-Person: Room MH4 (room used for poster sessions) Virtual: iclr.cc/virtual/2023/w…

Introducing Manifold Diffusion Fields (MDF), our new work on learning generative models over fields defined on curved geometries. This is joint work with our intern Ahmed Elhag (who hasn’t even started his PhD yet!) and @jsusskin at Apple MLR arxiv.org/abs/2305.15586 🧵

Please consider applying to our team for a research engineer role, especially if you have managing experienve and research experience in: neural compression, diffusion, optimization, meta-learning, causality and fairness.

We're hiring a research scientist to join our Quantum Chemistry and Materials team ⚛️🚨 The team is working on using machine learning to better our understanding of the universe, down at the level of quantum physics. See: deepmind.com/blog/simulatin… Share: boards.greenhouse.io/deepmind/jobs/…

At the end of the summer, I gave an invited talk at the M2L school in Thessaloniki about training neural networks. It's a bit of a jumble of ideas, suggestions and best practices I've amassed over the years, interspersed with concrete examples. youtube.com/watch?v=wO4quY…

Today in nature we present FunSearch: an LLM-powered system that has found new discoveries in an established mathematical problem. FunSearch is versatile too: it can be applied to impactful practical problems. Blogpost: deepmind.google/discover/blog/… Paper: storage.googleapis.com/deepmind-media… 1/8

Pleased to share our #CVPR2024 paper on neural compression! TLDR: you can get very strong compression & super cheap decoding by overfitting a model to a single image 🖼️/video📽️. No need for a dataset! See main tweet for code💻 , paper📜 and project page🧑‍💻

Glad to see our video generation model 📽️ presented at #GoogleIO More details at: deepmind.google/technologies/v… We've made a lot of progress, but know that we can make it a lot better👷🛠️ Stay tuned!

🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models. w/ lovely coauthors Aleksander Holynski, Ben Poole and an amazing team!

What does it mean for an image, video, or text to be 𝑟𝑒𝑎𝑙𝑖𝑠𝑡𝑖𝑐? Despite how far we've come in 𝑔𝑒𝑛𝑒𝑟𝑎𝑡𝑖𝑛𝑔 realistic data, 𝑞𝑢𝑎𝑛𝑡𝑖𝑓𝑦𝑖𝑛𝑔 realism is still a poorly understood problem. I've shared my thoughts on how to correctly quantify realism here:

The noise schedule seems like a pretty important design choice for any diffusion model, but I have sometimes found this concept to be a greater source of confusion than insight😵‍💫 In this blog post, I try to explain why. sander.ai/2024/06/14/noi…

We're sharing progress on our video-to-audio (V2A) generative technology. 🎥 It can add sound to silent clips that match the acoustics of the scene, accompany on-screen action, and more. Here are 4 examples - turn your sound on. 🧵🔊 dpmd.ai/v2a

We’re presenting the first AI to solve International Mathematical Olympiad problems at a silver medalist level.🥈 It combines AlphaProof, a new breakthrough model for formal reasoning, and AlphaGeometry 2, an improved version of our previous system. 🧵 dpmd.ai/imo-silver

Diffusion is the rising tide that eventually submerges all frequencies, high and low 🌊 Diffusion is the gradual decomposition into feature scales, fine and coarse 🗼 Diffusion is just spectral autoregression 🤷🌈

Check out our new paper that turns (text, sparse images, videos) => (dynamic 3D scenes)! I can't get over how cool the interactive demo is. Try it out for yourself on the project page: cat-4d.github.io

New blog post: let's talk about latents! sander.ai/2025/04/15/lat…