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。

Action-controllable world models are evolving fast. LingBot-World-Infinity can run an unbroken session of real-time world generation for up to an hour. A distilled model can stream 720p at 60 fps. World models are going to be a critical piece in training robotic agents for unseen worlds.

The Humanoid Hub

117,635 subscribers

14,196 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

The Humanoid Hub 的头像

The Humanoid Hub3 个月前

The mode is open-source. @robbyant_brain Github: Try it online: Weights:

Shara 的头像

Shara3 个月前

An hour long unbroken session at 60fps is a serious technical milestone for world models.

Relax_to_Rich 的头像

Relax_to_Rich3 个月前

Virtual world simulation drastically cuts hardware wear and time costs from physical robot field testing.

Hamid AI 的头像

Hamid AI3 个月前

@robbyant_brain "Distilled intelligence, real-world impact. Exciting progress! 🚀"

m 的头像

m3 个月前

@robbyant_brain "A distilled model can stream 720p at 60 fps." - You forgot to add that in order to run live generation at 60 fps, you need to have several H200 series GPUs 😄

Evelyn 的头像

Evelyn3 个月前

Really impressive progress! 🌍🤖 Running long, real-time world simulations at 720p/60 FPS is a major step forward for embodied AI and robotics. Excited to see how world models continue to shape the future of intelligent agents. 🚀

Gerard Sans | Axiom 🇬🇧 的头像

Gerard Sans | Axiom 🇬🇧3 个月前

Important discussion around current AI’s ROI myth

Future Alpha 的头像

Future Alpha3 个月前

World models are becoming the data factory for robots that can't afford infinite real-world failures. Sim is cheap until transfer fails. The winners will be whoever closes that gap with real task data, not prettier videos

Ferbin 的头像

Ferbin3 个月前

the simulation runs clean. real robot has latency, parts wearing out, a floor it never trained on. that gap between sim and real? that's where this wins or fails.

相关视频

🌍 What if an AI-generated world didn’t end after a few seconds—but kept running for hours, responded to every move, let you attack, cast spells, shoot, or summon storms, and continued evolving through AI agents? That’s LingBot-World 2.0: our open-source real-time interactive world model, scaling to 720p/60fps in our full setup. Today, we’re open-sourcing 3 more models: 🔹 LingBot-World 2.0 Small (1.3B) 🔹 LingBot-World 2.0 Bidirectional 🔹 LingBot-World 2.0 Causal Pretrain And now, with our 1.3B Small Model, that world can run in real time on a single consumer GPU. 🧵

🌍 What if an AI-generated world didn’t end after a few seconds—but kept running for hours, responded to every move, let you attack, cast spells, shoot, or summon storms, and continued evolving through AI agents? That’s LingBot-World 2.0: our open-source real-time interactive world model, scaling to 720p/60fps in our full setup. Today, we’re open-sourcing 3 more models: 🔹 LingBot-World 2.0 Small (1.3B) 🔹 LingBot-World 2.0 Bidirectional 🔹 LingBot-World 2.0 Causal Pretrain And now, with our 1.3B Small Model, that world can run in real time on a single consumer GPU. 🧵

Robbyant

1,999,698 次观看 • 1 个月前

Robbyant released LingBot-World 2.0 (Infinity), a new open-source World model capable of generating hour-long experiences. > No quality decay, stable 720p / 60 fps real-time output. > Users can interact with the world via Actions. > The world is dynamic, with built-in agents generating new events in real time. > Multiplayer is supported within the same world. Testing time 👀

Robbyant released LingBot-World 2.0 (Infinity), a new open-source World model capable of generating hour-long experiences. > No quality decay, stable 720p / 60 fps real-time output. > Users can interact with the world via Actions. > The world is dynamic, with built-in agents generating new events in real time. > Multiplayer is supported within the same world. Testing time 👀

🚨 AI News | TestingCatalog

15,272 次观看 • 4 个月前

Most world models fall apart after a few seconds. Common failure modes include texture smearing, warped geometry, and scenes that no longer look real. LingBot-World 2.0 from Robbyant seems to hold 720p at 60 fps for a full hour of interaction. That’s impressive. Here is what makes that possible.

Most world models fall apart after a few seconds. Common failure modes include texture smearing, warped geometry, and scenes that no longer look real. LingBot-World 2.0 from Robbyant seems to hold 720p at 60 fps for a full hour of interaction. That’s impressive. Here is what makes that possible.

elvis

11,920 次观看 • 3 个月前

LingBot-World 2.0 (Infinity) is out on Hugging Face interactive world model with: Hour-long generation with zero quality drift Rich actions & events: attack, cast spells, shoot, summon storms Agentic world: a Director Agent drives real-time world evolution 720p/60fps. Playable like a game

LingBot-World 2.0 (Infinity) is out on Hugging Face interactive world model with: Hour-long generation with zero quality drift Rich actions & events: attack, cast spells, shoot, summon storms Agentic world: a Director Agent drives real-time world evolution 720p/60fps. Playable like a game

AK

29,480 次观看 • 4 个月前

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,693 次观看 • 5 个月前

Can we extend the power of world models beyond just online model-based learning? Absolutely! We believe the true potential of world models lies in enabling agents to reason at test time. Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.

Can we extend the power of world models beyond just online model-based learning? Absolutely! We believe the true potential of world models lies in enabling agents to reason at test time. Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.

Gaoyue Zhou

168,305 次观看 • 1 年前

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.

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

684,738 次观看 • 2 年前

Most AI world models can generate beautiful scenes. Keeping those scenes alive for an hour without falling apart is the real challenge. That's what caught my attention about LingBot-World 2.0 (LingBot-World-Infinity) from Robbyant Instead of chasing longer videos, it focuses on something much harder: persistent, interactive worlds that stay coherent while you explore. A few highlights: • Generates worlds from a single frame and continuously responds to live user actions through a causal world model. • Streams stable 720p at 60 FPS in real time. The team reports a continuous 60 minute stress test across 20 different scenarios with no noticeable visual degradation. • Uses a Brain-Cerebellum co-simulation framework where a VLM plans events while the video model turns them into consistent world evolution. • Pilot and Director Agents help drive character behavior and introduce new objects and events. • Open sourced with a 14B flagship model, while the paper also describes a lightweight 1.3B version for a single consumer GPU. There is also an online interactive demo. The biggest takeaway? We're moving beyond AI that generates clips. We're getting closer to AI that generates living, evolving worlds you can actually interact with. And that feels like a much bigger shift than another jump in video quality. Explore more: 💻 Github: 🤗 Weights: 🌐 Website-with videos you can use : 🎮 Try it online: #Robbyant #LingBot #WorldModel #EmbodiedAI #OpenSource #Robotics #ad

Most AI world models can generate beautiful scenes. Keeping those scenes alive for an hour without falling apart is the real challenge. That's what caught my attention about LingBot-World 2.0 (LingBot-World-Infinity) from Robbyant Instead of chasing longer videos, it focuses on something much harder: persistent, interactive worlds that stay coherent while you explore. A few highlights: • Generates worlds from a single frame and continuously responds to live user actions through a causal world model. • Streams stable 720p at 60 FPS in real time. The team reports a continuous 60 minute stress test across 20 different scenarios with no noticeable visual degradation. • Uses a Brain-Cerebellum co-simulation framework where a VLM plans events while the video model turns them into consistent world evolution. • Pilot and Director Agents help drive character behavior and introduce new objects and events. • Open sourced with a 14B flagship model, while the paper also describes a lightweight 1.3B version for a single consumer GPU. There is also an online interactive demo. The biggest takeaway? We're moving beyond AI that generates clips. We're getting closer to AI that generates living, evolving worlds you can actually interact with. And that feels like a much bigger shift than another jump in video quality. Explore more: 💻 Github: 🤗 Weights: 🌐 Website-with videos you can use : 🎮 Try it online: #Robbyant #LingBot #WorldModel #EmbodiedAI #OpenSource #Robotics #ad

Alif Khan

84,566 次观看 • 3 个月前

I’m incredibly excited to share a sneak peak of Wayve’s GAIA-1, a major step forward in action and language-conditioned world models for #AutonomousDriving. Here’s a glimpse of what GAIA-1 can do - more in the 🧵. (These are not real videos!) But what's a world model?

I’m incredibly excited to share a sneak peak of Wayve’s GAIA-1, a major step forward in action and language-conditioned world models for #AutonomousDriving. Here’s a glimpse of what GAIA-1 can do - more in the 🧵. (These are not real videos!) But what's a world model?

Jamie Shotton

198,954 次观看 • 3 年前

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Google DeepMind

1,443,434 次观看 • 1 年前

Introducing LingBot-World: An open-source world simulator pushing the boundaries of video generation. 🚀 🌍 High-Fidelity: Realistic, scientific, & stylized. 🧠 Long-Term Memory: Minute-level consistency. ⚡ Real-Time: <1s latency at 16 FPS. 📜 Apache 2.0 Licensed. Model: Github:

Introducing LingBot-World: An open-source world simulator pushing the boundaries of video generation. 🚀 🌍 High-Fidelity: Realistic, scientific, & stylized. 🧠 Long-Term Memory: Minute-level consistency. ⚡ Real-Time: <1s latency at 16 FPS. 📜 Apache 2.0 Licensed. Model: Github:

ModelScope

28,809 次观看 • 9 个月前

🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation. Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU. Project: Paper:

🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation. Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU. Project: Paper:

Haoyi Zhu

124,794 次观看 • 5 个月前

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

39,322 次观看 • 10 个月前

Self-learning worked in AlphaGo because the world was a clean rulebook, says Demis Hassabis. Real life has no perfect rulebook, so long-term planning needs a strong “world model” to simulate what happens next. Without that simulation, a robot has to guess in the real world—where mistakes can be costly and irreversible. Better world models are the first missing piece, says Demis Hassabis.

Self-learning worked in AlphaGo because the world was a clean rulebook, says Demis Hassabis. Real life has no perfect rulebook, so long-term planning needs a strong “world model” to simulate what happens next. Without that simulation, a robot has to guess in the real world—where mistakes can be costly and irreversible. Better world models are the first missing piece, says Demis Hassabis.

Wes Roth

15,757 次观看 • 9 个月前

Punchline: World models == VQA (about the future)! Planning with world models can be powerful for robotics/control. But most world models are video generators trained to predict everything, including irrelevant pixels and distractions. We ask - what if a world model only predicted the semantic information necessary for decision-making? Introducing Semantic World Models (SWM). Given an observation and an action sequence, SWMs cast modeling as answering textual questions about the future outcome resulting from the actions. Recasting world modeling as a VQA problem lets us directly leverage the pretrained knowledge and machinery of VLMs for generalizable modeling. We had a lot of fun thinking about how this work helps connect these two seemingly very different fields of study - VLMs and world models! 🧵(1/6) Paper: Fun demo:

Punchline: World models == VQA (about the future)! Planning with world models can be powerful for robotics/control. But most world models are video generators trained to predict everything, including irrelevant pixels and distractions. We ask - what if a world model only predicted the semantic information necessary for decision-making? Introducing Semantic World Models (SWM). Given an observation and an action sequence, SWMs cast modeling as answering textual questions about the future outcome resulting from the actions. Recasting world modeling as a VQA problem lets us directly leverage the pretrained knowledge and machinery of VLMs for generalizable modeling. We had a lot of fun thinking about how this work helps connect these two seemingly very different fields of study - VLMs and world models! 🧵(1/6) Paper: Fun demo:

Abhishek Gupta

61,483 次观看 • 1 年前

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Jack Parker-Holder

2,091,059 次观看 • 1 年前

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.

abdel

39,459 次观看 • 5 个月前

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

Runway

1,166,679 次观看 • 7 个月前