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 Subtask Annotations in LeRobot Datasets. LeRobot now supports subtasks as a native dataset field, so you can label task progression frame-by-frame, train hierarchical policies, and build stronger reward models with stage-aware supervision. Available today, with an annotation space + tooling to easily add subtasks and high-level dialogue to... show more

LeRobot

17,043 subscribers

16,478 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

Introducing Annotations. Starting today, you can add field notes to your research in Lore with customization options like bold, italics, position, size, and color.

Introducing Annotations. Starting today, you can add field notes to your research in Lore with customization options like bold, italics, position, size, and color.

zehra ✨

12,702 次观看 • 1 个月前

Introducing FoundationMotion. A large-scale, video-derived motion annotation dataset & auto-labeling pipeline + advanced models for motion understanding. Fully open-source: code, datasets, and models, free to use and build on. Understanding motion is core to physical reasoning, yet today’s leading models still struggle with simple spatial actions like “turn right” or “move up” or “flip the toast” - mainly due to the lack of large, fine-grained motion datasets. We present FoundationMotion, a fully automated pipeline that: • detects & tracks objects in videos • extracts trajectories • uses LLMs + frames to generate rich motion captions & QA pairs → creating large-scale, high-quality motion datasets at scale. After fine-tuning the open-source models Qwen and NVILA on our annotations, these models now outperform the closed-source Gemini-3-Flash and GPT-5.1 on spatial understanding tasks across autonomous driving, robotics, and everyday scenarios. 📜Paper: 🌐Webpage: 💻 Code: 🕸️Model: 📊 Dataset: 👉 Interactive Demo: Let’s move research forward together. FoundationMotion is also referred to as Wolf V2 🐺, the second chapter in the Wolf series:

Introducing FoundationMotion. A large-scale, video-derived motion annotation dataset & auto-labeling pipeline + advanced models for motion understanding. Fully open-source: code, datasets, and models, free to use and build on. Understanding motion is core to physical reasoning, yet today’s leading models still struggle with simple spatial actions like “turn right” or “move up” or “flip the toast” - mainly due to the lack of large, fine-grained motion datasets. We present FoundationMotion, a fully automated pipeline that: • detects & tracks objects in videos • extracts trajectories • uses LLMs + frames to generate rich motion captions & QA pairs → creating large-scale, high-quality motion datasets at scale. After fine-tuning the open-source models Qwen and NVILA on our annotations, these models now outperform the closed-source Gemini-3-Flash and GPT-5.1 on spatial understanding tasks across autonomous driving, robotics, and everyday scenarios. 📜Paper: 🌐Webpage: 💻 Code: 🕸️Model: 📊 Dataset: 👉 Interactive Demo: Let’s move research forward together. FoundationMotion is also referred to as Wolf V2 🐺, the second chapter in the Wolf series:

Boyi Li

66,720 次观看 • 6 个月前

Introducing Bambot, an open source, low cost (~$300) humanoid robot. Inspired by LeRobot , so-100 arm and lekiwi

Introducing Bambot, an open source, low cost (~$300) humanoid robot. Inspired by LeRobot , so-100 arm and lekiwi

Tim Qian

192,936 次观看 • 1 年前

🚀 Introducing the Earth Engine Dataset Explorer, powered by Google #Gemini! 🌍✨ Struggling to find the right #geospatial datasets for your research? Our Dataset Explorer recommends tailored datasets and offers an interactive exploration experience. 📹 Check out the video tutorial: 📒 Explore the notebook: #geemap #OpenSource #AI #EarthEngine

🚀 Introducing the Earth Engine Dataset Explorer, powered by Google #Gemini! 🌍✨ Struggling to find the right #geospatial datasets for your research? Our Dataset Explorer recommends tailored datasets and offers an interactive exploration experience. 📹 Check out the video tutorial: 📒 Explore the notebook: #geemap #OpenSource #AI #EarthEngine

Qiusheng Wu

23,929 次观看 • 1 年前

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here:

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here:

Unitree

5,630,260 次观看 • 3 个月前

(1/2) Introducing annotations in Mixboard! With the annotations tool, you can doodle directly on your board to add or edit elements. Just mark the area, describe it, and watch it appear.

(1/2) Introducing annotations in Mixboard! With the annotations tool, you can doodle directly on your board to add or edit elements. Just mark the area, describe it, and watch it appear.

Google Labs

60,516 次观看 • 7 个月前

We're introducing EnvHub to LeRobot! Upload simulation environments to the @hugginigface hub, and load them in lerobot, with one line of code ! env = lerobot.make_env("username/my-env", trust_remote_code=True) Back in 2017, OpenAI called on the community to build Gym environments. Today, we're doing the same for robotics. We're calling researchers, students, hobbyists, labs, and startups to publish complex envs, tasks, and benchmarks on the Hub, so we see how robot policies perform. (in Isaaac, Mujoco, Genesis, etc..) Fill out and submit the form linked in the comments to join the effort!

We're introducing EnvHub to LeRobot! Upload simulation environments to the @hugginigface hub, and load them in lerobot, with one line of code ! env = lerobot.make_env("username/my-env", trust_remote_code=True) Back in 2017, OpenAI called on the community to build Gym environments. Today, we're doing the same for robotics. We're calling researchers, students, hobbyists, labs, and startups to publish complex envs, tasks, and benchmarks on the Hub, so we see how robot policies perform. (in Isaaac, Mujoco, Genesis, etc..) Fill out and submit the form linked in the comments to join the effort!

jade

43,147 次观看 • 7 个月前

We're developing a native LeRobot data loader. It's a work in progress because the datasets vary greatly, but it's starting to be useful. Try it out with the latest 0.22.1 release! If you encounter any snags, let us know so we can resolve them quickly. cc Remi Cadene

We're developing a native LeRobot data loader. It's a work in progress because the datasets vary greatly, but it's starting to be useful. Try it out with the latest 0.22.1 release! If you encounter any snags, let us know so we can resolve them quickly. cc Remi Cadene

Rerun

23,899 次观看 • 1 年前

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset:

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset:

AK

10,551 次观看 • 3 个月前

Introducing AI fashion Photoshoots on Flair AI you can now train fashion models on your clothing with incredible accuracy - texture, labels, logos, and more preserved with midjourney level quality 🔥 rt and comment to try this feature in beta. serving access codes today:)

Introducing AI fashion Photoshoots on Flair AI you can now train fashion models on your clothing with incredible accuracy - texture, labels, logos, and more preserved with midjourney level quality 🔥 rt and comment to try this feature in beta. serving access codes today:)

mickey friedman

298,017 次观看 • 1 年前

Introducing Composer Actions - Developers can now build apps that modify new casts - Create a bounty, a poll or an event and automatically generate a frame - Developers build ongoing relationships with users in an app they already have and use everyday

Introducing Composer Actions - Developers can now build apps that modify new casts - Create a bounty, a poll or an event and automatically generate a frame - Developers build ongoing relationships with users in an app they already have and use everyday

Dan Romero

49,122 次观看 • 1 年前

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Unsloth AI

1,687,971 次观看 • 3 个月前

💡Why Vana? “Ultimately, AI models are only as good as their training data. So if you want to build the best AI, you need the best data.” shares the vision behind Vana’s mission, centered on DataDAOs that aggregate specific datasets, reward data owners for their contributions and level up AI models with high-quality data🏆

💡Why Vana? “Ultimately, AI models are only as good as their training data. So if you want to build the best AI, you need the best data.” shares the vision behind Vana’s mission, centered on DataDAOs that aggregate specific datasets, reward data owners for their contributions and level up AI models with high-quality data🏆

vana

108,354 次观看 • 1 年前

Welcome to the CORSAIR FRAME 5000D! Assemble with ease and showcase your build in our new stunning mid-tower PC case. Available in EU now ⤵

Welcome to the CORSAIR FRAME 5000D! Assemble with ease and showcase your build in our new stunning mid-tower PC case. Available in EU now ⤵

CORSAIR

228,837 次观看 • 11 个月前

Did you know that in Blender you can easily create a turntable animation with a single driver expression?✨ 1. Make an empty 2. Parent your camera to it 3. In the empty's Z rotation field write "# frame / 300 * pi * 2", where 300 is your final frame 4. Enjoy the loop! #b3d

Did you know that in Blender you can easily create a turntable animation with a single driver expression?✨ 1. Make an empty 2. Parent your camera to it 3. In the empty's Z rotation field write "# frame / 300 * pi * 2", where 300 is your final frame 4. Enjoy the loop! #b3d

passivestar

57,761 次观看 • 3 年前

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Matt Shumer

337,408 次观看 • 2 年前

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Matt Shumer

383,130 次观看 • 2 年前

Sydnie has a new addition to her kitchen with the Skylight Frame. Now her family and friends can add their favorite photos to her frame no matter where they are.

Sydnie has a new addition to her kitchen with the Skylight Frame. Now her family and friends can add their favorite photos to her frame no matter where they are.

Viva La Stool

810,069 次观看 • 6 个月前

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

William J.B. Mattingly

21,466 次观看 • 1 年前

Ray2 Keyframes, Extend & Loop is now here. Create your visual story with precise frame-by-frame control, seamless transitions, spatial exploration and long-form video durations using #Ray2 Text-to-Video and Image-to-Video models in Dream Machine.

Ray2 Keyframes, Extend & Loop is now here. Create your visual story with precise frame-by-frame control, seamless transitions, spatial exploration and long-form video durations using #Ray2 Text-to-Video and Image-to-Video models in Dream Machine.

Luma

7,362,289 次观看 • 1 年前