Proud to announce Dobb·E: the next step in home robot system that I was working on for the past 3 years. We have visited 10 homes, learned 100+ tasks, and we are just getting started! And we fully open-sourced it all, hardware, models, and software: dobb-e.com 🧵

Get visual instructions to your most pressing questions :) We jazz up an LLM's text-only answers with corresponding images.

Introducing the stellar lineup for #OxML2024, featuring pioneers in the field of Machine Learning for two cutting-edge summer schools: - MLx Representation Learning & Generative AI (6–9 July) and - MLx Health & Bio (11–14 July) 🌎🙌🎓💡🧬📈 Location: University of Oxford's

Meta just announced FlowVid Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis paper page: huggingface.co/papers/2312.17… Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of

🚀 Excited to share InstanceDiffusion @CVPR2024! It adds precise instance-level control for image gen: free-form text conditions per instance and diverse location specs—points, scribbles, boxes & instance masks Code: shorturl.at/dtxSW arXiv: shorturl.at/rQS14 1/n

Our third and last talk of today is from Ishan Misra from AI at Meta. From how to leverage existing visual understanding datasets for better generative model evaluations to making video and controllable diffusion models, another world expert sharing their knowledge with us 👏 🤩

Introducing the next generation of the Meta Training and Inference Accelerator (MTIA), the next in our family of custom-made silicon, designed for Meta’s AI workloads. Full details ➡️ go.fb.me/kwahju

Delighted to host the 1st edition of our tutorial "Time is precious: Self-Supervised Learning Beyond Images" at European Conference on Computer Vision #ECCV2024 with mrz.salehi and Yuki. We have an exciting line of speakers too joao carreira, Ishan Misra and Emin Orhan. More details coming soon...#ECCV2024

Llama3 is out with great performance and efficiency!! Models are available for download :) Check out meta.ai to interact

Check out the generative vision related release too meta.ai/?icebreaker=im… Imagine Flash generates the image as you type You can also "Animate" your images! (technique based on Emu Video emu-video.metademolab.com) Kudos to the team for putting this out :)

There's another quieter release from AI at Meta today that's really cool. * Live Preview: As you type your image prompt, you get a live preview, making iterating for a good image easier. * Animate: now you can animate images for short bursts

Don’t miss Imagine Flash, released as part of the Llama3 launch. It’s pretty awesome!

GenAI Media Generation Challenge Workshop #CVPR2024 is today (6/17): 📍 Summit 423-425 ⌛️ 1:15 - 5:40 pm ⌛️ We have exciting keynote speeches from Jun-Yan Zhu (Jun-Yan Zhu), Sergey Tulyakov, Richard Zhang (Richard Zhang), Yuanzhen Li, and Tim Salimans to share the latest progress on

Come hear about our work on creating fully illustrated how-to articles with LLMs and diffusion models CVPR News poster 143 this afternoon! This project came out of my internship AI at Meta with amazing collaborators Rohit Girdhar and Ishan Misra, excited to share today. #CVPR2024

Join us on June 19 5pm at posters 139, 143, and 331 for our CVPR work on image generation, VLMs and video generation! arxiv.org/abs/2402.03290 arxiv.org/abs/2312.04552 arxiv.org/abs/2312.17681 #cvpr2024

Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet. Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context

Llama 3.1 is out! Through adapters we've made it multimodal, supporting images, videos, speech! Was a fun journey adding video understanding capabilities with Rohit Girdhar, Filip Radenovic , Ishan Misra and the whole MM team! P.S. MM models are WIP (not part of the release).

The 5th edition of our self-supervised learning workshop at NeurIPS 2024 this year :) Great line-up of speakers and the call for papers is out!

Autoregressive language modeling meets diffusion models! In a single shared model. Super cool work 😊