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。

Gemini Robotics 1.5 features a separate reasoning engine (ER), but its VLA model is also capable of thinking due to interleaved reasoning tokens. The VLA is able to independently operate long autonomous sequences (15+ minutes) without aid from the ER/VLM.

The Humanoid Hub

93,163 subscribers

34,214 次观看 • 8 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

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

The Humanoid Hub

65,928 次观看 • 10 个月前

We’re launching the first in a series of Embodied Reasoning offerings: Perceptron Egocentric. It achieves SOTA over the best robotic annotation pipelines built on Gemini 3.5 Flash and Gemini Robotics-ER 1.6. Early access is available to partners.

We’re launching the first in a series of Embodied Reasoning offerings: Perceptron Egocentric. It achieves SOTA over the best robotic annotation pipelines built on Gemini 3.5 Flash and Gemini Robotics-ER 1.6. Early access is available to partners.

Perceptron AI

105,348 次观看 • 17 天前

For an industrial robot built for the rigors of factories and power plants, tidying up a living room may seem like a light day at the office for Spot. Yet, this demonstration represents the promise of AI models in robotics. In this case, Google DeepMind's visual-language model (VLM) Gemini Robotics-ER 1.5 was empowering Spot with embodied reasoning. Go behind the scenes and watch the full demo in our blog:

For an industrial robot built for the rigors of factories and power plants, tidying up a living room may seem like a light day at the office for Spot. Yet, this demonstration represents the promise of AI models in robotics. In this case, Google DeepMind's visual-language model (VLM) Gemini Robotics-ER 1.5 was empowering Spot with embodied reasoning. Go behind the scenes and watch the full demo in our blog:

Boston Dynamics

60,551 次观看 • 3 个月前

VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics. During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos. At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head. The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on NVIDIA Robotics DGX Spark! VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀 Thomas Wolf clem 🤗

VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics. During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos. At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head. The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on NVIDIA Robotics DGX Spark! VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀 Thomas Wolf clem 🤗

LeRobot

318,321 次观看 • 1 个月前

Some great videos from the Gemini VLA release. These kinds of dexterous tasks require tons of coordination and interact with materials that are very hard to model in simulation. Good use of e2e learning and yet more evidence this is the right direction for robotics

Some great videos from the Gemini VLA release. These kinds of dexterous tasks require tons of coordination and interact with materials that are very hard to model in simulation. Good use of e2e learning and yet more evidence this is the right direction for robotics

Chris Paxton

30,949 次观看 • 1 年前

New Episode: Carolina Parada leads the robotics team at Google DeepMind. Carolina believes in a future with a broad, rich ecosystem of diverse robot types, where AI is smart enough to embody any robot. We discuss her journey, advancements in Gemini Robotics 1.5, cross-embodiment transfer, RL versus imitation, humanoids, world models, scaling laws, societal concerns, and more. 1:17 Introduction 1:38 Career journey and inspirations 3:50 Reaction to the 2022 ChatGPT launch 4:53 Google DeepMind's robotics mission 9:13 Key upgrades in Gemini Robotics 1.5 14:06 Agentic system's web usage 15:33 Robotics data-gathering methods 16:57 VLA vs. reasoning model training differences 18:22 Convergence of action and reasoning models 19:35 Cross-embodiment transfer 22:34 Learning directly from humans 24:20 Generalization challenges 27:01 Imitation versus reinforcement learning 28:51 Use of world models in robotics 30:31 Applications and testing of Gemini Robotics 1.5 33:04 Do humanoids deserve special focus? 35:06 Home humanoids timeline & limiting factors 37:19 Scaling laws in robotics versus self-driving 38:46 Value of learning classical robotics approaches 40:38 Ethical issues and societal impact

New Episode: Carolina Parada leads the robotics team at Google DeepMind. Carolina believes in a future with a broad, rich ecosystem of diverse robot types, where AI is smart enough to embody any robot. We discuss her journey, advancements in Gemini Robotics 1.5, cross-embodiment transfer, RL versus imitation, humanoids, world models, scaling laws, societal concerns, and more. 1:17 Introduction 1:38 Career journey and inspirations 3:50 Reaction to the 2022 ChatGPT launch 4:53 Google DeepMind's robotics mission 9:13 Key upgrades in Gemini Robotics 1.5 14:06 Agentic system's web usage 15:33 Robotics data-gathering methods 16:57 VLA vs. reasoning model training differences 18:22 Convergence of action and reasoning models 19:35 Cross-embodiment transfer 22:34 Learning directly from humans 24:20 Generalization challenges 27:01 Imitation versus reinforcement learning 28:51 Use of world models in robotics 30:31 Applications and testing of Gemini Robotics 1.5 33:04 Do humanoids deserve special focus? 35:06 Home humanoids timeline & limiting factors 37:19 Scaling laws in robotics versus self-driving 38:46 Value of learning classical robotics approaches 40:38 Ethical issues and societal impact

The Humanoid Hub

71,481 次观看 • 9 个月前

You have to watch this! For years now, I've been looking for signs of nontrivial zero-shot transfer across seen embodiments. When I saw the Alohas unhang tools from a wall used only on our Frankas I knew we had it! Gemini Robotics 1.5 is the first VLA to achieve such transfer!!

You have to watch this! For years now, I've been looking for signs of nontrivial zero-shot transfer across seen embodiments. When I saw the Alohas unhang tools from a wall used only on our Frankas I knew we had it! Gemini Robotics 1.5 is the first VLA to achieve such transfer!!

Konstantinos Bousmalis

119,825 次观看 • 9 个月前

I ran a quick test of Gemini Robotics ER 1.5 controlling my LeKiwi using the MCP I developed before. No extra code required - just specified a new model. Unfortunately, it doesn't work well, even though I had expected it to be the best, as it is the first major VLM model trained specifically for robotics applications. The video below is a relatively good attempt. It does understand what is going on and generates a reasonable action plan, but it is not doing well with the low-level control. I guess it was not trained for this and was used together with the VLA, so it is trained to generate more high-level commands like "grab this object and put it there" rather than doing low-level control specifying every robot movement step by step. Did anybody try to use it in a similar setup? What is your experience?

I ran a quick test of Gemini Robotics ER 1.5 controlling my LeKiwi using the MCP I developed before. No extra code required - just specified a new model. Unfortunately, it doesn't work well, even though I had expected it to be the best, as it is the first major VLM model trained specifically for robotics applications. The video below is a relatively good attempt. It does understand what is going on and generates a reasonable action plan, but it is not doing well with the low-level control. I guess it was not trained for this and was used together with the VLA, so it is trained to generate more high-level commands like "grab this object and put it there" rather than doing low-level control specifying every robot movement step by step. Did anybody try to use it in a similar setup? What is your experience?

Ilia

15,601 次观看 • 10 个月前

MICROSOFT: "One of Grok 4’s headline features is its first-principles reasoning ability – essentially, the model tries to “think” like a scientist or detective, breaking problems down step by step."

MICROSOFT: "One of Grok 4’s headline features is its first-principles reasoning ability – essentially, the model tries to “think” like a scientist or detective, breaking problems down step by step."

DogeDesigner

19,246 次观看 • 10 个月前

How to train a reasoning model, specifically Magistral from Mistral AI? Here is a quick video walkthrough of the paper.

How to train a reasoning model, specifically Magistral from Mistral AI? Here is a quick video walkthrough of the paper.

Sophia Yang, Ph.D.

31,752 次观看 • 1 年前

llama.cpp is likely the first LLM runtime in the world to allow "interrupt" reasoning without stopping the whole response. We also added a small "skip" button on the Web UI, the model gives the final response as soon as you click the button. The response is no longer bound to reasoning budget!

llama.cpp is likely the first LLM runtime in the world to allow "interrupt" reasoning without stopping the whole response. We also added a small "skip" button on the Web UI, the model gives the final response as soon as you click the button. The response is no longer bound to reasoning budget!

Xuan-Son Nguyen

31,511 次观看 • 1 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

37,184 次观看 • 9 个月前

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:

Turing Post

62,362 次观看 • 6 个月前

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:

NVIDIA DRIVE

35,324 次观看 • 6 个月前

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Affine

14,536 次观看 • 1 个月前

🎃 Halloween is coming. Our hardworking team is lining up for sweet treats, of course, served by Dynasaur! DYNA VLA model now has robust agentic reasoning capability, allowing it to serve arbitrary combinations and counts of candies! Pure imitation learning can’t work given the combinatorially many possibilities. No video edits. Uninterrupted, real-life, as always 🤖 Happy Halloween from DYNA!🍬

🎃 Halloween is coming. Our hardworking team is lining up for sweet treats, of course, served by Dynasaur! DYNA VLA model now has robust agentic reasoning capability, allowing it to serve arbitrary combinations and counts of candies! Pure imitation learning can’t work given the combinatorially many possibilities. No video edits. Uninterrupted, real-life, as always 🤖 Happy Halloween from DYNA!🍬

Dyna Robotics

25,066 次观看 • 8 个月前

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning? Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings. To find out more, watch episode #44 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning? Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings. To find out more, watch episode #44 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

19,627 次观看 • 8 个月前

This is very late, but I'm finally done with my 5.5 vid - use low reasoning - the name sucks - it's fast - best code I've ever seen a model write came from this model - openai's new pre-training is amazing - price looks worse than it is - over sensitive to every little thing in it's context window - feels wildly different compared to 5.4 - turn reasoning off. try it. turn the reasoning off. do it.

This is very late, but I'm finally done with my 5.5 vid - use low reasoning - the name sucks - it's fast - best code I've ever seen a model write came from this model - openai's new pre-training is amazing - price looks worse than it is - over sensitive to every little thing in it's context window - feels wildly different compared to 5.4 - turn reasoning off. try it. turn the reasoning off. do it.

Ben Davis

281,510 次观看 • 2 个月前