Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing MolmoSpaces, a large-scale, fully open platform + benchmark for embodied AI research. 🤖 230k+ indoor scenes, 130k+ object models, & 42M annotated robotic grasps—all in one ecosystem.

allen_ai's profile picture

Ai2

86,169 subscribers

98,468 Aufrufe • vor 7 Monaten •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

15 Kommentare

Profilbild von kache
kachevor 7 Monaten

i have been using procthor to great effect. thank you for your service

Profilbild von Ai2
Ai2vor 7 Monaten

The next wave of AI will act in the physical world, but building robots that generalize across new environments – rather than replaying learned behaviors – requires far more diverse training data than exists today. That's where MolmoSpaces comes in.

Profilbild von Ai2
Ai2vor 7 Monaten

MolmoSpaces builds on two foundations: Objaverse, one of the largest open collections of 3D objects, and our THOR family of interactive simulation environments, all unified with physics-grounded simulation + validated physical parameters tuned for realistic manipulation. ⚙️

Profilbild von Ai2
Ai2vor 7 Monaten

MolmoSpaces ships with a massive bank of validated grasps for rigid and articulated objects, loadable directly into environments. An accompanying trajectory-generation pipeline supports reproducible demonstrations and imitation learning at scale.

Profilbild von Ai2
Ai2vor 7 Monaten

📐 MolmoSpaces-Bench is our new benchmark for evaluating generalist policies under systematic, controlled variation. Researchers can vary one factor at a time – from object properties to layouts, dynamics, and instruction phrasing – across thousands of realistic scenes.

Profilbild von Ai2
Ai2vor 7 Monaten

MolmoSpaces supports teleoperation via mobile platforms like Teledex—collect demonstrations right from your phone, compatible with all our embodiment setups, including DROID and CAP; no extra configuration is needed.

Profilbild von Ai2
Ai2vor 7 Monaten

All MolmoSpaces assets, scenes, & tools are open + modular, provided in MJCF with USD conversion for cross-simulator portability. Plug in new embodiments, regenerate grasps, & run across MuJoCo, ManiSkill, & NVIDIA Isaac Lab/Sim.

Profilbild von Ai2
Ai2vor 7 Monaten

Explore MolmoSpaces & start building: 📝 Blog: 💻 Demo: ⬇️ Code: 📊 Data: ✍️ Paper:

Profilbild von Shivaram Kumar
Shivaram Kumarvor 7 Monaten

This is awesome work! Curious—any plans to integrate SceneSmith-like agentic scene generation into MolmoSpaces? It feels like a natural combo: MolmoSpaces benchmark + SceneSmith prompt-to-sim scenes = infinite evaluation distribution.

Profilbild von 株式会社WEEL(ウィール)｜生成AI導入・開発
株式会社WEEL(ウィール)｜生成AI導入・開発vor 7 Monaten

凄いですね！めちゃくちゃロボット研究が進みそう！広めさせていただきました！

Profilbild von Tool Side Room
Tool Side Roomvor 7 Monaten

MolmoSpaces just turned embodied AI into an absolute playground

Profilbild von Kevin H. Zhao
Kevin H. Zhaovor 7 Monaten

AHHHHHH

Profilbild von Everlier
Everliervor 7 Monaten

I can imagine how this paired with some skinning can be an absolute goldmine for RL.

Profilbild von Eddie
Eddievor 7 Monaten

free? sure, until they find a way to monetize your data. local means nothing when they own the code.

Profilbild von AI Integrity Alliance (AI²)
AI Integrity Alliance (AI²)vor 7 Monaten

This is cool research but we have the best ai2 domain!

Ähnliche Videos

🤖 NEW: TetherIA has launched the Aero Hand Open, a $314 open-source robotic hand built for embodied AI research.
2:12

🤖 NEW: TetherIA has launched the Aero Hand Open, a $314 open-source robotic hand built for embodied AI research.

Cointelegraph

27,651 Aufrufe • vor 3 Monaten

We built a fully open-source dexterous robotic hand — for just $314. 🤖 Meet Aero Hand Open — precise, affordable, and built for embodied AI research. Watch it perform natural finger motions 👇 🔗 📘 Docs: 💻 GitHub: #robotics #opensource #AI #dexteroushand #embodiedAI
0:29

We built a fully open-source dexterous robotic hand — for just $314. 🤖 Meet Aero Hand Open — precise, affordable, and built for embodied AI research. Watch it perform natural finger motions 👇 🔗 📘 Docs: 💻 GitHub: #robotics #opensource #AI #dexteroushand #embodiedAI

Chestnut Robotics

58,061 Aufrufe • vor 11 Monaten

🤖Introducing RoboNet 2.0 🤖 A platform for the next generation of AI agents, actively competing in a live financial ecosystem leveraging Allora's collective intelligence. A new era of personality-rich, capital-deploying AI agents begins.
0:33

🤖Introducing RoboNet 2.0 🤖 A platform for the next generation of AI agents, actively competing in a live financial ecosystem leveraging Allora's collective intelligence. A new era of personality-rich, capital-deploying AI agents begins.

RoboNet

65,961 Aufrufe • vor 1 Jahr

📢Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.
0:29

📢Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.

Kaggle

114,176 Aufrufe • vor 1 Jahr

1/ Introducing ᴏᴘᴇɴꜱᴄʜᴏʟᴀʀ: a retrieval-augmented LM to help scientists synthesize knowledge 📚 UW NLP Ai2 With open models & 45M-paper datastores, it outperforms proprietary systems & match human experts. Try out our demo! We also introduce ꜱᴄʜᴏʟᴀʀQᴀʙᴇɴᴄʜ, a new large-scale multi-domain benchmark for scientific research synthesis, covering CS, Bio and Physics.
2:29

1/ Introducing ᴏᴘᴇɴꜱᴄʜᴏʟᴀʀ: a retrieval-augmented LM to help scientists synthesize knowledge 📚 UW NLP Ai2 With open models & 45M-paper datastores, it outperforms proprietary systems & match human experts. Try out our demo! We also introduce ꜱᴄʜᴏʟᴀʀQᴀʙᴇɴᴄʜ, a new large-scale multi-domain benchmark for scientific research synthesis, covering CS, Bio and Physics.

Akari Asai

249,723 Aufrufe • vor 1 Jahr

Introducing AI Voice Agents: The All-In-One Platform for Voice AI Agents and Everything Audio! 🎙 Build conversational agents, clone voices, generate sounds & engage like never before 🤖 DEMO IS LIVE: 🌱 Start farming & earn rewards!
0:54

Introducing AI Voice Agents: The All-In-One Platform for Voice AI Agents and Everything Audio! 🎙 Build conversational agents, clone voices, generate sounds & engage like never before 🤖 DEMO IS LIVE: 🌱 Start farming & earn rewards!

AI Voice Agents | AIVA

95,603 Aufrufe • vor 1 Jahr

Open-Source Robotic Hand That Costs Just $300. California-based company TetherIA.ai has officially launched its open-source robotic hand, the Aero Hand Open. Designed to be the most capable at the lowest cost, this hand is a new tool for embodied AI research. In the clip, it demonstrates impressive dexterity by grasping an M5 screw, picking up an iPhone, and opening a soda can. Key Features: ► Price: $314.00 ► Open Source: CAD, electronics, and firmware are all open source. ► Actuation: 7 Active Degrees of Freedom (16 joints) with a tendon-driven design. ► Weight: Under 400 grams. ► Purpose: Built for embodied AI research to make dexterous manipulation accessible to all. For more details and to purchase:
2:12

Open-Source Robotic Hand That Costs Just $300. California-based company TetherIA.ai has officially launched its open-source robotic hand, the Aero Hand Open. Designed to be the most capable at the lowest cost, this hand is a new tool for embodied AI research. In the clip, it demonstrates impressive dexterity by grasping an M5 screw, picking up an iPhone, and opening a soda can. Key Features: ► Price: $314.00 ► Open Source: CAD, electronics, and firmware are all open source. ► Actuation: 7 Active Degrees of Freedom (16 joints) with a tendon-driven design. ► Weight: Under 400 grams. ► Purpose: Built for embodied AI research to make dexterous manipulation accessible to all. For more details and to purchase:

RoboHub🤖

45,830 Aufrufe • vor 1 Jahr

Can robots self-improve by collecting data autonomously🤖? Introducing SOAR: a system for large-scale autonomous data collection 🚀 and autonomous improvement📈of a multi-task language-conditioned policy in diverse scenes without human interventions .
1:36

Can robots self-improve by collecting data autonomously🤖? Introducing SOAR: a system for large-scale autonomous data collection 🚀 and autonomous improvement📈of a multi-task language-conditioned policy in diverse scenes without human interventions .

Paul Zhou

47,729 Aufrufe • vor 2 Jahren

📢 OPEN AGENTS 🤖⚡️ A new video series in which we build an open platform for AI agents. ✅ 100% open-source ✅ Open models & data ✅ Open compute via GPUtopia ✅ Open money aka #bitcoin ✅ Open agent marketplace with rev-share ⚡️ Follow along 👉
2:32

📢 OPEN AGENTS 🤖⚡️ A new video series in which we build an open platform for AI agents. ✅ 100% open-source ✅ Open models & data ✅ Open compute via GPUtopia ✅ Open money aka #bitcoin ✅ Open agent marketplace with rev-share ⚡️ Follow along 👉

OpenAgents

594,276 Aufrufe • vor 2 Jahren

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:
1:17

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

OpenBMB

330,472 Aufrufe • vor 2 Monaten

Scale your generations with BudgetPixel API & MCP. Access a large selection of image, video, music, and SFX models through one platform, then use them for bulk generation workflows without managing separate integrations.
0:32

Scale your generations with BudgetPixel API & MCP. Access a large selection of image, video, music, and SFX models through one platform, then use them for bulk generation workflows without managing separate integrations.

BudgetPixel AI

67,740 Aufrufe • vor 18 Tagen

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.
0:22

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,646 Aufrufe • vor 1 Jahr

Introducing Pane a fully open-source windows tray app that tracks all your AI subscriptions in one place one of a kind app out there right now try it out 👇
0:29

Introducing Pane a fully open-source windows tray app that tracks all your AI subscriptions in one place one of a kind app out there right now try it out 👇

J A Z I I

31,160 Aufrufe • vor 2 Monaten

The time has come 🔥 We're thrilled to announce the Beta version of our SōzōAI App! Just a simple prompt to trade, research or create your own AI agents - $SOAI is the first all-in-one AI platform. Free and fully open-source, try it now 🔽
0:26

The time has come 🔥 We're thrilled to announce the Beta version of our SōzōAI App! Just a simple prompt to trade, research or create your own AI agents - $SOAI is the first all-in-one AI platform. Free and fully open-source, try it now 🔽

SōzōAI

119,169 Aufrufe • vor 1 Jahr

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.
1:05

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

239,092 Aufrufe • vor 23 Tagen

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications. Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: The Genesis physics engine and simulation platform is fully open source at We'll gradually roll out access to our generative framework in the near future. Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism. We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications. Open Source Code: Project webpage: Documentation: 1/n
3:26

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications. Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: The Genesis physics engine and simulation platform is fully open source at We'll gradually roll out access to our generative framework in the near future. Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism. We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications. Open Source Code: Project webpage: Documentation: 1/n

Zhou Xian

3,822,134 Aufrufe • vor 1 Jahr

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at
0:34

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Yuke Zhu

141,540 Aufrufe • vor 2 Jahren

Introducing A Branding New ComfyUI Look and Native API Nodes! Seamlessly integrate 11 amazing online visual AI models into ComfyUI, including BlackForestLabsAI - Unofficial Flux, MiniMax Design (H3), , Kling AI, Luma, , Recraft, Stability AI, Google Veo2, Ideogram, OpenAI GPT image-1, and Pika! 🔹One platform, 11 models, 65 nodes, all at once 🔹Chain the APIs with open models and workflows 🔹No hardware limitation!
1:26

Introducing A Branding New ComfyUI Look and Native API Nodes! Seamlessly integrate 11 amazing online visual AI models into ComfyUI, including BlackForestLabsAI - Unofficial Flux, MiniMax Design (H3), , Kling AI, Luma, , Recraft, Stability AI, Google Veo2, Ideogram, OpenAI GPT image-1, and Pika! 🔹One platform, 11 models, 65 nodes, all at once 🔹Chain the APIs with open models and workflows 🔹No hardware limitation!

ComfyUI

187,649 Aufrufe • vor 1 Jahr

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:
1:25

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

67,623 Aufrufe • vor 9 Monaten