The 3D Humans workshop is kicking off in 15 min! Remote attendees: Zoom link is available at CVPR website: cvpr.thecvf.com/virtual/2024/w…

It’s starting! The opening and introductions by Siwei Zhang

Siwei Zhang Our first talk is starting: Prof Kris Kitani from CMU on “Estimation and Actuation of 3D bodies”

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.

Nvidia presents Edify Image High-Quality Image Generation with Pixel Space Laplacian Diffusion Models

Creativity unleashed 👨‍🎨🎨✨ 👀 Edify3D from #NVIDIAResearch explores a new way to generate text-to-#3D images. 📗 Project page: research.nvidia.com/labs/dir/edify… 📝 Paper: arxiv.org/abs/2411.07135 🔊 sound on

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025

🚨Excited to announce the 1st Workshop on Vision Meets Physics at @CVPR2025! Join us on June 12 for a full-day event exploring the synergy between physical simulation & computer vision to bridge the gap between the virtual and physical worlds. URL: tinyurl.com/vis-phys

I’ll be giving several workshop talks at CVPR this year. Because I'm a gluten for punishment, there will be very little overlap between most of these talks. I’ll cover several of our CVPR2025 papers including PromptHMR, PICO, InteractVLM, ChatHuman, ChatGarment, DiffLocks as

🚨Excited to announce the 1st Workshop on Vision Meets Physics at @CVPR2025 Join us tomorrow 6/12 for a full-day event exploring the synergy between physical simulation & computer vision to bridge the gap between the virtual and physical worlds. URL: tinyurl.com/vis-phys

🚀 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

Starting now! Prof Wei-Chiu Ma is talking about “Towards Physically-Grounded Digital Twins”! 📍104A

Happening now at Vision Meets Physics Workshop: Tsung-Yi Lin is talking about NVIDIA cosmos! 📍104A

Come back at 4:30PM for the second session with 2 exciting talks from Sebastian Starke and Hanbyul (Han) Joo and a panel discussion featuring Georgios Pavlakos and all speakers!