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。

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Vector Wang

1,916 subscribers

30,474 次观看 • 5 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

Fast Foundation Stereo + SAM2 basically = zero shot Foundation Pose😂 No CAD model, no object image, just click the target. Run directly on my 3070 at 13fps, with a 30$ stereo camera (calibrated in 10min) Thanks Bowen Wen for his contribution to the community!

Fast Foundation Stereo + SAM2 basically = zero shot Foundation Pose😂 No CAD model, no object image, just click the target. Run directly on my 3070 at 13fps, with a 30$ stereo camera (calibrated in 10min) Thanks Bowen Wen for his contribution to the community!

Vector Wang

22,496 次观看 • 5 个月前

InstantSplat++ is now open source. It is a lightweight library that connects foundation models (VGGT, MASt3R, MAP-Anything, etc.) with the Gaussian splatting family. Given uncalibrated images, it optimizes a 3D scene in a few seconds. Try the demo and code here:

InstantSplat++ is now open source. It is a lightweight library that connects foundation models (VGGT, MASt3R, MAP-Anything, etc.) with the Gaussian splatting family. Given uncalibrated images, it optimizes a 3D scene in a few seconds. Try the demo and code here:

Zhiwen(Aaron) Fan

31,864 次观看 • 6 个月前

Nothing demonstrates the power of a network better than a real time demo. No marketing bull, just plain performance. And yes, 10c can be sent to a bank halfway across the world in seconds!

Nothing demonstrates the power of a network better than a real time demo. No marketing bull, just plain performance. And yes, 10c can be sent to a bank halfway across the world in seconds!

Alloy Networks

14,636 次观看 • 9 个月前

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 次观看 • 6 个月前

Just recorded a demo of automatically converting 2D images into 3D mesh with a balloon/lego style. Still many trivial work need to be done on the UI. Icons and stickers in the demo are from Flaticon #webgl #raytracing #generative #voxel

Just recorded a demo of automatically converting 2D images into 3D mesh with a balloon/lego style. Still many trivial work need to be done on the UI. Icons and stickers in the demo are from Flaticon #webgl #raytracing #generative #voxel

Yi Shen

50,250 次观看 • 3 年前

TWO DEVS BUILT A FULL MULTIPLAYER 3D GAME WITH WEBGL + THREE.JS - IN 5.7MB. NO UNITY. NO INSTALL. "Messenger" by Abeto is a planetary-delivery game: you're a kid on a tiny round world, dropping off mail, bumping into real players, waving with emojis. It runs entirely in a browser tab. The part that breaks your brain is the size. The whole thing loads in ~5.7MB. Not 5.7GB. Megabytes. You click a link and you're already playing - no download, no launcher, no account. what's under the hood: → WebGL + Three.js as the core - no Unity, no Godot → three-mesh-bvh for fast collisions on the curved planet → 3D models in Houdini + Blender, textures from Substance → real-time multiplayer over WebSockets on Node.js → lo-fi soundtrack streamed in, not bundled for scale: → AAA games ship at 50-150GB → this is ~10,000× lighter → install time for most 3D games: minutes → this: ~0 seconds → platform needed: none. it's a URL. We spent a decade saying "real games need a 100GB download and a gaming rig." A two-person studio just shipped a multiplayer 3D world that fits in the size of a few photos and opens in a tab. The browser quietly became a game console. Most people haven't noticed yet. 🔗 Link:

TWO DEVS BUILT A FULL MULTIPLAYER 3D GAME WITH WEBGL + THREE.JS - IN 5.7MB. NO UNITY. NO INSTALL. "Messenger" by Abeto is a planetary-delivery game: you're a kid on a tiny round world, dropping off mail, bumping into real players, waving with emojis. It runs entirely in a browser tab. The part that breaks your brain is the size. The whole thing loads in ~5.7MB. Not 5.7GB. Megabytes. You click a link and you're already playing - no download, no launcher, no account. what's under the hood: → WebGL + Three.js as the core - no Unity, no Godot → three-mesh-bvh for fast collisions on the curved planet → 3D models in Houdini + Blender, textures from Substance → real-time multiplayer over WebSockets on Node.js → lo-fi soundtrack streamed in, not bundled for scale: → AAA games ship at 50-150GB → this is ~10,000× lighter → install time for most 3D games: minutes → this: ~0 seconds → platform needed: none. it's a URL. We spent a decade saying "real games need a 100GB download and a gaming rig." A two-person studio just shipped a multiplayer 3D world that fits in the size of a few photos and opens in a tab. The browser quietly became a game console. Most people haven't noticed yet. 🔗 Link:

ZEUS⚡️

50,596 次观看 • 2 个月前

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

38,919 次观看 • 2 个月前

Introducing WildDet3D, a grounding model for monocular 3D object detection in the wild. A question I keep coming back to is: what is the right backbone for robotics foundation models? Should it be a video model, a language model, or perhaps a grounding model? WildDet3D is our first step in exploring that direction.

Introducing WildDet3D, a grounding model for monocular 3D object detection in the wild. A question I keep coming back to is: what is the right backbone for robotics foundation models? Should it be a video model, a language model, or perhaps a grounding model? WildDet3D is our first step in exploring that direction.

Jiafei Duan

12,137 次观看 • 4 个月前

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

119,091 次观看 • 20 天前

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Abhishek Gupta

11,994 次观看 • 1 年前

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,722 次观看 • 11 个月前

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

31,804 次观看 • 5 个月前

Get a taste of the Digital World: Iliad in Digimon Story #TimeStranger! Explore Central Town and fight your way to the top of Central Tower in a special hands-on demo! This demo will be playable at upcoming events worldwide - catch it if you can!

Get a taste of the Digital World: Iliad in Digimon Story #TimeStranger! Explore Central Town and fight your way to the top of Central Tower in a special hands-on demo! This demo will be playable at upcoming events worldwide - catch it if you can!

Digimon Games

161,787 次观看 • 1 年前

This is exactly how I envision the future of Non-VR games Instead of just a 2D window or even just adding stereo-3D to it — make it a fully 6DoF “portal” to the game you’re playing Fully adjustable, resizable, and maybe in the future: affect your real life world with special FX

This is exactly how I envision the future of Non-VR games Instead of just a 2D window or even just adding stereo-3D to it — make it a fully 6DoF “portal” to the game you’re playing Fully adjustable, resizable, and maybe in the future: affect your real life world with special FX

Brad Lynch

119,501 次观看 • 4 个月前

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive 3D worlds from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

Tencent Hy

371,977 次观看 • 4 个月前

Real-world assets are moving onchain. Open the RWA category on @Wallet and trade tokenized stocks, metals, and more in just a few taps. No brokerage account or extra apps needed.

Real-world assets are moving onchain. Open the RWA category on @Wallet and trade tokenized stocks, metals, and more in just a few taps. No brokerage account or extra apps needed.

OKX

65,079 次观看 • 1 个月前

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

SpAItial AI

176,524 次观看 • 8 个月前

oracles are already fully implemented in crypto exchanges and prediction markets the next big implementation is actually going to be in AI (not just stablecoin pricing for settlements by agents, that’s a given) access to data that’s privatized ie real world asset price feeds

oracles are already fully implemented in crypto exchanges and prediction markets the next big implementation is actually going to be in AI (not just stablecoin pricing for settlements by agents, that’s a given) access to data that’s privatized ie real world asset price feeds

gainzy

19,143 次观看 • 4 个月前