🔥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

Exciting updates on Project GR00T! We discover a systematic way to scale up robot data, tackling the most painful pain point in robotics. The idea is simple: human collects demonstration on a real robot, and we multiply that data 1000x or more in simulation. Let’s break it down:

🚀 Just dropped the code: #InstantSplat! Reconstruct your 3D scenes in seconds. Get it now at github.com/NVlabs/Instant… and start building! ✨ #3DVision #AI #ComputerVision #NVlabs #OpenSource

劇場版、パリオリンピック射撃。 無課金おじさんよ、永遠にーーー

🔥Excited to share our work on speculative diffusion decoding! We use discrete diffusion as a drafting model to massively speed up #LLM inference---up to 8.7x faster over standard generation and 2.5x faster than traditional spec dec approaches.🚀 🔗Links below

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based

More importantly, check out the AI at Meta's research paper that details how Meta Movie Gen foundation model was built. ai.meta.com/static-resourc…

I finally released my new video on YouTube about Diffusion Models / Score-Based Generative Models. youtube.com/watch?v=B4oHJp… Literally planned this for a year and put so much work in. I think this approach to diffusion models is so intuitive and highly recommend giving that a

🏆 #UIST2024 We won the Best Paper Award for Augmented Physics! Huge congratulations to Aditya Gunturu Nandi Zhang Yi Wen Rubaiat Habib at U Calgary Adobe Research ATLAS Institute 🦬 Don't miss Aditya's talk and demo showcasing the AI-powered future of education. ryosuzuki.org/augmented-phys…

Introducing MarDini 🍸 -- our latest exploration in video diffusion models from AI at Meta! MarDini brings an asymmetric design that breaks down video modelling into two sub-tasks: 1. A masked, auto-regressive, heavy-weight planning model focusing on long-range temporal

Absolutely beautiful industrial design.

World Labs just dropped their first results/demos!

🚀Introducing Leffa: Learning Flow Fields in Attention for Controllable Person Image Generation! 👤🔄👗 Leffa is a unified framework for controllable person image generation that enables precise manipulation of both appearance (virtual try-on) and pose (pose transfer). It guides

1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feeling uncomfortable. As a community, I believe we should take a moment to reflect on why such remarks in public discourse can be offensive and harmful.

o3 is incredible

Felix Hill was a wonderful human being. He was, not only extremely intelligent, creative and passionate, but also very helpful and kind at work. He had a very special thoughtful mind - the rare kind that I’ve learned to deeply appreciate. Beyond work, he brought fun, joy and

I have Post-Doc, PhD, and Research Assistant positions available, for a new project working with me on dexterous robot learning! Come and join me, my team, and our robots, at Imperial College London! 🤖🧑‍💻🇬🇧💂🤖 See robot-learning.uk/dexterous-robo… for more info. Please share/retweet!

Some further thoughts on the idea of "thinking with images": 1) zero-shot tool use is limited -- you can’t just call an object detector to do visual search. That’s why approaches like VisProg/ViperGPT/Visual-sketchpad will not generalize or scale well. 2) visual search needs to

Can diffusion models appear to be learning, when they’re actually just memorizing the training data? We show and investigate this phenomenon in the context of neural network weight generation, in our recent paper “Generative Modeling of Weights: Generalization or Memorization?"

I’m honored to have been invited to create a brand-new piece of calligraphic motion design for 'Ink & The City: Calligraphy in Urban Life' , an exhibition that’s part of the Hong Kong International Airport Arts & Culture Festival 2025 Exhibition Period: 25 July – 8 November 2025