正在加载视频...

视频加载失败

返回首页

🤖 One predictive backbone, three distinct tasks, consistent gains: a strong signal that investing in reusable world models is the right abstraction for robot learning. Toyota Research Institute (TRI) just ran the same idea three different ways—and it worked each time. Using our NVIDIA Cosmos Predict 2–style world models,...

NVIDIAAIDev's profile picture

NVIDIA AI Developer

110,898 subscribers

38,100 次观看 • 4 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Protein language models just got an upgrade. Meet Profluent-E1: a free, flexible, frontier protein sequence encoder. E1 is built with retrieval augmentation to learn from multiple sequences. Models trained over 4T tokens with only 150M-600M params, E1 is SOTA for zero-shot functional and unsupervised structural tasks. It raises the bar for protein representation learning and is freely available today.
0:13

Protein language models just got an upgrade. Meet Profluent-E1: a free, flexible, frontier protein sequence encoder. E1 is built with retrieval augmentation to learn from multiple sequences. Models trained over 4T tokens with only 150M-600M params, E1 is SOTA for zero-shot functional and unsupervised structural tasks. It raises the bar for protein representation learning and is freely available today.

Profluent

222,093 次观看 • 7 个月前

World models aren't the same as regular video models. The benchmarks are different. I'm really stoked to see what visionary creators do with this technology.
0:10

World models aren't the same as regular video models. The benchmarks are different. I'm really stoked to see what visionary creators do with this technology.

Purz.ai

47,486 次观看 • 1 个月前

JUST IN: Meta AI introduces Voicebox, an all-in-one generative speech model. Voicebox is an impressive breakthrough! It could do for speech what other models like GPT-3 and Stable Diffusion have done for text and images. Some key details: - Voicebox can synthesize speech across 6 languages - It's a general-purpose model that can perform tasks it wasn't trained on. It can perform noise removal, content editing, style conversion, and more - Supports in-context text-to-speech synthesis and cross-lingual style transfer - It's 20x faster than current models and outperforms single-purpose models through in-context learning paper: blog:
0:13

JUST IN: Meta AI introduces Voicebox, an all-in-one generative speech model. Voicebox is an impressive breakthrough! It could do for speech what other models like GPT-3 and Stable Diffusion have done for text and images. Some key details: - Voicebox can synthesize speech across 6 languages - It's a general-purpose model that can perform tasks it wasn't trained on. It can perform noise removal, content editing, style conversion, and more - Supports in-context text-to-speech synthesis and cross-lingual style transfer - It's 20x faster than current models and outperforms single-purpose models through in-context learning paper: blog:

elvis

88,512 次观看 • 3 年前

(1/6) X-Humanoid 🤖: Scaling up data for Humanoid Robots. We convert human daily activity videos (from Ego-Exo4D) into humanoid videos (i.e., Tesla Optimus) performing tasks like cooking or fixing a bike. This data can be potentially used to train robot policies and world models. 🔥 Project page: Paper link:
0:11

(1/6) X-Humanoid 🤖: Scaling up data for Humanoid Robots. We convert human daily activity videos (from Ego-Exo4D) into humanoid videos (i.e., Tesla Optimus) performing tasks like cooking or fixing a bike. This data can be potentially used to train robot policies and world models. 🔥 Project page: Paper link:

Mike Shou

87,622 次观看 • 6 个月前

Placing objects sounds simple… until robots have to do it. This method makes it simple, fast & reliable. [Github ⬇️] Robotic object placement is tough, especially with stacking, hanging, or insertion. AnyPlace is a new two-stage method that uses only synthetic data and a vision-language model to teach robots where and how to place objects; even in the real world. Why this works ✅ Finds the right spot with help from vision-language models ✅ Handles stacking, insertion, and hanging with no real-world training ✅ Trained on synthetic data using Blender and IsaacSim ✅ Works in the real world without fine-tuning It shows that smart use of simulation and language models can make robotic placement tasks easier, faster, and more reliable. Github: Paper: Thank you for sharing Animesh Garg !
0:13

Placing objects sounds simple… until robots have to do it. This method makes it simple, fast & reliable. [Github ⬇️] Robotic object placement is tough, especially with stacking, hanging, or insertion. AnyPlace is a new two-stage method that uses only synthetic data and a vision-language model to teach robots where and how to place objects; even in the real world. Why this works ✅ Finds the right spot with help from vision-language models ✅ Handles stacking, insertion, and hanging with no real-world training ✅ Trained on synthetic data using Blender and IsaacSim ✅ Works in the real world without fine-tuning It shows that smart use of simulation and language models can make robotic placement tasks easier, faster, and more reliable. Github: Paper: Thank you for sharing Animesh Garg !

Ilir Aliu - eu/acc

22,843 次观看 • 1 年前

Bring new robot testing environments to life with World Labs and Isaac Sim. 🤖 If you can describe a world 🌎, you can start testing in it the same day. Learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #SIGGRAPHAsia2025
0:12

Bring new robot testing environments to life with World Labs and Isaac Sim. 🤖 If you can describe a world 🌎, you can start testing in it the same day. Learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #SIGGRAPHAsia2025

NVIDIA Robotics

157,556 次观看 • 6 个月前

Vision AI agents are becoming a practical way to automatically turn video data from the physical world into operational intelligence in factories, cities, warehouses and transportation systems. See how Roboflow, DeepHow, and Linker Vision use NVIDIA Cosmos and NVIDIA Metropolis to generate synthetic data, fine-tune vision models faster, and deploy vision agents at scale. 📰 Read the blog:
0:13

Vision AI agents are becoming a practical way to automatically turn video data from the physical world into operational intelligence in factories, cities, warehouses and transportation systems. See how Roboflow, DeepHow, and Linker Vision use NVIDIA Cosmos and NVIDIA Metropolis to generate synthetic data, fine-tune vision models faster, and deploy vision agents at scale. 📰 Read the blog:

NVIDIA Omniverse

17,804 次观看 • 2 天前

In a masterclass at Sequoia Capital AI Ascent, Jim Fan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook. 🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics. 🔹 Teleop → EgoScale: Replacing manual data with human egocentric video. 🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments. "Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics." He believes that robots will pass the Physical Turing Test in the coming 2–3 years.
0:19

In a masterclass at Sequoia Capital AI Ascent, Jim Fan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook. 🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics. 🔹 Teleop → EgoScale: Replacing manual data with human egocentric video. 🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments. "Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics." He believes that robots will pass the Physical Turing Test in the coming 2–3 years.

Humanoids daily

12,117 次观看 • 1 个月前

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵
2:39

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

Hila Chefer

67,648 次观看 • 4 个月前

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!
0:15

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

Santiago

171,340 次观看 • 1 年前

Most AI models just predict the next pixel to build a narrative or an image. Gemini Omni is different. Gemini Omni has an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics for more realistic movements that follow real-world logic.
0:10

Most AI models just predict the next pixel to build a narrative or an image. Gemini Omni is different. Gemini Omni has an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics for more realistic movements that follow real-world logic.

Google

67,332 次观看 • 1 个月前

Over the Reality just hit another major milestone in the AI era. We have now surpassed 200,000 mappings in our dataset. 🎉 These are not just images. They are high-quality 3D maps generated from the mapping activity of our global community, which has produced more than 94M images of real-world locations so far. The dataset also includes 900TB+ of spatial data that can power Visual AI models, Robotics VPS for real-world navigation and positioning, XR VPS for precise spatial anchoring and AR experiences, Spatial Computing applications, Digital Twins, and the next generation of real-world AI infrastructure. In just the past 2 weeks, our dataset grew by +17,955 mapped locations. That is nearly +10% growth in just 14 days. More maps. More data. More demand for $OVR.
0:10

Over the Reality just hit another major milestone in the AI era. We have now surpassed 200,000 mappings in our dataset. 🎉 These are not just images. They are high-quality 3D maps generated from the mapping activity of our global community, which has produced more than 94M images of real-world locations so far. The dataset also includes 900TB+ of spatial data that can power Visual AI models, Robotics VPS for real-world navigation and positioning, XR VPS for precise spatial anchoring and AR experiences, Spatial Computing applications, Digital Twins, and the next generation of real-world AI infrastructure. In just the past 2 weeks, our dataset grew by +17,955 mapped locations. That is nearly +10% growth in just 14 days. More maps. More data. More demand for $OVR.

Over the Reality 🌐

926,400 次观看 • 3 个月前

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.
0:17

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

Bilawal Sidhu

25,802 次观看 • 5 个月前

made an app that guesses where you are in the world with just a picture using image embeddings trained on street view data first time using swiftui, consumer apps in general, TestFlight below
0:18

made an app that guesses where you are in the world with just a picture using image embeddings trained on street view data first time using swiftui, consumer apps in general, TestFlight below

Surya

9,600,832 次观看 • 2 年前

MoVieS Motion-Aware 4D Dynamic View Synthesis in One Second
0:14

MoVieS Motion-Aware 4D Dynamic View Synthesis in One Second

AK

29,601 次观看 • 11 个月前

How can we rigorously quantify the uncertainty of pretrained perception models to provide end-to-end statistical safety assurances for robot navigation?Perceive With Confidence: Statistical Safety Assurances for Navigation with Learning-Based Perception 🧵
0:11

How can we rigorously quantify the uncertainty of pretrained perception models to provide end-to-end statistical safety assurances for robot navigation?Perceive With Confidence: Statistical Safety Assurances for Navigation with Learning-Based Perception 🧵

Anirudha Majumdar

11,393 次观看 • 2 年前

📢 Our lab has been exploring 3D world models for years — and we’re thrilled to share **PhysTwin**: a milestone that reconstructs object appearance, geometry, and dynamics from just a few seconds of interaction! Led by the amazing Hanxiao Jiang 👉 PhysTwin combines **Gaussian splatting** with **inverse dynamics optimization** based on simple **spring-mass** systems. ⚙️ The result? Real-time, action-conditioned 3D video prediction under novel interactions (i.e., 3D world models). 🔑 A few key takeaways: 1. Having the right structure (e.g., particles/masses) helps navigate the trade-off between sample efficiency, generalization, and broad applicability. 2. Visual foundation models (VFMs) have matured to the point where they can provide rich supervision for world modeling (e.g., tracking, shape completion). 3. Beyond VFMs, many crucial components have come together in recent years: Gaussian splats for rendering, NVIDIA Warp for high-performance simulation, and scene/asset generation from a wide range of labs and companies. The future of 3D world models is looking bright! ✨ 4. The resulting digital twin supports a wide range of downstream applications—especially in data generation and policy evaluation, thanks to its realistic rendering and simulation capabilities. 🎥 All code and data to reproduce the results, along with interactive demos, are available on the website. Check the following visualizations of: (1) observations, (2) reconstructed state/actions, (3) interactive digital twins, and (4) the overlays between real-world robot teleoperation and our model’s open-loop predictions.
0:05

📢 Our lab has been exploring 3D world models for years — and we’re thrilled to share **PhysTwin**: a milestone that reconstructs object appearance, geometry, and dynamics from just a few seconds of interaction! Led by the amazing Hanxiao Jiang 👉 PhysTwin combines **Gaussian splatting** with **inverse dynamics optimization** based on simple **spring-mass** systems. ⚙️ The result? Real-time, action-conditioned 3D video prediction under novel interactions (i.e., 3D world models). 🔑 A few key takeaways: 1. Having the right structure (e.g., particles/masses) helps navigate the trade-off between sample efficiency, generalization, and broad applicability. 2. Visual foundation models (VFMs) have matured to the point where they can provide rich supervision for world modeling (e.g., tracking, shape completion). 3. Beyond VFMs, many crucial components have come together in recent years: Gaussian splats for rendering, NVIDIA Warp for high-performance simulation, and scene/asset generation from a wide range of labs and companies. The future of 3D world models is looking bright! ✨ 4. The resulting digital twin supports a wide range of downstream applications—especially in data generation and policy evaluation, thanks to its realistic rendering and simulation capabilities. 🎥 All code and data to reproduce the results, along with interactive demos, are available on the website. Check the following visualizations of: (1) observations, (2) reconstructed state/actions, (3) interactive digital twins, and (4) the overlays between real-world robot teleoperation and our model’s open-loop predictions.

Yunzhu Li

25,279 次观看 • 1 年前

One of the tallest models in the world from Pakistan getting into his car
0:12

One of the tallest models in the world from Pakistan getting into his car

Historic Vids

11,452,517 次观看 • 2 年前

India can’t be left behind in AI. कृत्रिम has accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!
0:12

India can’t be left behind in AI. कृत्रिम has accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!

Bhavish Aggarwal

379,427 次观看 • 1 年前

Matrix-Game 3.0🔥real-time interactive world models from Skywork ✨ MIT license ✨ 720p @ 40FPS with a 5B model ✨ Minute-long memory consistency ✨ Unreal + AAA + real-world data ✨ Scales up to 28B MoE
0:15

Matrix-Game 3.0🔥real-time interactive world models from Skywork ✨ MIT license ✨ 720p @ 40FPS with a 5B model ✨ Minute-long memory consistency ✨ Unreal + AAA + real-world data ✨ Scales up to 28B MoE

Adina Yakup

43,746 次观看 • 3 个月前