🎉 Our paper MJEPA has been accepted at #ECCV2026# !! Huge thanks to my awesome collaborators @AdrienBardes, @michaelrabbat , Sumit Chopra @mattmucklm and Nicolas Ballas Paper: Code + checkpoints coming soon See you at ECCV!

I want to offer some unsolicited advice to computer vision researchers jumping into robotics. Don't focus too much on VLMs, VLAs etc. That's fine, but the real action is at the sensorimotor level. Most of the open problems in robotics are in manipulation, which is about hand-object interaction, and contacts and forces are central. Proprioception and tactile sensing are as important as vision. Don't get seduced by cherry-picked demos. You can't do robotics without doing robotics.

I’m thrilled to share that I have joined AMI Labs as a Member of Technical Staff! 🚀 We are building the future of AI in the physical world and actively hiring from all our offices. Reach out to me if you are interested in research roles in our Paris office!

📢 Accepted to TMLR, with reproducibility certification 🏅 v2 of our JEPA-WM study (arXiv:2512.24497) is out, with new data-scaling experiments, a Lipschitz analysis of multistep rollout training, and extended discussions. Recap + what's new 👇 w/ @JimmyTYYang1, Jean Ponce, @AdrienBardes, @ylecun

Planning is one of the most exciting uses of world models, but existing planners struggle on long horizons. Introducing GRASP: a fast gradient-based planner for world models that outperforms prior methods on long-horizon tasks. Two key ideas: 1.jointly optimize actions and intermediate subgoals 2.inject stochasticity to explore subgoal space Project page: Paper: w/ @michaelpsenka @mikerabb @ask1729 and @ylecun

𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗘𝗕-𝗝𝗘𝗣𝗔 ⚡ An open-source library making JEPAs accessible, trainable on a single GPU in hours! 🚀 🔗 Paper: 💻 Code:

My first PhD paper is out! 🎓 "What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?" tl:dr: JEPA-WMs for robotics: learn dynamics on top of visual encoders, optimize actions towards goal 👇 w/ @JimmyTYYang1, Jean Ponce, @AdrienBardes, @ylecun

🚨New Paper @AIatMeta 🚨 You want to train a largely multilingual model, but languages keep interfering and you can’t boost performance? Using a dense model is suboptimal when mixing many languages, so what can you do? You can use our new architecture Mixture of Languages! 🧵1/n

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

Does your LLM truly comprehend the complexity of the code it generates? 🥰   Introducing our new non-saturated (for at least the coming week? 😉) benchmark:   ✨BigO(Bench)✨ - Can LLMs Generate Code with Controlled Time and Space Complexity?   Check out the details below !👇

The last paper of my PhD is finally out ! Introducing "Intuitive physics understanding emerges from self-supervised pretraining on natural videos" We show that without any prior, V-JEPA --a self-supervised video model-- develops an understanding of intuitive physics !

Job alert 🚨 My team @AIatMeta is looking for a PhD intern to join us in 2025 in Paris. We are working on self-supervised learning from video, world modelling and JEPA ! Apply here or reach out directly:

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details ➡️

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 window and improved support for 8 languages among other improvements. Llama 3.1 405B rivals leading closed source models on state-of-the-art capabilities across a range of tasks in general knowledge, steerability, math, tool use and multilingual translation. The models are available to download now directly from Meta or @huggingface. With today’s release the ecosystem is also ready to go with 25+ partners rolling out our latest models — including @awscloud, @nvidia, @databricks, @groqinc, @dell, @azure and @googlecloud ready on day one. More details in the full announcement ➡️ Download Llama 3.1 models ➡️ With these releases we’re setting the stage for unprecedented new opportunities and we can’t wait to see the innovation our newest models will unlock across all levels of the AI community.

@ylecun from @AIatMeta greets the public at the exclusive Open Source AI Day event at @joinstationf at panel with @adriennejan from @Scaleway, @Thom_Wolf from @huggingface and @ptrkprz from @kyutai_labs Join us as We will continue by great...

Are sota image generative models effective world models? Consistency-diversity-realism Pareto fronts show they're not (yet): - No model dominates others as a world model - Improvements in quality and consistency have come at the expense of diversity 🔗

📝 New from FAIR: An Introduction to Vision-Language Modeling. Vision-language models (VLMs) are an area of research that holds a lot of potential to change our interactions with technology, however there are many challenges in building these types of models. Together with a set of collaborators across academia, we’re releasing ‘An Introduction to Vision-Language Modeling’ — we hope that this new resource will help anyone who would like to enter this field to better understand the mechanics behind mapping vision to language. Full paper ➡️ This guide covers how VLMs work, how to train them and approaches to evaluation — and while it primarily covers mapping image to language, it also discusses how to extend VLMs to videos. We hope that releasing this guide will inspire and enable more work in this space.

What happens if we make language models predict several tokens ahead instead of only the next one? In this paper, we show that multi-token prediction boosts language model training efficiency. 🧵 1/11 Paper: Joint work with @FabianGloeckle