🔥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

CUTLASS is in the center of the CUDA Blackwell release blog. As always, we work hand in hand with CUDA team to deliver the next level performance. developer.nvidia.com/blog/cuda-tool…

Great work by Google DeepMind on Matryoshka Quantization! Back in 2019, we introduced Any-Precision DNNs, enabling a single deep learning model to dynamically support any bit-widths without retraining. Excited to see how these ideas help Gemini/LLMs! arxiv.org/abs/1911.07346

Thrilled to share this story covering our collaboration with Project Aria @Meta Reality Labs at Meta ! Human data is robot data in disguise. Imitation learning is human modeling. We are at the beginning of something truly revolutionary, both for robotics and human-level AI beyond language.

Thanks for featuring our work! Aran Komatsuzaki. 🔥Today we are thrilled to announce our MSR flagship project Magma! This is a fully open-sourced project. We will roll out all the stuff: code, model and training data through the following days. Check out our full work here:

Come see my presentation on Distributed GEMM in GPU MODE tomorrow!

Five months after Hurricane Helene, we’re finally starting to rebuild our home. Grateful for my family’s resilience through this journey 🙏 Meanwhile, AI’s rapid progress feels like a hurricane, reshaping everything in its path. Perhaps we, too, should rebuild—forward & onward.

Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD

Congrats to Prof Barto & Sutton on Turing Award! 🎉 Barto’s journey is inspiring—I happen to be teaching McCulloch-Pitts neuron to hundreds of Georgia Tech undergrads today in my comp vision class.Makes me wonder what breakthroughs our next-gen leaders will achieve in 50 years🚀

Check out WorldModelBench, our first workshop on Benchmarking World Models #CVPR2025, lead by researchers from NVIDIA and beyond. Explore benchmarks, evaluation metrics, downstream tasks, & safety for World Models. Call for papers now open till April 7th: worldmodelbench.github.io

Video/Physics Generative AI was bottlenecked by diffusion runtime— 5s used to take minutes. My student Ali Hassani Georgia Tech Computing helped scale full 35-step Cosmos 7B DiT 40× to real-time on Blackwell NVL72, in collab w/ NVIDIA Ming-Yu Liu’s team. Congrats—just the beginning!🐝🚀

One year ago, Abhishek Das and I left Meta to start Yutori. Ten months ago, Dhruv Batra joined us :) Nine months ago, we crystallized our vision. Two months ago, we released a sneak peak into what we’ve been building. Today, can’t be more excited to fully unveil Yutori’s

Check out Slow-Fast Video MLLM — a new paradigm to empower multi-modal LLMs with longer video context and finer spatial detail! 🎥🧠 🔗 github.com/SHI-Labs/Slow-… Led by 🐝 Min Min Shi from Georgia Tech Computing, in collaboration with NVIDIA Zhiding Yu and more 🤝

Huge congrats to Jiahui Yu and Bowen Cheng—our young and talented former IFP lab alumni—for their amazing work on GPT-4.1 at OpenAI.🎉 Proud and inspired — as one of the old guards watching the next wave take flight. The future clearly belongs to the young. Onward and upward! 🚀

After nearly 5 incredible years, I’ve stepped down from my role as Chief Scientist at Picsart. Grateful for the journey—from building AI Research from scratch to a global team creating products used by millions every day✨ Now exploring what’s next in multimodal AI🚀. DMs open🤝

"Thinking with Images" is what we have been cooking after GPT-4o launched last year and it marks a paradigm shift in how we view/solve perception problems in this new era of RL. It is such a pleasant and an honor to work with this amazing team to get it out!

Impressed by FramePack from style2paints & Maneesh Agrawala! Their table puts our StreamingT2V (Mar 2024) at #2 overall and 🥇 in motion (99.96 %). A nice reminder that memory blocks still matter—and may fruitfully complement token‑compression and other approaches for marathon vids!🏃

Wondering what's happening with NATTEN in 2025? Check out Generalized Neighborhood Attention! Spoiler: NATTEN gets a new stride parameter, we made a simulator for all your analytical studies, AND a Blackwell kernel! Keep reading for more... (1 / 5)

A paper from my PhD students—nearly a year of work—was rejected by ICML Conference despite 4 weak accepts, citing “calibration with other submissions.” Still incredibly proud of my students. To young researchers: rejections happen. Keep learning, keep going—the real judge is within.