Super excited to announce seven new world-class MAI models today. They represent what we consider a new era in AI designed to keep you in control and on the frontier. First is our text foundation model, MAI-Thinking-1, exceptionally strong on reasoning and SWE tasks. - It’s a 35B active parameter MoE with a 256K context window. Independent human raters on Surge prefer it for overall quality in blind side-by-sides versus Sonnet 4.6, and it’s achieved 97% on AIME 2025, the key measure of its general-purpose reasoning abilities. - It's at 53% on SWE Bench Pro, placing it right alongside Opus 4.6 on one of the toughest coding benchmarks. - And since we co-designed our models with our own silicon, MAI-Thinking-1 is optimized on our MAIA 200 chip. Benchmarking head-to-head against the GB200, we see 30% better performance per dollar as well as a 1.4x performance-per-watt gain when running our MAI models on the MAIA 200 end-to-end. Next is MAI-Image-2.5 and its Flash variant. Two super strong models now at #2 on the leaderboards, surpassing the score of Nano Banana 2 on image editing. Last for now is MAI-Code-1-Flash, our new inference efficient coding model, especially tuned for VS Code and GitHub Copilot CLI. - Code-1-Flash achieves 51% on SWE Bench Pro, despite having just 5B parameters, putting it closer to Haiku in size but cheaper in cost. All of this is the foundation for Microsoft Frontier Tuning. It lets you customize our models to create custom, company-specific agents that only you control. You can make our model, your model. Your data. Your agents. Your moat. Early adopters are already seeing a difference. When we tuned our models for McKinsey’s tasks, MAI delivered the highest win rate, outperforming GPT-5.5 on quality, while being 10x lower on cost. Also really excited to be collaborating with the amazing team at Mayo Clinic to jointly train a new frontier AI model for healthcare. Our announcements today mark another milestone on the road to humanist superintelligence. You can learn more and about our other new models in our latest blog: microsoft.ai/news/building-a…

WOW microsoft new "MAI Thinking 1" model comes with a 109 page tech report that looks REALLY detailed, this is amazing

Mustafa Suleyman, Microsoft AI: 7 new Microsoft Models, no end in sight when it comes to development, orders of magnitude in the next few years

Microsoft’s MAI-Image-2 enters the top three AI image generators in the world thenextweb.com/news/microsof… via @thenextweb

I am working on building teams for the likes of @NandoDF and @asadovsky for @MicrosoftAI! We are #HiringNow in Europe and US 🧵👇 - follow me for more updates on our Superintelligence Lab - Roles below 🔔

Video gen models excel at replacing humans in front of the camera. But what if they could augment & enhance our performance instead? 🧵 (1/6) 🎬EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers edit-yourself.github.io

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: facebookresearch.github.io/S… Paper: arxiv.org/abs/2601.11514 Links to code and huggingface below ⬇️

Was gonna wait to announce this 😅 🚨 but yeah new checkpoints just dropped!! Pull latest code and update hf cache - it's a direct slot in & just a better MapA 😉 HF demo also updated: huggingface.co/spaces/facebo… Stay tuned for more details & 3DV camera ready ⏳

See you later at the #iccv25 Oral Session 6B (Kalākaua Ballroom) at 1PM and poster 356 from 2:30PM! We will present our paper “Easy3D: A Simple Yet Effective Method for 3D Interactive Segmentation” with @Normanisation Project Code: simonelli-andrea.github.io/e…

📢 SceneComp @ ICCV 2025 🏝️ 🌎 Generative Scene Completion for Immersive Worlds 🛠️ Reconstruct what you know AND 🪄 Generate what you don’t! 🙌 Meet our speakers @angelaqdai, @holynski_, @jampani_varun, @ZGojcic @taiyasaki, Peter Kontschieder scenecomp.github.io #ICCV2025

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

📢Excited to be at #ICLR2025 for our paper: VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control Poster: Thu 3-5:30 PM (#134) Website: snap-research.github.io/vd3d… Code: github.com/snap-research/ac3… Also check out our #CVPR2025 follow-up AC3D: snap-research.github.io/ac3d…

Tired of staring at GS reconstructions? Check out our new method for 3D Interactive Segmentation💥 Easy3D: A Simple Yet Effective Method for 3D Interactive Segmentation Project: simonelli-andrea.github.io/e… Paper: arxiv.org/pdf/2504.11024 👇Real-time VR interaction on a GS scene👇

1/3 Introducing FlowR 🌸: Flowing from Sparse to Dense 3D Reconstructions We learn a direct mapping between incorrect renderings and their corresponding ground-truth images, augmenting scene captures with consistent novel, generated views to improve reconstruction quality.