正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Ψ₀ ( — an open foundation model for universal humanoid loco-manipulation. 🏆 Outperforms GR00T N1.6 by 40%+ overall success rate 📉 Uses only ~10% of the pre-training data 📦 Fully open-source: model, data, code, and deployment pipeline 1/10

Yue Wang

8,398 subscribers

20,927 次观看 • 4 个月前 •via X (Twitter)

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

NVIDIA announces the first open humanoid robot reference design built for robotics research. The NVIDIA Isaac GR00T Reference Humanoid Robot combines the Unitree H2 humanoid robot, Sharpa Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment. Read the #NVIDIAGTC Taipei announcement:

NVIDIA announces the first open humanoid robot reference design built for robotics research. The NVIDIA Isaac GR00T Reference Humanoid Robot combines the Unitree H2 humanoid robot, Sharpa Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment. Read the #NVIDIAGTC Taipei announcement:

NVIDIA Robotics

169,453 次观看 • 2 个月前

🚀UniWorld: a unified model that skips VAEs and uses semantic features from SigLIP! Using just 1% of BAGEL’s data, it outperforms on image editing and excels in understanding & generation. 🌟Now data, model, training & evaluation script are open-source!

🚀UniWorld: a unified model that skips VAEs and uses semantic features from SigLIP! Using just 1% of BAGEL’s data, it outperforms on image editing and excels in understanding & generation. 🌟Now data, model, training & evaluation script are open-source!

Bin Lin

22,345 次观看 • 1 年前

"Bring me the healthiest snack." The robot goes to the kitchen and gets the snack, fully autonomously. This is the first public demo of NVIDIA's Isaac GR00T N1.6 foundation model presented by Yuke Zhu at CoRL 2025. The previous versions focused only on bimanual stationary manipulation; the N1.6 unlocks the entire kinematic range of the robot. The latest release of the open Isaac GR00T N1.6 VLA model will be available soon on Hugging Face. It integrates with NVIDIA Cosmos Reason, an open, customizable reasoning vision language model that turns vague instructions into step-by-step plans.

"Bring me the healthiest snack." The robot goes to the kitchen and gets the snack, fully autonomously. This is the first public demo of NVIDIA's Isaac GR00T N1.6 foundation model presented by Yuke Zhu at CoRL 2025. The previous versions focused only on bimanual stationary manipulation; the N1.6 unlocks the entire kinematic range of the robot. The latest release of the open Isaac GR00T N1.6 VLA model will be available soon on Hugging Face. It integrates with NVIDIA Cosmos Reason, an open, customizable reasoning vision language model that turns vague instructions into step-by-step plans.

The Humanoid Hub

42,621 次观看 • 10 个月前

✨ Introducing 𝐎𝐩𝐞𝐧𝐕𝐋𝐀 — an open-source vision-language-action model for robotics! 👐 - SOTA generalist policy - 7B params - outperforms Octo, RT-2-X on zero-shot evals 🦾 - trained on 970k episodes from OpenX dataset 🤖 - fully open: model/code/data all online 🤗 🧵👇

✨ Introducing 𝐎𝐩𝐞𝐧𝐕𝐋𝐀 — an open-source vision-language-action model for robotics! 👐 - SOTA generalist policy - 7B params - outperforms Octo, RT-2-X on zero-shot evals 🦾 - trained on 970k episodes from OpenX dataset 🤖 - fully open: model/code/data all online 🤗 🧵👇

Moo Jin Kim

227,044 次观看 • 2 年前

Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗

Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗

NVIDIA Robotics

13,479 次观看 • 6 个月前

Introducing Project Stera by FPV Labs, an open data infra for embodied AI research. Project Stera includes Stera-10M, with 10M+ frames of long-horizon data with persistent state tracking, and an open-source pipeline that converts raw data into training-ready formats.

Introducing Project Stera by FPV Labs, an open data infra for embodied AI research. Project Stera includes Stera-10M, with 10M+ frames of long-horizon data with persistent state tracking, and an open-source pipeline that converts raw data into training-ready formats.

FPV Labs

15,326 次观看 • 3 个月前

Jensen just announced NVIDIA’s Isaac GR00T N1.5 and GR00T-Dreams blueprint at COMPUTEX 2025: ⦿ Isaac GR00T N1.5 is the first update to NVIDIA’s open, generalized, fully customizable foundation model for humanoid reasoning and skills. ⦿ “Human demonstrations aren’t scalable — limited by the number of hours in a day,” said Jensen. The GR00T-Dreams blueprint enables the generation of vast synthetic motion data from single images, accelerating robot behavior learning via compressed action tokens. ⦿ Synthetic training data generated by GR00T-Dreams was used to develop GR00T N1.5 in just 36 hours — what would have taken nearly three months without the blueprint. ⦿ This update significantly improves the foundation model’s success rate for common material handling and manufacturing tasks. GR00T N1.5 can be deployed on Jetson Thor, launching later this year.

Jensen just announced NVIDIA’s Isaac GR00T N1.5 and GR00T-Dreams blueprint at COMPUTEX 2025: ⦿ Isaac GR00T N1.5 is the first update to NVIDIA’s open, generalized, fully customizable foundation model for humanoid reasoning and skills. ⦿ “Human demonstrations aren’t scalable — limited by the number of hours in a day,” said Jensen. The GR00T-Dreams blueprint enables the generation of vast synthetic motion data from single images, accelerating robot behavior learning via compressed action tokens. ⦿ Synthetic training data generated by GR00T-Dreams was used to develop GR00T N1.5 in just 36 hours — what would have taken nearly three months without the blueprint. ⦿ This update significantly improves the foundation model’s success rate for common material handling and manufacturing tasks. GR00T N1.5 can be deployed on Jetson Thor, launching later this year.

The Humanoid Hub

69,557 次观看 • 1 年前

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

Jun Gao

104,664 次观看 • 2 个月前

MolmoAct 2 artifacts have been downloaded 400K+ times in under 1 month. Today we're opening up the full code & training data: everything you need to fine-tune or build on our fully open robotics foundation model. 🧵

MolmoAct 2 artifacts have been downloaded 400K+ times in under 1 month. Today we're opening up the full code & training data: everything you need to fine-tune or build on our fully open robotics foundation model. 🧵

Ai2

17,870 次观看 • 2 个月前

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

kwindla

42,246 次观看 • 1 年前

🚀 1/7 We are thrilled to launch LLM360 — pushing the frontier of open-source & transparent LLMs! Starting with Amber (7B) & CrystalCoder (7B), we are releasing brand new pre-trained LLMs with all training code, data, and up to 360 model checkpoints. 🔗

LLM360

329,499 次观看 • 2 年前

Introducing: Auto Private Model Routing on June Choose Low, Balanced, or High. June picks the right model for every request. Defaults to zero data retention and private models. Powered by Venice. Free to try. Open source. MIT. Try June:

Introducing: Auto Private Model Routing on June Choose Low, Balanced, or High. June picks the right model for every request. Defaults to zero data retention and private models. Powered by Venice. Free to try. Open source. MIT. Try June:

OpenSoftware

111,495 次观看 • 24 天前

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

The Humanoid Hub

20,968 次观看 • 1 年前

New episode: Spencer Huang is a Product Lead for NVIDIA Robotics, focusing on open-source simulation frameworks, synthetic data generation, and robot autonomy. Spencer breaks down RL breakthroughs unlocked by hardware, open-source simulation, synthetic data flywheels, the competitive landscape at the application layer, humanoid use cases, and more. 01:16 Favorite part of Jensen’s keynote 03:37 Sudden unlock of humanoid dance demos 07:17 Sim-to-real RL for manipulation 10:20 Open-source vs. proprietary tools 12:55 How developers can accelerate Cosmos 16:40 Competitive landscape at the application layer 20:57 Humanoids in home and care use cases

New episode: Spencer Huang is a Product Lead for NVIDIA Robotics, focusing on open-source simulation frameworks, synthetic data generation, and robot autonomy. Spencer breaks down RL breakthroughs unlocked by hardware, open-source simulation, synthetic data flywheels, the competitive landscape at the application layer, humanoid use cases, and more. 01:16 Favorite part of Jensen’s keynote 03:37 Sudden unlock of humanoid dance demos 07:17 Sim-to-real RL for manipulation 10:20 Open-source vs. proprietary tools 12:55 How developers can accelerate Cosmos 16:40 Competitive landscape at the application layer 20:57 Humanoids in home and care use cases

The Humanoid Hub

25,006 次观看 • 9 个月前

Introducing the Describe Anything Model (DAM), a powerful Multimodal LLM that generates detailed descriptions for user-specified regions in images or videos using points, boxes, scribbles, or masks. Open-source code, models, demo, data, and benchmark at:

Introducing the Describe Anything Model (DAM), a powerful Multimodal LLM that generates detailed descriptions for user-specified regions in images or videos using points, boxes, scribbles, or masks. Open-source code, models, demo, data, and benchmark at:

Yin Cui

34,990 次观看 • 1 年前

🔥 another win for open source AI SNOWFLAKE ARCTIC: 1] Mixture of Experts model with 128 (!) experts 2] open weights, open code 3] Company is sharing "cookbook" and data and teaching people how to build their own world class MoE models. 4] very cheap model to train (16x times less than Llama 3)

🔥 another win for open source AI SNOWFLAKE ARCTIC: 1] Mixture of Experts model with 128 (!) experts 2] open weights, open code 3] Company is sharing "cookbook" and data and teaching people how to build their own world class MoE models. 4] very cheap model to train (16x times less than Llama 3)

Wes Roth

10,239 次观看 • 2 年前

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

PatronusAI

14,856 次观看 • 1 年前

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 次观看 • 5 个月前

DiT4DiT is now open source! As the first humanoid-deployable Video-Action Model built on a world model, DiT4DiT continues to surprise us. In our paper last month, we showed its strong data efficiency. Now, with only slight modifications, it enables real-time whole-body autonomous pick-and-place. Paper: Code: Website:

DiT4DiT is now open source! As the first humanoid-deployable Video-Action Model built on a world model, DiT4DiT continues to surprise us. In our paper last month, we showed its strong data efficiency. Now, with only slight modifications, it enables real-time whole-body autonomous pick-and-place. Paper: Code: Website:

Shuo Yang

14,534 次观看 • 4 个月前