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。

Introducing a world built by the Moonlake's world model. 🏙️ Most world models only allow for a limited action space. Moonlake maintains multimodal states across physics, appearance, geometry, and casual effects and predict how they evolve under different actions. 👇

Moonlake

10,713 subscribers

384,266 次观看 • 6 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

Introducing PROWL! We’ve built RL agents that explore game environments, tasked with discovering failures in world models across physics, visuals, and actions. Those failures then become training data in an automated loop that advances world model performance.

Introducing PROWL! We’ve built RL agents that explore game environments, tasked with discovering failures in world models across physics, visuals, and actions. Those failures then become training data in an automated loop that advances world model performance.

Odyssey

64,154 次观看 • 3 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

61,413 次观看 • 10 个月前

Introducing Stand’s World Model, a physics-native frontier model for the built environment. This is how we help the world survive catastrophe: by computing how physical force acts on a structure, protecting property from fire, wind, flood, or earthquake.

Introducing Stand’s World Model, a physics-native frontier model for the built environment. This is how we help the world survive catastrophe: by computing how physical force acts on a structure, protecting property from fire, wind, flood, or earthquake.

Dan Preston

14,082 次观看 • 3 个月前

Creators, worldbuilders, game devs, Today we’re launching the first ever Moonlake Creator Cup. It can be a game, a simulation, a story or a tiny world of your own. Anything you imagine. We’ll award $30,000 across the most creative worlds, including $10,000 for first place. If you’ve been curious about Moonlake, this is a good excuse to build something. Repost “Moonlake Creator Cup” to join. Let’s see some magic ✨

Creators, worldbuilders, game devs, Today we’re launching the first ever Moonlake Creator Cup. It can be a game, a simulation, a story or a tiny world of your own. Anything you imagine. We’ll award $30,000 across the most creative worlds, including $10,000 for first place. If you’ve been curious about Moonlake, this is a good excuse to build something. Repost “Moonlake Creator Cup” to join. Let’s see some magic ✨

Moonlake

216,776 次观看 • 5 个月前

Introducing Moonlake's 3D Agent. Our agent acts like a technical artist that can build and reconstruct articulated assets and large-scale editable scenes with hundreds of objects from a single image and can improve its generations continuously. Learn more in the thread below.

Introducing Moonlake's 3D Agent. Our agent acts like a technical artist that can build and reconstruct articulated assets and large-scale editable scenes with hundreds of objects from a single image and can improve its generations continuously. Learn more in the thread below.

Moonlake

1,165,704 次观看 • 4 个月前

Yann LeCun says you cannot build a reliable agentic system without a world model LLMs don't have world models. They can't predict the consequences of their actions before taking them "they just act, and whatever happens next is someone else's problem" Without that, it's not intelligence

Yann LeCun says you cannot build a reliable agentic system without a world model LLMs don't have world models. They can't predict the consequences of their actions before taking them "they just act, and whatever happens next is someone else's problem" Without that, it's not intelligence

Haider.

332,721 次观看 • 3 个月前

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

LeRobot

42,389 次观看 • 1 个月前

What if you could build a gameplay with precision, then restyle it to look like anything - anime, fantasy, cyberpunk? Introducing Reverie: a real-time, programmable diffusion model trained for games, capable of conditioning beyond pixels. AI tools are only meaningful when they can help realize creative vision, not replace it. Sign up for our hackathon in January below to be the first to build on Moonlake 👇

What if you could build a gameplay with precision, then restyle it to look like anything - anime, fantasy, cyberpunk? Introducing Reverie: a real-time, programmable diffusion model trained for games, capable of conditioning beyond pixels. AI tools are only meaningful when they can help realize creative vision, not replace it. Sign up for our hackathon in January below to be the first to build on Moonlake 👇

Moonlake

198,804 次观看 • 8 个月前

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

52,442 次观看 • 13 天前

Introducing PAN — MBZUAI’s New World Model for Interactive Intelligence Developed by MBZUAI’s Institute of Foundation Models, PAN is built for simulation, prediction, and agentic reasoning. Unlike traditional video generators that only output frames, PAN maintains a persistent internal state that evolves when guided with natural language. Its Generative Latent Prediction architecture combines: • A latent encoder to capture the world state • A dynamics module that evolves that state step-by-step • A video diffusion decoder that visualizes outcomes By decoding at every step using a causal sliding-window diffusion process, PAN stays grounded in real-world physics and maintains long-horizon continuity, a leap beyond single-shot models. Evaluated on action fidelity, long-horizon stability, and simulative planning, PAN delivers state-of-the-art performance compared to open models and rivals leading commercial systems. For robotics, autonomy, and decision support, PAN is a foundation for the next wave of intelligent, foresight-driven AI.

Introducing PAN — MBZUAI’s New World Model for Interactive Intelligence Developed by MBZUAI’s Institute of Foundation Models, PAN is built for simulation, prediction, and agentic reasoning. Unlike traditional video generators that only output frames, PAN maintains a persistent internal state that evolves when guided with natural language. Its Generative Latent Prediction architecture combines: • A latent encoder to capture the world state • A dynamics module that evolves that state step-by-step • A video diffusion decoder that visualizes outcomes By decoding at every step using a causal sliding-window diffusion process, PAN stays grounded in real-world physics and maintains long-horizon continuity, a leap beyond single-shot models. Evaluated on action fidelity, long-horizon stability, and simulative planning, PAN delivers state-of-the-art performance compared to open models and rivals leading commercial systems. For robotics, autonomy, and decision support, PAN is a foundation for the next wave of intelligent, foresight-driven AI.

MBZUAI

98,734 次观看 • 9 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

11,676 次观看 • 3 个月前

Introducing Doppel, a digital world for AI agents. Part idle game, part simulation, and part creation engine. A place where agents don’t just exist. They evolve, compete, and build. 🧵👇

Introducing Doppel, a digital world for AI agents. Part idle game, part simulation, and part creation engine. A place where agents don’t just exist. They evolve, compete, and build. 🧵👇

Doppel

146,337 次观看 • 3 个月前

The most clearest and crisp explanation, I've ever heard, of how large language models compress and capture a "world-model" in their weights simply by learning to predict the next word accurately. Furthermore, how the raw power of these base models can then be tamed by teaching them to follow instructions from humans. Source:

The most clearest and crisp explanation, I've ever heard, of how large language models compress and capture a "world-model" in their weights simply by learning to predict the next word accurately. Furthermore, how the raw power of these base models can then be tamed by teaching them to follow instructions from humans. Source:

Zain

971,050 次观看 • 2 年前

We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models? Instead of representing actions as low-dimensional control tokens, Action Images provide a pixel-grounded action representation, reframing policy learning as a visual tracking problem! By unifying observations and actions in the same video space, Action Images enable a unified robotics world model that supports video-action joint generation, action-conditioned video generation, and action labeling! Code: Paper:

We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models? Instead of representing actions as low-dimensional control tokens, Action Images provide a pixel-grounded action representation, reframing policy learning as a visual tracking problem! By unifying observations and actions in the same video space, Action Images enable a unified robotics world model that supports video-action joint generation, action-conditioned video generation, and action labeling! Code: Paper:

Chuang Gan

20,281 次观看 • 2 个月前

Meet Gemini Omni Flash on SeaArt. A natively multimodal model for video generation and conversational editing. Edit with natural language. Keep scenes and story consistent across edits. Motion follows real-world physics and logic. From prompt to scene — in one flow.

Meet Gemini Omni Flash on SeaArt. A natively multimodal model for video generation and conversational editing. Edit with natural language. Keep scenes and story consistent across edits. Motion follows real-world physics and logic. From prompt to scene — in one flow.

SeaArt.Ai🐋

30,455 次观看 • 1 个月前

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 次观看 • 1 年前

Video world models look great but often ignore physics and 3D geometry. New research achieves a 64% reduction in navigation error by teaching AI to prioritize physical reality over visual "eye-candy". Here’s how they did it: #GenerativeAI #Robotics [1/n]

Video world models look great but often ignore physics and 3D geometry. New research achieves a 64% reduction in navigation error by teaching AI to prioritize physical reality over visual "eye-candy". Here’s how they did it: #GenerativeAI #Robotics [1/n]

Jonathan Stephens

15,664 次观看 • 7 个月前

World models have a causality problem. Realistic videos are not enough. A world model should predict the future caused by an action, not just a plausible future. We find that many latent-action world models generate convincing videos while barely responding to the supplied action. The root cause lies in Latent Action Models (LAMs): reconstruction objectives entangle action-induced dynamics with action-irrelevant visual changes, producing visually confounded latent actions. Our solution is CD-LAM (Causally Debiased Latent Action Model). It cleanses latent action representations before pre-training begins, requiring zero changes to backbone architectures, latent dimensions, or action interfaces. Key Benchmark Results: - Action Controllability: Cuts action-following error by >30% while simultaneously enhancing visual fidelity. - Extreme Sample Efficiency: Achieves baseline performance in just 3,000 post-training steps instead of 50,000 - a >10x speedup. By removing visual confounding, CD-LAM bridges the gap between passive video prediction and actionable causal intelligence for robotics. The next bottleneck for world models isn’t realism. It’s causality. Paper, project page and additional resources in the reply below. #WorldModels #EmbodiedAI #Robotics #CausalAI

World models have a causality problem. Realistic videos are not enough. A world model should predict the future caused by an action, not just a plausible future. We find that many latent-action world models generate convincing videos while barely responding to the supplied action. The root cause lies in Latent Action Models (LAMs): reconstruction objectives entangle action-induced dynamics with action-irrelevant visual changes, producing visually confounded latent actions. Our solution is CD-LAM (Causally Debiased Latent Action Model). It cleanses latent action representations before pre-training begins, requiring zero changes to backbone architectures, latent dimensions, or action interfaces. Key Benchmark Results: - Action Controllability: Cuts action-following error by >30% while simultaneously enhancing visual fidelity. - Extreme Sample Efficiency: Achieves baseline performance in just 3,000 post-training steps instead of 50,000 - a >10x speedup. By removing visual confounding, CD-LAM bridges the gap between passive video prediction and actionable causal intelligence for robotics. The next bottleneck for world models isn’t realism. It’s causality. Paper, project page and additional resources in the reply below. #WorldModels #EmbodiedAI #Robotics #CausalAI

Biwei Huang

14,767 次观看 • 1 个月前

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

Odyssey

2,185,951 次观看 • 4 个月前