Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Eric Jang explains that 1X's world model is a video generation model at its core, but had to be retrained from scratch to make it action-controllable. He also notes that simulated people in the world model might eventually pass the Turing test.

TheHumanoidHub's profile picture

The Humanoid Hub

66,750 subscribers

62,767 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

2 Kommentare

Profilbild von The Humanoid Hub
The Humanoid Hubvor 1 Jahr

Full interview with @ericjang11, diving into 1X’s comprehensive AI approach for humanoids:

Profilbild von Nev (unsupervised)
Nev (unsupervised)vor 1 Jahr

I think he was being modest about simulations passing the Turing Test

Ähnliche Videos

Attention: this might be the video that opens the door to the future. When a SOTA agent model connects to a robot dog with no remote control— MiniMax M2.1 × Vbot, super-powered in action. A model trained in the virtual world now controls a robot in the physical world. Hello, humans. Welcome to the future.
0:49

Attention: this might be the video that opens the door to the future. When a SOTA agent model connects to a robot dog with no remote control— MiniMax M2.1 × Vbot, super-powered in action. A model trained in the virtual world now controls a robot in the physical world. Hello, humans. Welcome to the future.

MiniMax (official)

151,672 Aufrufe • vor 6 Monaten

📁 Yann LeCun, Chief AI Scientist at Meta, says many people misunderstand what a world model really is. He explains that it is not about reproducing the world in full detail like a visual simulator. He warns that generating video may look impressive, but it does not guarantee the system has learned the underlying dynamics of reality.
0:48

📁 Yann LeCun, Chief AI Scientist at Meta, says many people misunderstand what a world model really is. He explains that it is not about reproducing the world in full detail like a visual simulator. He warns that generating video may look impressive, but it does not guarantee the system has learned the underlying dynamics of reality.

Jon Hernandez

36,093 Aufrufe • vor 7 Monaten

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 🤗
0:35

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 Aufrufe • vor 1 Monat

In response to Runway's new Gen-4 Video model announcement.. "Someone please try the video model turing test - flapping wings" I had this laying around 🥹😎 (Made with Gen-4)
0:56

In response to Runway's new Gen-4 Video model announcement.. "Someone please try the video model turing test - flapping wings" I had this laying around 🥹😎 (Made with Gen-4)

🍥 Timmy 🍥

37,604 Aufrufe • vor 1 Jahr

Dubai was long seen as a safe haven in an uncertain part of the world. But the Iran war has put that model to the test
1:40

Dubai was long seen as a safe haven in an uncertain part of the world. But the Iran war has put that model to the test

Bloomberg

84,965 Aufrufe • vor 4 Monaten

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.
0:27

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

AK

684,303 Aufrufe • vor 2 Jahren

.Eric Jang explained Go to me in five minutes before his lecture on building AlphaGo from scratch. That was enough to see the key problems AlphaGo had to solve: gameplay involves search, but also strategic elements that make brute-force search intractable.
2:24

.Eric Jang explained Go to me in five minutes before his lecture on building AlphaGo from scratch. That was enough to see the key problems AlphaGo had to solve: gameplay involves search, but also strategic elements that make brute-force search intractable.

Dwarkesh Patel

26,932 Aufrufe • vor 2 Monaten

Satya Nadella reveals why every company may need its own AI model: the model becomes the new company database. "To me, a model is like the database market." "A firm should be able to take the tacit knowledge it has and embed it inside weights in a model that they control." "When somebody asks me how many models should there be, I'll say as many models as firms in the world." The contrarian part: the value may not sit in one universal frontier model. It sits in each company turning its private operating knowledge into a controlled model.
1:44

Satya Nadella reveals why every company may need its own AI model: the model becomes the new company database. "To me, a model is like the database market." "A firm should be able to take the tacit knowledge it has and embed it inside weights in a model that they control." "When somebody asks me how many models should there be, I'll say as many models as firms in the world." The contrarian part: the value may not sit in one universal frontier model. It sits in each company turning its private operating knowledge into a controlled model.

Karl Mehta

466,364 Aufrufe • vor 26 Tagen

.Eric Jang is spearheading AI at 1X. Eric believes 1X is on the path to becoming an AGI company — not just a robotics company. I sat down with him at 1X’s new Palo Alto office to discuss the key AI building blocks needed to bring humanoid robots into homes at scale. 00:00 Eric Jang joins Humanoid Hub 00:27 Move to Palo Alto 01:02 Why 1X targets the home 02:01 The AGI company 02:49 Redwood AI overview 04:01 Unified control, modular stack 06:07 Data labeling at scale 07:10 RL mobility update for NEO 10:03 GPU and onboard compute 11:09 World model explained 13:34 Trusting world models for evaluation 15:05 Synthetic data generation 16:30 A world model Turing Test 17:41 RL in manipulation 20:08 Lessons from early NEO deployments 21:00 Full autonomy 22:18 1X’s unique edge in AI 24:02 Eric asks Devang a question
26:53

.Eric Jang is spearheading AI at 1X. Eric believes 1X is on the path to becoming an AGI company — not just a robotics company. I sat down with him at 1X’s new Palo Alto office to discuss the key AI building blocks needed to bring humanoid robots into homes at scale. 00:00 Eric Jang joins Humanoid Hub 00:27 Move to Palo Alto 01:02 Why 1X targets the home 02:01 The AGI company 02:49 Redwood AI overview 04:01 Unified control, modular stack 06:07 Data labeling at scale 07:10 RL mobility update for NEO 10:03 GPU and onboard compute 11:09 World model explained 13:34 Trusting world models for evaluation 15:05 Synthetic data generation 16:30 A world model Turing Test 17:41 RL in manipulation 20:08 Lessons from early NEO deployments 21:00 Full autonomy 22:18 1X’s unique edge in AI 24:02 Eric asks Devang a question

The Humanoid Hub

96,465 Aufrufe • vor 1 Jahr

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.
5:01

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

Ali Romman

119,837 Aufrufe • vor 1 Monat

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!
2:41

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 Aufrufe • vor 3 Monaten

Doug DeMuro ranked the Tesla Model S as the #1 most important car of the last 30 years in his new video. Doug: "The Model S really changed the world. It made you think that EVs could be cool, fast, luxurious. It really reset any public opinion about EVs, that you didn't have to make major compromises; They (Tesla) created a cultural icon. If you created a list of the top 10 all-time cars that changed the world, Model S is in the top 5."
1:56

Doug DeMuro ranked the Tesla Model S as the #1 most important car of the last 30 years in his new video. Doug: "The Model S really changed the world. It made you think that EVs could be cool, fast, luxurious. It really reset any public opinion about EVs, that you didn't have to make major compromises; They (Tesla) created a cultural icon. If you created a list of the top 10 all-time cars that changed the world, Model S is in the top 5."

Sawyer Merritt

9,349,045 Aufrufe • vor 5 Monaten

I used multi-frame generation to make a mecha video. What’s impressive isn’t the visuals — it’s that the model remembers what happened in the previous frame. When AI understands continuous action, creation shifts from generating content to executing intent. That step matters.
0:35

I used multi-frame generation to make a mecha video. What’s impressive isn’t the visuals — it’s that the model remembers what happened in the previous frame. When AI understands continuous action, creation shifts from generating content to executing intent. That step matters.

Tyler TechForge

34,746 Aufrufe • vor 6 Monaten

Demis Hassabis says our brains are likely to be approximate Turing machines. AlphaFold showed why that matters: protein folding looked like a quantum problem, but a classical neural network could model it well enough to solve it. The world may be quantum, but understanding it may only need the right approximation.
0:55

Demis Hassabis says our brains are likely to be approximate Turing machines. AlphaFold showed why that matters: protein folding looked like a quantum problem, but a classical neural network could model it well enough to solve it. The world may be quantum, but understanding it may only need the right approximation.

vitrupo

47,068 Aufrufe • vor 2 Monaten

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!
0:52

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!

Odyssey

166,093 Aufrufe • vor 5 Monaten

The World Model as NEO's Cognitive Core 1X has revealed a major AI development where the NEO humanoid can translate any natural language prompt into robotic action. It demonstrates this capability even for novel tasks, objects, and environments not found in its robot dataset. - the 1X World Model is trained on internet-scale human interaction videos and fine-tuned with robot data to ground its understanding in physics and in NEO's embodiment - from a simple voice or text prompt, the world model generates a visualization of future actions - a built-in inverse dynamics model then translates these into precise motor movements for NEO
1:02

The World Model as NEO's Cognitive Core 1X has revealed a major AI development where the NEO humanoid can translate any natural language prompt into robotic action. It demonstrates this capability even for novel tasks, objects, and environments not found in its robot dataset. - the 1X World Model is trained on internet-scale human interaction videos and fine-tuned with robot data to ground its understanding in physics and in NEO's embodiment - from a simple voice or text prompt, the world model generates a visualization of future actions - a built-in inverse dynamics model then translates these into precise motor movements for NEO

The Humanoid Hub

68,453 Aufrufe • vor 6 Monaten

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.
0:25

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

66,088 Aufrufe • vor 6 Monaten

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang
2:08

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

112,021 Aufrufe • vor 1 Monat

Useless fact #1042 Paper Cordelius outline is built into his model meaning if you were to extract this model from the game and put it in a 3d viewing app the outline will also be there (Its just his model but black) no idea abt other model we only care abt Cordelius -F
0:35

Useless fact #1042 Paper Cordelius outline is built into his model meaning if you were to extract this model from the game and put it in a 3d viewing app the outline will also be there (Its just his model but black) no idea abt other model we only care abt Cordelius -F

Useless Brawl Stars Facts

13,473 Aufrufe • vor 1 Jahr