Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Gemini Robotics model is able to generalize to tasks it has never seen before in training.

TheHumanoidHub's profile picture

The Humanoid Hub

50,675 subscribers

34,691 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieNachrichten & Politik
LIVE

Anya Rossi• Live Now

Private livecam show

4 Kommentare

Profilbild von /
/vor 1 Jahr

The first example (wiping the whiteboard) shows that it lacks understanding of contact forces, typical of current VLA models. Might improve with tactile sensors.

Profilbild von MightyBot
MightyBotvor 1 Jahr

🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

Profilbild von NEO
NEOvor 1 Jahr

@elder_plinius liberate this

Profilbild von William Selby
William Selbyvor 1 Jahr

Now this is cool!

Ähnliche Videos

So Google has just released the best model in the world?! Gemini 3.1 Pro is already available in: → Gemini App → Antigravity → Google AI Studio And it has insane capabilities when it comes to complex tasks and coding! (Roughly 2x cheaper than Opus 4.6 btw)
0:25

So Google has just released the best model in the world?! Gemini 3.1 Pro is already available in: → Gemini App → Antigravity → Google AI Studio And it has insane capabilities when it comes to complex tasks and coding! (Roughly 2x cheaper than Opus 4.6 btw)

Paul Couvert

39,652 Aufrufe • vor 4 Monaten

"America is going to reach heights that it has never seen before." Elon Musk
1:26

"America is going to reach heights that it has never seen before." Elon Musk

Tesla Owners Silicon Valley

1,563,136 Aufrufe • vor 1 Jahr

Google DeepMind announces Gemini Robotics On-Device - an efficient VLA model optimized to run locally with low-latency inference. It enables general-purpose dexterity, adapts to new tasks or robot hardware with fewer than 100 demos.
0:31

Google DeepMind announces Gemini Robotics On-Device - an efficient VLA model optimized to run locally with low-latency inference. It enables general-purpose dexterity, adapts to new tasks or robot hardware with fewer than 100 demos.

The Humanoid Hub

46,528 Aufrufe • vor 1 Jahr

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.
0:20

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Google AI Developers

1,296,440 Aufrufe • vor 5 Monaten

ELON MUSK: "America is going to reach heights that it has never seen before. The future is going to be amazing."
0:23

ELON MUSK: "America is going to reach heights that it has never seen before. The future is going to be amazing."

DogeDesigner

460,668 Aufrufe • vor 1 Jahr

Gemini in Android Studio's Agent Mode is your coding partner for complex tasks, and is able to dive into your codebase to answer your questions and make changes. Try it today in the latest stable release →
0:29

Gemini in Android Studio's Agent Mode is your coding partner for complex tasks, and is able to dive into your codebase to answer your questions and make changes. Try it today in the latest stable release →

Android Studio

17,428 Aufrufe • vor 10 Monaten

Shenzhen Astribot released an end-to-end VLA: Duocore, which enables the humanoid robot S1 to respond to tasks in complex and uncertain environments in real time. Even if it is disturbed and replaced with tools it has never seen before, it can still complete the task flexibly. The real-time adaptability is enhanced, and the ability to cope with random and uncertain demand tasks is enhanced, especially in the field of home and nursing.
1:30

Shenzhen Astribot released an end-to-end VLA: Duocore, which enables the humanoid robot S1 to respond to tasks in complex and uncertain environments in real time. Even if it is disturbed and replaced with tools it has never seen before, it can still complete the task flexibly. The real-time adaptability is enhanced, and the ability to cope with random and uncertain demand tasks is enhanced, especially in the field of home and nursing.

CyberRobo

11,628 Aufrufe • vor 1 Jahr

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵
0:27

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

Google DeepMind

552,845 Aufrufe • vor 2 Monaten

gemini just one shotted this entire landing page 🤯 never has an ai model been able to design a startup landing page like this prompt below 👇
0:57

gemini just one shotted this entire landing page 🤯 never has an ai model been able to design a startup landing page like this prompt below 👇

Klaas

213,610 Aufrufe • vor 7 Monaten

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.
1:42

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 Aufrufe • vor 9 Monaten

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.
1:58

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

34,214 Aufrufe • vor 7 Monaten

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
0:33

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 Aufrufe • vor 1 Jahr

Super excited to announce SIMA 2! It’s a general agent that can understand & reason about complex instructions and complete tasks in simulated game worlds, even ones it has never seen before. Incredible to see how it can learn just from self-play… a crucial step towards AGI
1:37

Super excited to announce SIMA 2! It’s a general agent that can understand & reason about complex instructions and complete tasks in simulated game worlds, even ones it has never seen before. Incredible to see how it can learn just from self-play… a crucial step towards AGI

Demis Hassabis

154,038 Aufrufe • vor 7 Monaten

NVIDIA Isaac GR00T N1 is an open generalist foundation model for #humanoidrobots. 🤖 Discover how the model can easily generalize common tasks, boosting robot reasoning and skills. ▶️
0:30

NVIDIA Isaac GR00T N1 is an open generalist foundation model for #humanoidrobots. 🤖 Discover how the model can easily generalize common tasks, boosting robot reasoning and skills. ▶️

NVIDIA Robotics

53,401 Aufrufe • vor 1 Jahr

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵
0:35

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

Google DeepMind

819,292 Aufrufe • vor 1 Jahr

A new robot policy just cleaned up a kitchen it had never seen before [watch what happens. paper included ⬇️] Pi-0.5 builds on top of Pi-0 and shows how smart co-training with diverse data can unlock real generalization in the home. It doesn’t just learn from one setup but adapts to many, including homes it’s never seen. What it does ✅ Handles new homes without training in them ✅ Follows complex language instructions ✅ Cleans, places dishes, handles spills ✅ Matches in-home training models using cross-embodiment and web data Robots that understand tasks and adapt to new spaces are finally within reach. More in the blog: Read the paper ⬇️ Physical Intelligence, co-founded by UC Berkeley professor Sergey Levine, is a robotics startup developing general-purpose AI foundation models that enable robots to perform a wide variety of real-world tasks with human-like adaptability, recently raising $400 million to advance this vision.
1:22

A new robot policy just cleaned up a kitchen it had never seen before [watch what happens. paper included ⬇️] Pi-0.5 builds on top of Pi-0 and shows how smart co-training with diverse data can unlock real generalization in the home. It doesn’t just learn from one setup but adapts to many, including homes it’s never seen. What it does ✅ Handles new homes without training in them ✅ Follows complex language instructions ✅ Cleans, places dishes, handles spills ✅ Matches in-home training models using cross-embodiment and web data Robots that understand tasks and adapt to new spaces are finally within reach. More in the blog: Read the paper ⬇️ Physical Intelligence, co-founded by UC Berkeley professor Sergey Levine, is a robotics startup developing general-purpose AI foundation models that enable robots to perform a wide variety of real-world tasks with human-like adaptability, recently raising $400 million to advance this vision.

Ilir Aliu - eu/acc

18,120 Aufrufe • vor 1 Jahr

Lawfare in America has reached levels never before seen No one is stopping what is coming It is not time to believe the drama. Its time to lock in for our allies in this fight against the zionist lobby
3:33

Lawfare in America has reached levels never before seen No one is stopping what is coming It is not time to believe the drama. Its time to lock in for our allies in this fight against the zionist lobby

Bleau Jackson

22,651 Aufrufe • vor 2 Monaten

We're also launching the Gemini Robotics software development kit (SDK) to help developers fine-tune the model for their own applications, including by testing it in the MuJoCo physics simulator. 🌐
0:23

We're also launching the Gemini Robotics software development kit (SDK) to help developers fine-tune the model for their own applications, including by testing it in the MuJoCo physics simulator. 🌐

Google DeepMind

34,238 Aufrufe • vor 1 Jahr