Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

1X World Model Scaling Evaluation for Robots

1X

130,162 subscribers

385,680 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

1X1 year ago

Read More:

dar1 year ago

THE MATRIX IS REAL! EVALUATING ROBOT MODELS WORKS!!! BIRDS ARE NOT FAKE?? SCALING LAWS ARE PROVEN!!!!!😩

TestingCatalog News 🗞1 year ago

Brilliant 🤖🤖🤖

frishtik de AI weirdo1 year ago

do yall live in the woods what’s up

1X1 year ago

The artsy fartsy guys keep taking the engineers into the woods... Working on resolving this internally

Daniel Ho1 year ago

📺

Humanoids daily1 year ago

An interesting insight from the video: the finding that the most valuable data for scaling the world model comes from NEO autonomously interacting with real environments—"succeeding and failing in interesting and diverse ways". The robot itself is the data engine.

DeBarra Shaw1 year ago

Impressive design and visionary approach. Can’t wait to see more!

Ted Xiao1 year ago

Scalable and predictive evaluation is one of the biggest bottlenecks in robotics, congrats @itsdanielho and the whole 1X team!

✧Heavens✧1 year ago

Beautiful! This is a game-changer, bridging reality and simulation to rapidly accelerate the evaluation of generalist robots, it's one of the most important aspects of the process. Seems like NEO will be one of the first commercially available robots for house use, looking forward to it, the future is bright. 👀✨

Related Videos

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

RoboPapers

27,567 views • 4 months ago

Since 2014 1X has been building humanoid-like robots. Now, they're revealing their new robot, NEO, to the world.

Since 2014 1X has been building humanoid-like robots. Now, they're revealing their new robot, NEO, to the world.

Jason Carman

1,402,949 views • 1 year ago

OpenAI's Noam Brown says letting AI models think for 20 seconds got the same boost in performance as scaling up the model by 100,000x and training it for 100,000 times longer, and scaling model size and compute will end up being a footnote compared to scaling model thinking

OpenAI's Noam Brown says letting AI models think for 20 seconds got the same boost in performance as scaling up the model by 100,000x and training it for 100,000 times longer, and scaling model size and compute will end up being a footnote compared to scaling model thinking

Tsarathustra

273,500 views • 1 year ago

Axis is officially LIVE on Base. 🔵 Axis is scaling Physical AI for the real world, contributed by everyone. You can control robots in a virtual world, generate training data at scale, and help build the brain behind tomorrow's robots. All from browser. No hardware needed. Start building robotics intelligence today:

Axis is officially LIVE on Base. 🔵 Axis is scaling Physical AI for the real world, contributed by everyone. You can control robots in a virtual world, generate training data at scale, and help build the brain behind tomorrow's robots. All from browser. No hardware needed. Start building robotics intelligence today:

Axis Robotics

232,410 views • 3 months ago

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

483,552 views • 7 months ago

📢 Announcing one of the most exciting works from us this year on **scalable robot policy evaluation through real-to-sim transfer**, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is **orders of magnitude slower** than the development of language agents. We propose a new framework where simulation performance **strongly correlates** with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing **state-of-the-art correlation** between simulation and reality for deformable object manipulation. It provides a **scalable and reproducible evaluation engine** for robot learning. 🌐

📢 Announcing one of the most exciting works from us this year on scalable robot policy evaluation through real-to-sim transfer, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is orders of magnitude slower than the development of language agents. We propose a new framework where simulation performance strongly correlates with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing state-of-the-art correlation between simulation and reality for deformable object manipulation. It provides a scalable and reproducible evaluation engine for robot learning. 🌐

Yunzhu Li

39,864 views • 7 months ago

OpenDriveLab just dropped RISE — a new paradigm for robot learning. Instead of expensive real-world trials, robots learn in imagination. A compositional world model simulates futures → evaluates outcomes → updates policy.

OpenDriveLab just dropped RISE — a new paradigm for robot learning. Instead of expensive real-world trials, robots learn in imagination. A compositional world model simulates futures → evaluates outcomes → updates policy.

Robots Digest 🤖

23,754 views • 1 month ago

.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

.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 views • 11 months ago

MindJourney Test-Time Scaling with World Models for Spatial Reasoning

MindJourney Test-Time Scaling with World Models for Spatial Reasoning

AK

61,714 views • 11 months ago

A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)

A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)

Jesse Zhang

100,274 views • 3 months ago

Yann LeCun says most humanoid robot companies don't yet know how to make robots generally useful They can train them for narrow tasks like manufacturing, but not for general use Domestic robots will only emerge after breakthroughs in world‑model and planning architectures

Yann LeCun says most humanoid robot companies don't yet know how to make robots generally useful They can train them for narrow tasks like manufacturing, but not for general use Domestic robots will only emerge after breakthroughs in world‑model and planning architectures

Haider.

14,360 views • 8 months ago

3rd Place: GrokWorld uses Grok Imagine as a world model to generate synthetic training data for robots — augmenting or replacing months of manual collection in hours. Aptura AI

3rd Place: GrokWorld uses Grok Imagine as a world model to generate synthetic training data for robots — augmenting or replacing months of manual collection in hours. Aptura AI

xAI

846,095 views • 5 months ago

#AGIBOTAIWeek Day4: Introducing GE-Sim 2.0 (Genie Envisioner World Simulator 2.0) , a comprehensive embodied world simulator for robotic manipulation. By integrating future video generation, proprioceptive state estimation, and reward-based policy assessment, GE-Sim 2.0 moves beyond visual simulation toward an embodied world simulator with built-in evaluation capability, laying the foundation for a world-model-centric platform for closed-loop and interactive policy learning. It provides a practical framework for scalable evaluation and training of robotic manipulation policies. Project page: #AGIBOT #AGIBOTAIWeek #GenieEnvisioner #Robotics #visualsimulation

#AGIBOTAIWeek Day4: Introducing GE-Sim 2.0 (Genie Envisioner World Simulator 2.0) , a comprehensive embodied world simulator for robotic manipulation. By integrating future video generation, proprioceptive state estimation, and reward-based policy assessment, GE-Sim 2.0 moves beyond visual simulation toward an embodied world simulator with built-in evaluation capability, laying the foundation for a world-model-centric platform for closed-loop and interactive policy learning. It provides a practical framework for scalable evaluation and training of robotic manipulation policies. Project page: #AGIBOT #AGIBOTAIWeek #GenieEnvisioner #Robotics #visualsimulation

AGIBOT

28,219 views • 2 months ago

At Mistral, robots keep their workspace tidy. Autonomous, 1x. Robostral WMa1. wip 🚧

At Mistral, robots keep their workspace tidy. Autonomous, 1x. Robostral WMa1. wip 🚧

Olivier Duchenne

54,984 views • 3 months ago

🇨🇳 China is deplying Robots everywhere. Here Unitree's humanoid robots + quadruped robot dogs patrol and perform duty in a team. You scale patrol hours without scaling headcount. Robots handle patrols, officers focus on judgment and de-escalation.

🇨🇳 China is deplying Robots everywhere. Here Unitree's humanoid robots + quadruped robot dogs patrol and perform duty in a team. You scale patrol hours without scaling headcount. Robots handle patrols, officers focus on judgment and de-escalation.

Rohan Paul

247,333 views • 6 months ago

Full episode dropping soon! Geeking out with Daniel Ho on 1X World Model Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

Full episode dropping soon! Geeking out with Daniel Ho on 1X World Model Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

RoboPapers

13,619 views • 4 months ago

Introducing 𝐃𝐫𝐞𝐚𝐦𝐆𝐞𝐧! We got humanoid robots to perform totally new 𝑣𝑒𝑟𝑏𝑠 in new environments through video world models. We believe video world models will solve the data problem in robotics. Bringing the paradigm of scaling human hours to GPU hours. Quick 🧵

Introducing 𝐃𝐫𝐞𝐚𝐦𝐆𝐞𝐧! We got humanoid robots to perform totally new 𝑣𝑒𝑟𝑏𝑠 in new environments through video world models. We believe video world models will solve the data problem in robotics. Bringing the paradigm of scaling human hours to GPU hours. Quick 🧵

Joel Jang

117,493 views • 1 year ago

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

Ted Xiao

152,423 views • 1 year ago

Jim Fan's predictions: ⦿ In the next 2–5 years, robotics will uncover its own scaling laws – similar to those seen in LLMs – by analyzing how model size, real‑world data, simulation data, and compute affect performance. ⦿ Within the next 20 years, robotics will accelerate fields like biomedical science by automating repetitive experiments, reducing time and cost in research. ⦿ Also within the next 20 years, robots may build and repair other robots and achieve recursive self‑improvement.

Jim Fan's predictions: ⦿ In the next 2–5 years, robotics will uncover its own scaling laws – similar to those seen in LLMs – by analyzing how model size, real‑world data, simulation data, and compute affect performance. ⦿ Within the next 20 years, robotics will accelerate fields like biomedical science by automating repetitive experiments, reducing time and cost in research. ⦿ Also within the next 20 years, robots may build and repair other robots and achieve recursive self‑improvement.

The Humanoid Hub

16,518 views • 1 year ago

While humans prepare for the World Cup, robots are training for theirs too! Look for RoboCup!

While humans prepare for the World Cup, robots are training for theirs too! Look for RoboCup!

Booster Robotics

11,629 views • 29 days ago