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。

Today, we are introducing RFM-1, our Robotics Foundation Model giving robots human-like reasoning capabilities.

Covariant

11,628 subscribers

118,348 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Covariant 的头像

Covariant2 年前

RFM-1 is a Robotics Foundation Model trained on a vast amount of multimodal data rich in physical real-world interactions and general internet data.

Covariant 的头像

Covariant2 年前

This repersents a remarkable leap forward toward building generalized AI models that can accurately simulate and operate in the demanding conditions of the physical world, like warehouse environments.

Ben Holfeld 的头像

Ben Holfeld2 年前

Exciting to see the new world of robotics unfold @pabbeel

Roland Fernandez 的头像

Roland Fernandez2 年前

@ashah0052 Sounds fantastic. What’s the release model for this? Will a local model version be available?

Oana Olteanu 的头像

Oana Olteanu2 年前

Super cool

Chief AI Officer 的头像

Chief AI Officer2 年前

is this the first any-any model?

Aayush Deshmukh 的头像

Aayush Deshmukh2 年前

This is so cool….. Covariant is one of the most underrated robotics startup for sure

Prashant Rai 的头像

Prashant Rai2 年前

Wow!

PDFgear 的头像

PDFgear2 年前

Is it you? Dum-E?

Superintelligent: Useful AI Tutorials 的头像

Superintelligent: Useful AI Tutorials2 年前

This is next-level innovation! How will RFM-1 adapt to diverse environments beyond warehouses?

相关视频

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Jiafei Duan

48,773 次观看 • 1 年前

Meet Helix, our in-house AI that reasons like a human Robotics won't get to the home without a step change in capabilities Our robots can now handle virtually any household item:

Meet Helix, our in-house AI that reasons like a human Robotics won't get to the home without a step change in capabilities Our robots can now handle virtually any household item:

Figure

1,781,839 次观看 • 1 年前

SITUATION ANALYSIS: Everyone assumes the humanoid robotics race will be won by whoever builds the best foundation model. FleetingBits says that's exactly backwards. "The long run winners [in humanoid robotics] are people who make the robots cheaply, not those training the models." "That's the total opposite of the reasoning model world, where there are increasing returns to intelligence, and Foundation Labs are very well-positioned."

SITUATION ANALYSIS: Everyone assumes the humanoid robotics race will be won by whoever builds the best foundation model. FleetingBits says that's exactly backwards. "The long run winners [in humanoid robotics] are people who make the robots cheaply, not those training the models." "That's the total opposite of the reasoning model world, where there are increasing returns to intelligence, and Foundation Labs are very well-positioned."

MTS

16,194 次观看 • 1 个月前

Yes, 2024 is shaping up a big year for robotics! Introducing Covariant's RFM-1, which just like Sora can generate video, but RFM-1 does it for robotic interaction with the world. But there is so much more it can do. RFM-1 is a multimodal any-to-any sequence model. RFM-1 tokenizes 5 modalities: video, keyframes, text, sensory readings, robot actions. Any-to-any means RFM-1 can handle any subset on the input and any subset on the output.

Yes, 2024 is shaping up a big year for robotics! Introducing Covariant's RFM-1, which just like Sora can generate video, but RFM-1 does it for robotic interaction with the world. But there is so much more it can do. RFM-1 is a multimodal any-to-any sequence model. RFM-1 tokenizes 5 modalities: video, keyframes, text, sensory readings, robot actions. Any-to-any means RFM-1 can handle any subset on the input and any subset on the output.

Pieter Abbeel

167,056 次观看 • 2 年前

Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇

Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇

Generalist

484,055 次观看 • 8 个月前

Reasoning is central to purposeful action. Today we introduce MolmoAct — a fully open Action Reasoning Model (ARM) for robotics. Grounded in large-scale pre-training with action reasoning data, every predicted action is interpretable and user-steerable via visual trace. We are open-sourcing everything!

Reasoning is central to purposeful action. Today we introduce MolmoAct — a fully open Action Reasoning Model (ARM) for robotics. Grounded in large-scale pre-training with action reasoning data, every predicted action is interpretable and user-steerable via visual trace. We are open-sourcing everything!

Jiafei Duan

99,944 次观看 • 11 个月前

Can we bring human-like Touch to robots🤖? Introducing our CoRL work on 3D-ViTac. Humans rely on both vision 👁️ and touch 🫳 for complex tasks. With combined visual-tactile sensing, robots can now tackle challenging tasks, like precise in-hand reorientation, fragile objects grasping. Website: #Robotics #CoRL2024 #Touch #tactile #AI #ML

Can we bring human-like Touch to robots🤖? Introducing our CoRL work on 3D-ViTac. Humans rely on both vision 👁️ and touch 🫳 for complex tasks. With combined visual-tactile sensing, robots can now tackle challenging tasks, like precise in-hand reorientation, fragile objects grasping. Website: #Robotics #CoRL2024 #Touch #tactile #AI #ML

Binghao Huang

49,544 次观看 • 1 年前

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵

Google DeepMind

642,430 次观看 • 1 年前

Introducing The Largest Organized and Incentivized Human-Data Fleet for General-Purpose Humanoid-Robotics and large language model training Our users are creators that complete daily data quests with crypto incentives through our Mobile App 🧵

Introducing The Largest Organized and Incentivized Human-Data Fleet for General-Purpose Humanoid-Robotics and large language model training Our users are creators that complete daily data quests with crypto incentives through our Mobile App 🧵

Mecka

385,649 次观看 • 2 年前

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Jason Ma

519,363 次观看 • 1 年前

Today, we shared evals for an early version of the next model in our o-model reasoning series: OpenAI o3

Today, we shared evals for an early version of the next model in our o-model reasoning series: OpenAI o3

OpenAI

1,669,037 次观看 • 1 年前

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.

Robots Digest 🤖

14,663 次观看 • 1 个月前

"We are not trying to rebuild a human; we are not doing biomimicry," Agility Robotics' CEO Peggy Johnson discusses the reliance on human-centric robots in environments built for humans with Brad Stone at #BloombergTech.

"We are not trying to rebuild a human; we are not doing biomimicry," Agility Robotics' CEO Peggy Johnson discusses the reliance on human-centric robots in environments built for humans with Brad Stone at #BloombergTech.

Bloomberg Live

30,792 次观看 • 1 年前

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

Jiafei Duan

108,164 次观看 • 2 个月前

Fundamental spatial and temporal understanding is the bedrock upon which robots will learn motor control. These types of Embodied Reasoning capabilities enable policy learning but also inference abilities like image or video conditioning. We just released a new SOTA ER model!

Fundamental spatial and temporal understanding is the bedrock upon which robots will learn motor control. These types of Embodied Reasoning capabilities enable policy learning but also inference abilities like image or video conditioning. We just released a new SOTA ER model!

Ted Xiao

35,893 次观看 • 9 个月前

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

Genesis AI

2,714,137 次观看 • 2 个月前

🤖WE HUMANS ARE TRAINING OUR AI REPLACEMENTS Humanoid robots are learning by watching humans work. Workers wear devices that capture egocentric data, showing robots exactly how tasks look from a human perspective. We are not just building robots. We are handing them our job's playbook.

🤖WE HUMANS ARE TRAINING OUR AI REPLACEMENTS Humanoid robots are learning by watching humans work. Workers wear devices that capture egocentric data, showing robots exactly how tasks look from a human perspective. We are not just building robots. We are handing them our job's playbook.

Coin Bureau

20,173 次观看 • 1 个月前

1/ We are speed running industrial robotics. It took us just 19 days from the first day of data collection to filming a 2.5-hour continuous run of our model autonomously breaking down industrial containers — zero human intervention. The data efficiency of our DVA model is fundamentally changing how fast we bring robots out of the lab and into the factory. Autonomous operation with 3 hours of data collection at a customer factory.

1/ We are speed running industrial robotics. It took us just 19 days from the first day of data collection to filming a 2.5-hour continuous run of our model autonomously breaking down industrial containers — zero human intervention. The data efficiency of our DVA model is fundamentally changing how fast we bring robots out of the lab and into the factory. Autonomous operation with 3 hours of data collection at a customer factory.

Rhoda AI

25,517 次观看 • 3 个月前

🔷 Introducing Rig3R - our new geometric foundation model for 3D perception in AVs.

🔷 Introducing Rig3R - our new geometric foundation model for 3D perception in AVs.

Wayve

39,671 次观看 • 9 个月前