We had a lot of fun presenting our NVIDIA Edify for 3D scene generation at #SIGGRAPH2024 !! We made a blog post to introduce the show and the technology behind it.

Check out our 3D generator! #SIGGRAPH2024

The NVIDIA Graduate Fellowship application is now open! Deadline: 09/13 research.nvidia.com/graduate-fello… As a past recipient, I strongly recommend applying! You get the money as well as the guaranteed opportunity for a summer internship!

Looking for SOTA image/video tokenizers to tokenize visual content efficiently for your Physical AI or Gen AI applications? Cosmos tokenizer provides a family of tokenizers with different compression factors for both continuous and discrete tokens youtu.be/Soy_myOfWIU?si…

We have released a tech report on Edify 3D, documenting our two-year effort at NVIDIA on 3D asset generation, from research to product launch! Paper: arxiv.org/abs/2411.07135 Project page: research.nvidia.com/labs/dir/edify… Definitely check out the video with 🔊! youtube.com/watch?v=ROqB8x…

Our latest work generates meshes of up to 64K faces with great topology. It supports both quad and triangle topology, with face count control and creativity control. Check out the blog post for details! Kudos to the team! w/David W. Romero Tsung-Yi Lin Ming-Yu Liu

A peaceful winter landscape unfolds as a car drives along a snow-covered road, which stretches toward the horizon, flanked by tall, slender trees on either side. #NVIDIACosmos #NVIDIACES #Nvidia

A galaxy of open-weight world foundation models from awesome teammates!

Video generation models exploded onto the scene in 2024, sparked by the release of Sora from OpenAI. I wrote a blog post on key techniques that are used in building large video generation models: yenchenlin.me/blog/2025/01/0…

We have added a couple of new capabilities to Cosmos to help physical AI builders further advance their systems. Please come to join the session. We are eager to share the latest and greatest of Cosmos with you.

Our reasoning VLM that understands Physical AI!

DeepSeek R1 demonstrates AI mastering math through reinforcement learning. We introduce Cosmos-Reason1, which learns with Physical AI rewards and excels in physical AI tasks.

You think camera pose estimation is solved? How about NVIDIA's Racer RTX? youtu.be/AsykNkUMoNU?si… We challenge you with ⚡️ Lightspeed benchmark (as part of DynPose-100K release) — crazy wild videos with 𝗴𝗿𝗼𝘂𝗻𝗱-𝘁𝗿𝘂𝘁𝗵 camera poses! huggingface.co/datasets/nvidi… #CVPR2025

The beginning of Physical AI reasoning -now available on Hugging Face. Proud to be part of the release. Looking forward to community feedback!

Cosmos-Reason1 has exciting updates 💡 Now it understands physical reality — judging videos as real or fake! Check out the resources👇 Paper: arxiv.org/abs/2503.15558 Huggingface: huggingface.co/nvidia/Cosmos-… Code: github.com/nvidia-cosmos/… Project page: research.nvidia.com/labs/dir/cosmo… (1/n)

🚀 Introducing Cosmos-Predict2! Our most powerful open video foundation model for Physical AI. Cosmos-Predict2 significantly improves upon Predict1 in visual quality, prompt alignment, and motion dynamics—outperforming popular open-source video foundation models. It’s openly

Happy to share our work PartPacker: We enable one-shot image-to-3D generation with any number of parts! Project page: research.nvidia.com/labs/dir/partp… Demo: huggingface.co/spaces/nvidia/… Code: github.com/NVlabs/PartPac…

Generating 3D shapes with parts! Be sure to check out our online demo: huggingface.co/spaces/nvidia/…

Nvidia cooked with PartPacker 3D Generation A new method to create 3D objects from a single image, with each part separate and easy to edit 🔥 ⬇️ Demo available on Hugging Face

We build Cosmos-Predict2 as a world foundation model for Physical AI builders — fully open and adaptable. Post-train it for specialized tasks or different output types. Available in multiple sizes, resolutions, and frame rates. 📷 Watch the repo walkthrough