Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Cosmos-Reason1 has exciting updates 💡 Now it understands physical reality — judging videos as real or fake! Check out the resources👇 Paper: Huggingface: Code: Project page: (1/n)

Max Zhaoshuo Li 李赵硕

1,280 subscribers

14,492 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨 Code dropped! One of the most exciting papers of the year! Check it out! Link in the comments 👇

🚨 Code dropped! One of the most exciting papers of the year! Check it out! Link in the comments 👇

MrNeRF

28,389 views • 1 year ago

📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: 📜 Paper: 🛠️ Code and weights: 🧵Details in thread... (1/n)

📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: 📜 Paper: 🛠️ Code and weights: 🧵Details in thread... (1/n)

Karsten Kreis

42,407 views • 1 year ago

The eagerly-awaited source code and weights for DragGAN are now out: (project page )

The eagerly-awaited source code and weights for DragGAN are now out: (project page )

Ben Ferns

175,313 views • 3 years ago

Multiple modalities, many applications. Cosmos 3, the first omni-model for physical AI, is here. Check out some amazing examples below 👇

Multiple modalities, many applications. Cosmos 3, the first omni-model for physical AI, is here. Check out some amazing examples below 👇

NVIDIA AI

23,276 views • 1 month ago

Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion Paper: (not yet) Project: Code:

Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion Paper: (not yet) Project: Code:

MrNeRF

19,907 views • 2 years ago

Advancing dexterous manipulation through scalable visual sim-to-real transfer. We are excited to share our RSS paper, “ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation.” 🌐 Project page: 1/N 🧵

Advancing dexterous manipulation through scalable visual sim-to-real transfer. We are excited to share our RSS paper, “ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation.” 🌐 Project page: 1/N 🧵

Robotic Systems Lab

39,143 views • 1 month ago

Ahmedabad Has Emerged As The No. 1 Cleanest City In The Country But let's check out the ground reality 🤡

Ahmedabad Has Emerged As The No. 1 Cleanest City In The Country But let's check out the ground reality 🤡

🚨Indian Gems

34,163 views • 11 months ago

Cut the slop out of your media diet. Embrace the physical reality of the printed word, brought to you by America's only newspaper. Real reporting. Real writing. Real art. Nothing fake. Subscribe here:

Cut the slop out of your media diet. Embrace the physical reality of the printed word, brought to you by America's only newspaper. Real reporting. Real writing. Real art. Nothing fake. Subscribe here:

County Highway

26,699 views • 4 months ago

Check out HSMR, Yan Xia's Yan XIA latest work. We reconstruct humans using a biomechanically accurate skeleton. Code and HuggingFace demo are live. Give it a try! Webpage: Code: Demo:

Check out HSMR, Yan Xia's Yan XIA latest work. We reconstruct humans using a biomechanically accurate skeleton. Code and HuggingFace demo are live. Give it a try! Webpage: Code: Demo:

Georgios Pavlakos

12,110 views • 1 year ago

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,077,699 views • 1 month ago

🔥🚀 Rewatch The Epic Era 3 Live Stream and check out the TL;DR! 🔥 🚀 Catch up on the exciting updates from our Era 3 reveal! 👇Watch the live stream NOW! 👇 TL;DR in 🧵

🔥🚀 Rewatch The Epic Era 3 Live Stream and check out the TL;DR! 🔥 🚀 Catch up on the exciting updates from our Era 3 reveal! 👇Watch the live stream NOW! 👇 TL;DR in 🧵

Angry Dynomites Lab 🦖

48,799 views • 1 year ago

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: Paper: Links to code and huggingface below ⬇️

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: Paper: Links to code and huggingface below ⬇️

Yawar Siddiqui

70,626 views • 5 months ago

[SIGGRAPH '24] RTG-SLAM: Real-time 3D Reconstruction at Scale Using Gaussian Splatting Paper (pdf link): Project: Code: Method ⬇️ 1 I 2

[SIGGRAPH '24] RTG-SLAM: Real-time 3D Reconstruction at Scale Using Gaussian Splatting Paper (pdf link): Project: Code: Method ⬇️ 1 I 2

MrNeRF

35,675 views • 2 years ago

1/ The Asteroid Protocol launchpad is now live! 🎉 With it, mintable art collections have arrived on Cosmos Hub ⚛️ for the first time. Learn more, and see how you can check out the brand new collections that are minting now! 🧵👇

Asteroid Protocol

16,146 views • 1 year ago

Happy Friday, Hydro Fam! 🎉 As we wrap up another exciting month, we’re thrilled to share some key updates from February. Check out what we’ve been up to and get ready for the big things to come! 🚀👇👇👇👇👇

Happy Friday, Hydro Fam! 🎉 As we wrap up another exciting month, we’re thrilled to share some key updates from February. Check out what we’ve been up to and get ready for the big things to come! 🚀👇👇👇👇👇

Hydro Online

58,718 views • 1 year ago

Teaser trailer from our accent project. Check it out 👇

Teaser trailer from our accent project. Check it out 👇

Appodlachia

50,561 views • 1 year ago

[1/N] Rotary Position Embeddings (RoPE) are ubiquitous across transformers that process tokens from 1D, 2D, or 3D grids e.g. language, images, or videos. Our RayRoPE formulation extends these to multi-view transformers. Paper and code:

[1/N] Rotary Position Embeddings (RoPE) are ubiquitous across transformers that process tokens from 1D, 2D, or 3D grids e.g. language, images, or videos. Our RayRoPE formulation extends these to multi-view transformers. Paper and code:

Shubham Tulsiani

55,859 views • 5 months ago

🚀 Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:

🚀 Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:

DeepSeek

16,400 views • 2 years ago

Exciting announcement💗 Instagram heard it first and now you! So excited to partner with PHLster a company I believe in. Check out their free learning resources for better concealment!

Exciting announcement💗 Instagram heard it first and now you! So excited to partner with PHLster a company I believe in. Check out their free learning resources for better concealment!

Emily Stanley / Princessandthepistol

12,049 views • 7 months ago

The Blackbox CLI is now open source. Smart debugging, automated project setup, and multi-agent execution to run multiple coding agents in parallel. Check out the code, contribute, or report any issues here

The Blackbox CLI is now open source. Smart debugging, automated project setup, and multi-agent execution to run multiple coding agents in parallel. Check out the code, contribute, or report any issues here

BLACKBOX AI

14,117 views • 6 months ago