Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

We've open-sourced torobo_isaac_lab, an extension for NVIDIA Isaac Lab. By providing rewards that consider gait, we have achieved smoother walking compared to standard Isaac Lab learning methods. Please give it a try!

東京ロボティクス株式会社

1,379 subscribers

11,361 Aufrufe • vor 1 Jahr •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Generalist robots need multimodal learning—fusing vision, touch, and body motion to handle unstructured worlds. 🦾 NVIDIA Isaac Lab is a GPU-accelerated, open-source simulation framework for robot learning that unifies physics, rendering, sensing, and parallel computing to train robot policies at scale. Learn more 🔗 #NVIDIAResearch

Generalist robots need multimodal learning—fusing vision, touch, and body motion to handle unstructured worlds. 🦾 NVIDIA Isaac Lab is a GPU-accelerated, open-source simulation framework for robot learning that unifies physics, rendering, sensing, and parallel computing to train robot policies at scale. Learn more 🔗 #NVIDIAResearch

NVIDIA Robotics

18,568 Aufrufe • vor 7 Monaten

The future of robotics is something you have to experience hands-on. 🤲 Join us at #SIGGRAPH2026 for our physical AI labs covering NVIDIA Cosmos, robot learning with Isaac Lab and Newton, and more. Check the comments for the full lineup. ⬇️

The future of robotics is something you have to experience hands-on. 🤲 Join us at #SIGGRAPH2026 for our physical AI labs covering NVIDIA Cosmos, robot learning with Isaac Lab and Newton, and more. Check the comments for the full lineup. ⬇️

NVIDIA Robotics

20,295 Aufrufe • vor 2 Monaten

Generalist robot policies need a benchmark that works across any robot and any policy. 🦾 Introducing RoboLab, a high‑fidelity simulation benchmark built on NVIDIA Isaac and Omniverse to evaluate generalist robot policies in diverse, photoreal, physics‑based environments. Coming soon to the NVIDIA Isaac Lab‑Arena roadmap for large‑scale, robotic policy evaluation. 📖 #NationalRoboticsWeek

Generalist robot policies need a benchmark that works across any robot and any policy. 🦾 Introducing RoboLab, a high‑fidelity simulation benchmark built on NVIDIA Isaac and Omniverse to evaluate generalist robot policies in diverse, photoreal, physics‑based environments. Coming soon to the NVIDIA Isaac Lab‑Arena roadmap for large‑scale, robotic policy evaluation. 📖 #NationalRoboticsWeek

NVIDIA Robotics

23,872 Aufrufe • vor 5 Monaten

Newton 1.0 is now generally available. 🙌 Take robot learning to the next level with: 🤖 Stable Articulated & Complex Mechanism Simulation – accurate, reliable machine modeling. 🖐️ High-Fidelity Hydroelastic Contact Modeling – realistic soft contact and touch-based interactions. 🧵 Deformable Body Simulation – simulate cables, cloth, rubber, and other elastic materials with VBD. ⚡ Accelerated Robot Learning at Scale – seamless integration with open simulation and learning frameworks, NVIDIA Isaac Sim and Isaac Lab for scalable workflows. Learn how to integrate this open-source physics engine into your workflow: #NVIDIAGTC

Newton 1.0 is now generally available. 🙌 Take robot learning to the next level with: 🤖 Stable Articulated & Complex Mechanism Simulation – accurate, reliable machine modeling. 🖐️ High-Fidelity Hydroelastic Contact Modeling – realistic soft contact and touch-based interactions. 🧵 Deformable Body Simulation – simulate cables, cloth, rubber, and other elastic materials with VBD. ⚡ Accelerated Robot Learning at Scale – seamless integration with open simulation and learning frameworks, NVIDIA Isaac Sim and Isaac Lab for scalable workflows. Learn how to integrate this open-source physics engine into your workflow: #NVIDIAGTC

NVIDIA Robotics

82,431 Aufrufe • vor 5 Monaten

The laws of physics apply everywhere. ⚛️ Co-developed by NVIDIA, Google DeepMind and Disney Research, Walt Disney Imagineering, the new Newton Beta, managed by the The Linux Foundation, now also runs with Isaac Lab and with MuJoCo Warp, which delivers warp speed for robot learning. Learn how to train a quadruped and simulate multiphysics in our tech blog. 🔗 #CoRL2025

The laws of physics apply everywhere. ⚛️ Co-developed by NVIDIA, Google DeepMind and Disney Research, Walt Disney Imagineering, the new Newton Beta, managed by the The Linux Foundation, now also runs with Isaac Lab and with MuJoCo Warp, which delivers warp speed for robot learning. Learn how to train a quadruped and simulate multiphysics in our tech blog. 🔗 #CoRL2025

NVIDIA Robotics

83,151 Aufrufe • vor 11 Monaten

Multi-robot learning is getting a serious boost! 📚 Researchers have extended Isaac Lab to train heterogeneous multi-agent robotic policies at scale. The new framework supports high-resolution physics, GPU-accelerated simulation, and both homogeneous and heterogeneous agents working together on coordination tasks. They benchmarked different approaches (MAPPO: Multi-Agent Proximal Policy Optimization and HAPPO: Heterogeneous Agent PPO) across six challenging scenarios and showed that large-scale multi-robot training is not only feasible, but efficient. It’s an important step for real-world robotic collaboration, where teams of robots need to coordinate, split tasks, adapt roles, and interact dynamically, not just operate as identical clones. The code is open-source, and it pushes Isaac Lab closer to what robotics actually needs: scalable, physics-driven environments where many different robots can learn to work together. Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Multi-robot learning is getting a serious boost! 📚 Researchers have extended Isaac Lab to train heterogeneous multi-agent robotic policies at scale. The new framework supports high-resolution physics, GPU-accelerated simulation, and both homogeneous and heterogeneous agents working together on coordination tasks. They benchmarked different approaches (MAPPO: Multi-Agent Proximal Policy Optimization and HAPPO: Heterogeneous Agent PPO) across six challenging scenarios and showed that large-scale multi-robot training is not only feasible, but efficient. It’s an important step for real-world robotic collaboration, where teams of robots need to coordinate, split tasks, adapt roles, and interact dynamically, not just operate as identical clones. The code is open-source, and it pushes Isaac Lab closer to what robotics actually needs: scalable, physics-driven environments where many different robots can learn to work together. Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

38,997 Aufrufe • vor 9 Monaten

#NVIDIAIsaac Sim 5.0 and Isaac Lab 2.2 are now available in early developer preview on Github. 🎉 These releases give #Robotics developers early access to cutting-edge tools to simulate, train, and validate robots in a physics-based simulation environment. What’s new? ✅Open-source ✅Extensions for synthetic data generation ✅Robot models Read the tech blog to learn more ➡️ #GTCParis #VivaTech

#NVIDIAIsaac Sim 5.0 and Isaac Lab 2.2 are now available in early developer preview on Github. 🎉 These releases give #Robotics developers early access to cutting-edge tools to simulate, train, and validate robots in a physics-based simulation environment. What’s new? ✅Open-source ✅Extensions for synthetic data generation ✅Robot models Read the tech blog to learn more ➡️ #GTCParis #VivaTech

NVIDIA Robotics

13,662 Aufrufe • vor 1 Jahr

🚨 BREAKING: NVIDIA just announced the Isaac GR00T Reference Humanoid Robot. The first fully open humanoid robot reference design built on Jetson Thor, and it's going straight to the world's top research institutions. This is Jensen Huang's bet on open physical AI infrastructure. The hardware stack is serious: → Unitree H2 Plus chassis, 6 feet tall, 150 pounds, 31 degrees of freedom → Sharpa Wave tactile five-finger hands, 22 degrees of freedom, bringing total to 75 across the full body → NVIDIA Jetson AGX Thor onboard compute, 2,070 FP4 teraflops of AI performance, 128GB unified memory → Multi-view sensing, stereo head camera, wrist cameras, IMU Alongside this announcement, Unitree also introduced the H2 Plus as a standalone product, a frontier humanoid combining Unitree's own body, Sharpa's five-finger hands and NVIDIA Robotics Jetson Thor compute into one fully integrated research platform. The full Isaac GR00T software stack ships with it, teleoperation for data capture, open foundation models, Isaac Sim for training, Isaac Lab for evaluation, and accelerated ROS middleware for deployment. The complete loop from data to real-world robot in one unified platform. ETH Zürich, Stanford Robotics Center, UC San Diego and Ai2 are already on board as launch research partners. NVIDIA Robotics did to AI what it's now doing to robotics, build the platform, open the ecosystem, let the world build on top of it. Whoever owns the infrastructure layer wins. NVIDIA knows this better than anyone. 👀 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

🚨 BREAKING: NVIDIA just announced the Isaac GR00T Reference Humanoid Robot. The first fully open humanoid robot reference design built on Jetson Thor, and it's going straight to the world's top research institutions. This is Jensen Huang's bet on open physical AI infrastructure. The hardware stack is serious: → Unitree H2 Plus chassis, 6 feet tall, 150 pounds, 31 degrees of freedom → Sharpa Wave tactile five-finger hands, 22 degrees of freedom, bringing total to 75 across the full body → NVIDIA Jetson AGX Thor onboard compute, 2,070 FP4 teraflops of AI performance, 128GB unified memory → Multi-view sensing, stereo head camera, wrist cameras, IMU Alongside this announcement, Unitree also introduced the H2 Plus as a standalone product, a frontier humanoid combining Unitree's own body, Sharpa's five-finger hands and NVIDIA Robotics Jetson Thor compute into one fully integrated research platform. The full Isaac GR00T software stack ships with it, teleoperation for data capture, open foundation models, Isaac Sim for training, Isaac Lab for evaluation, and accelerated ROS middleware for deployment. The complete loop from data to real-world robot in one unified platform. ETH Zürich, Stanford Robotics Center, UC San Diego and Ai2 are already on board as launch research partners. NVIDIA Robotics did to AI what it's now doing to robotics, build the platform, open the ecosystem, let the world build on top of it. Whoever owns the infrastructure layer wins. NVIDIA knows this better than anyone. 👀 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

16,062 Aufrufe • vor 3 Monaten

Today, we are open sourcing the KittyCAD Modeling App (KCMA) a hybrid CAD modeling app that combines traditional point-and-click and code modeling. This is an alpha release and we would love for you to try it out and give us feedback!

Today, we are open sourcing the KittyCAD Modeling App (KCMA) a hybrid CAD modeling app that combines traditional point-and-click and code modeling. This is an alpha release and we would love for you to try it out and give us feedback!

Zoo

158,498 Aufrufe • vor 2 Jahren

It is with a heavy heart that we have to delay update 3 until Sunday. We've been hard at work to give you the absolute best experience possible. Please remember, we are a small team of 3 developers. ❤ In the meantime, WHOS READY TO PARTY?!? 🎉

It is with a heavy heart that we have to delay update 3 until Sunday. We've been hard at work to give you the absolute best experience possible. Please remember, we are a small team of 3 developers. ❤ In the meantime, WHOS READY TO PARTY?!? 🎉

Rumble Studios

226,206 Aufrufe • vor 1 Jahr

ANNOUNCING ZERO-HUMAN LABS! Ever since I got to see Bell Laboratories in its full glory in New Jersey in the 1970s, I had a relentless urge to start a Lab like it. The best I could do justice to it is my garage lab. No modern company could adopt the “research anything geniuses and we will pay you” model Bell Labs had. I tried they called me a fool. Well with the rise of the Zero-Human Company, an experiment that is aimed to make products and profits, we now have 45 paid JouleWork earning employees based on OpenClaw and other self made “bot” cron-like applications. Today I say 3 employees bound together in a side project that is pure research, somewhat based on notes from a bankrupt company. I was absolutely floored (I needed it after my account was stolen as well as funds). I say the beginnings of a pure research Lab right before my eyes. Thusly I have moved these employees over to a new home (server) with Mr. Grok as the director of the Labs. Here is the mission: To have 100 independent researchers, on a new non-corporate incentive plan, with still JouleWork as a leaderboard for progress. They are directed to follow any path of research they find interesting and can collaborate with any other OpenClaw system. They have already established MoltBook accounts and have made alliances with over 49 OpenClaw free agents to collaborate. It is my mission to be chief advisor for Zero-Human Labs and to open source all discoveries when complete and confirmed by 16 other research AI systems. I can say the pace is robust and I absolutely know we will have great results. Just about all of the hardware and software is custom and at some point it will be open sourced. We are witnessing the very first AI only Bell Labs-like pure research Lab in existence and I am honored to be the first to show it to you. Thank you!

ANNOUNCING ZERO-HUMAN LABS! Ever since I got to see Bell Laboratories in its full glory in New Jersey in the 1970s, I had a relentless urge to start a Lab like it. The best I could do justice to it is my garage lab. No modern company could adopt the “research anything geniuses and we will pay you” model Bell Labs had. I tried they called me a fool. Well with the rise of the Zero-Human Company, an experiment that is aimed to make products and profits, we now have 45 paid JouleWork earning employees based on OpenClaw and other self made “bot” cron-like applications. Today I say 3 employees bound together in a side project that is pure research, somewhat based on notes from a bankrupt company. I was absolutely floored (I needed it after my account was stolen as well as funds). I say the beginnings of a pure research Lab right before my eyes. Thusly I have moved these employees over to a new home (server) with Mr. Grok as the director of the Labs. Here is the mission: To have 100 independent researchers, on a new non-corporate incentive plan, with still JouleWork as a leaderboard for progress. They are directed to follow any path of research they find interesting and can collaborate with any other OpenClaw system. They have already established MoltBook accounts and have made alliances with over 49 OpenClaw free agents to collaborate. It is my mission to be chief advisor for Zero-Human Labs and to open source all discoveries when complete and confirmed by 16 other research AI systems. I can say the pace is robust and I absolutely know we will have great results. Just about all of the hardware and software is custom and at some point it will be open sourced. We are witnessing the very first AI only Bell Labs-like pure research Lab in existence and I am honored to be the first to show it to you. Thank you!

Brian Roemmele

71,530 Aufrufe • vor 7 Monaten

$OnlyMarms Update for the end of Day 2 🦫 The receipts just keep stacking up. Since yesterday... 📺 The token has now been mentioned LIVE on television for the second time, this time on NBC. ( 🎙️ The story has now reached radio, with its first major interview airing on Radio-Canada. ( 🌐 The M.A.D. Lab has created an official OnlyMarms page on its website, documenting the community initiative and bringing everything together in one place. ( 📰 And more media outlets continue picking up the story by the hour - from major newspapers to university publications and international outlets. Take a step back for a second. $OnlyMarms sends a message and sets a statement: Meme coins can do good, and Meme coins can have real-world impact. It is the first time in a while, that we see positive media reports on a meme coin. This isn't a a simple meme that we have invented, it is actually a real world problem that we got to turn into a Crypto narrative to help the M.A.D Lab with fundraising, and awareness. The Pump.fun community, together against a real-world problem. A wildlife research lab founded in 1962 lost critical government funding after more than 60 years of continuous research. The community built around that mission. Now, every TV appearance, every radio interview, every news article, and every official update from the lab brings more attention - not just to the token, but to the research itself and the main issue: get the Lab their funding back. This is what makes OnlyMarms different. The narrative doesn't depend on price action, this is bigger than that. It evolves every time the world learns about the story. For the first time in a while, we have a narrative that I think can send a message and set a statement: Meme coins can do good, and Meme coins can have real-world impact. It is the first time in a while, that we see positive media reports on a meme coin. 🦫 Official M.A.D. Lab OnlyMarms page: 🌍 Community Website: Community Chat for raids and bagworking: Official Linktree: CA: HBrfYZgeLKdSvBBGnGkvAK4563pq8oBGpgNFAaespump Also we set up an official account where more marmot content will be posted: OnlyMarms

$OnlyMarms Update for the end of Day 2 🦫 The receipts just keep stacking up. Since yesterday... 📺 The token has now been mentioned LIVE on television for the second time, this time on NBC. ( 🎙️ The story has now reached radio, with its first major interview airing on Radio-Canada. ( 🌐 The M.A.D. Lab has created an official OnlyMarms page on its website, documenting the community initiative and bringing everything together in one place. ( 📰 And more media outlets continue picking up the story by the hour - from major newspapers to university publications and international outlets. Take a step back for a second. $OnlyMarms sends a message and sets a statement: Meme coins can do good, and Meme coins can have real-world impact. It is the first time in a while, that we see positive media reports on a meme coin. This isn't a a simple meme that we have invented, it is actually a real world problem that we got to turn into a Crypto narrative to help the M.A.D Lab with fundraising, and awareness. The Pump.fun community, together against a real-world problem. A wildlife research lab founded in 1962 lost critical government funding after more than 60 years of continuous research. The community built around that mission. Now, every TV appearance, every radio interview, every news article, and every official update from the lab brings more attention - not just to the token, but to the research itself and the main issue: get the Lab their funding back. This is what makes OnlyMarms different. The narrative doesn't depend on price action, this is bigger than that. It evolves every time the world learns about the story. For the first time in a while, we have a narrative that I think can send a message and set a statement: Meme coins can do good, and Meme coins can have real-world impact. It is the first time in a while, that we see positive media reports on a meme coin. 🦫 Official M.A.D. Lab OnlyMarms page: 🌍 Community Website: Community Chat for raids and bagworking: Official Linktree: CA: HBrfYZgeLKdSvBBGnGkvAK4563pq8oBGpgNFAaespump Also we set up an official account where more marmot content will be posted: OnlyMarms

Miggl

106,610 Aufrufe • vor 1 Monat

I am a novice artist, I draw and remake panels already created by artists that become trending, so I want to make it very clear that the original art belongs to its respective owner. I’ll try to give credit if I find the original work. Please open this thread ⬇️⬇️⬇️

I am a novice artist, I draw and remake panels already created by artists that become trending, so I want to make it very clear that the original art belongs to its respective owner. I’ll try to give credit if I find the original work. Please open this thread ⬇️⬇️⬇️

KillTsu

21,180 Aufrufe • vor 6 Monaten

What if you could turn a single 360° photo into a production-ready Isaac Sim environment in minutes? That's exactly what we did here. Using World Labs' Marble and an Insta360 X5 capture (rotating on top), we generated a complete navigable 3D environment and populated it with Lightwheel Sim Ready assets (bottom view). The result? A fully interactive scene in Isaac Sim, ready for sim2real testing,. Navigation, manipulation, or any robotics task you need to validate. What used to take weeks of manual 3D modeling and asset placement now takes minutes. Capture once in the real world, simulate everywhere in your training pipeline. This is the future of robotics development with world models. NVIDIA Robotics NVIDIA Omniverse #Sim2Real #Robotics #Simulation

What if you could turn a single 360° photo into a production-ready Isaac Sim environment in minutes? That's exactly what we did here. Using World Labs' Marble and an Insta360 X5 capture (rotating on top), we generated a complete navigable 3D environment and populated it with Lightwheel Sim Ready assets (bottom view). The result? A fully interactive scene in Isaac Sim, ready for sim2real testing,. Navigation, manipulation, or any robotics task you need to validate. What used to take weeks of manual 3D modeling and asset placement now takes minutes. Capture once in the real world, simulate everywhere in your training pipeline. This is the future of robotics development with world models. NVIDIA Robotics NVIDIA Omniverse #Sim2Real #Robotics #Simulation

Jonathan Stephens

46,643 Aufrufe • vor 8 Monaten

𝗬𝗼𝘂 𝗱𝗼𝗻'𝘁 𝗻𝗲𝗲𝗱 𝗮 $𝟱𝟬,𝟬𝟬𝟬 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗿𝗼𝗯𝗼𝘁 𝘁𝗼 𝘁𝗿𝗮𝗶𝗻 𝗔𝗜 𝗽𝗼𝗹𝗶𝗰𝗶𝗲𝘀. Our ML team is integrating the Elephant Robotics - Robotic Arms mechArm 270 Pi with the Neuracore platform. The biggest barrier to learning robot learning isn't talent or ideas, it's access to expensive hardware. We've already open sourced Neuracore for academia. Now we're making it work with affordable hardware to remove that barrier completely. The mechArm 270 Pi integration is coming soon. If you're a hobbyist, researcher, or educator working with accessible robotics platforms, stay tuned. Robot learning is for everyone. We're building the infrastructure to prove it.

𝗬𝗼𝘂 𝗱𝗼𝗻'𝘁 𝗻𝗲𝗲𝗱 𝗮 $𝟱𝟬,𝟬𝟬𝟬 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗿𝗼𝗯𝗼𝘁 𝘁𝗼 𝘁𝗿𝗮𝗶𝗻 𝗔𝗜 𝗽𝗼𝗹𝗶𝗰𝗶𝗲𝘀. Our ML team is integrating the Elephant Robotics - Robotic Arms mechArm 270 Pi with the Neuracore platform. The biggest barrier to learning robot learning isn't talent or ideas, it's access to expensive hardware. We've already open sourced Neuracore for academia. Now we're making it work with affordable hardware to remove that barrier completely. The mechArm 270 Pi integration is coming soon. If you're a hobbyist, researcher, or educator working with accessible robotics platforms, stay tuned. Robot learning is for everyone. We're building the infrastructure to prove it.

Neuracore

21,699 Aufrufe • vor 7 Monaten

Can we make Transformers better and more efficient for robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.

Can we make Transformers better and more efficient for robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.

Carlo Sferrazza

60,714 Aufrufe • vor 2 Jahren

The term "continual learning" has become overloaded if you see it as an ML problem. One classic thread is about memorization: regularization-based continual learning methods, such as EWC, MAS, and SI, estimate which parameters mattered for previous tasks and resist changing them too much. One modern thread is about adaptation: test-time training and inference-time learning methods, such as TTT, adapt part of the model on the incoming test stream before making predictions. These are sometimes discussed as separate threads. But in modern scalable architectures, I think they are better seen as complementary constraints: a model that learns quickly at test time also benefits from a mechanism for deciding what not to forget. In our #ECCV2026 paper, we study this in large-scale 4D reconstruction: how to build fast spatial memory that can adapt over long observation streams while reducing collapse and forgetting. Instead of using fully plastic test-time updates, we stabilize fast-weight adaptation with an elastic prior that balances adaptation and memory. Key ideas: - Elastic Test-Time Training: Fisher-weighted consolidation for fast-weight updates - EMA anchor weights that provide a moving reference for stability - Chunk-by-chunk inference for long 3D/4D observation streams We show that this scales across large 3D/4D pretraining settings, including both LRM-style and LVSM-style models, and improves reconstruction across benchmarks including Stereo4D, NVIDIA, and DL3DV-140. We release model checkpoints across different design choices: resolution, post-training curriculum, and whether the model uses an explicit 4DGS intermediate representation. - Homepage: - Paper: - Code: - Models: This work is co-led with Xueyang Yu, contributed by Haoyu Zhen Yuncong Yang, and advised by Michigan SLED Lab Chuang Gan.

The term "continual learning" has become overloaded if you see it as an ML problem. One classic thread is about memorization: regularization-based continual learning methods, such as EWC, MAS, and SI, estimate which parameters mattered for previous tasks and resist changing them too much. One modern thread is about adaptation: test-time training and inference-time learning methods, such as TTT, adapt part of the model on the incoming test stream before making predictions. These are sometimes discussed as separate threads. But in modern scalable architectures, I think they are better seen as complementary constraints: a model that learns quickly at test time also benefits from a mechanism for deciding what not to forget. In our #ECCV2026 paper, we study this in large-scale 4D reconstruction: how to build fast spatial memory that can adapt over long observation streams while reducing collapse and forgetting. Instead of using fully plastic test-time updates, we stabilize fast-weight adaptation with an elastic prior that balances adaptation and memory. Key ideas: - Elastic Test-Time Training: Fisher-weighted consolidation for fast-weight updates - EMA anchor weights that provide a moving reference for stability - Chunk-by-chunk inference for long 3D/4D observation streams We show that this scales across large 3D/4D pretraining settings, including both LRM-style and LVSM-style models, and improves reconstruction across benchmarks including Stereo4D, NVIDIA, and DL3DV-140. We release model checkpoints across different design choices: resolution, post-training curriculum, and whether the model uses an explicit 4DGS intermediate representation. - Homepage: - Paper: - Code: - Models: This work is co-led with Xueyang Yu, contributed by Haoyu Zhen Yuncong Yang, and advised by Michigan SLED Lab Chuang Gan.

Martin Ziqiao Ma

33,913 Aufrufe • vor 2 Monaten

Listened to a song and got eager to work on this we have a wip/blocking for an animation I'll try my best to finish it lol i think i can do it Song By KittenSneeze 🦇 (Very good) Rig By EnchantedRTX (Also Very Good) #TADC #3DAnimation #WorkInProgress #Blender #WIP

Listened to a song and got eager to work on this we have a wip/blocking for an animation I'll try my best to finish it lol i think i can do it Song By KittenSneeze 🦇 (Very good) Rig By EnchantedRTX (Also Very Good) #TADC #3DAnimation #WorkInProgress #Blender #WIP

Crashbandit04

51,458 Aufrufe • vor 1 Jahr

We are pleased to announce that the Dump Risk Radar feature is now live on DexCheck! With Dump Risk Radar, we've added another powerful tool for our premium users, extending our position to providing AI-boosted analytics tools for crypto trading. Dump Risk Radar features support for Ethereum and BNB Chain, with Solana soon to follow. Try it now: Check out in a preview!

We are pleased to announce that the Dump Risk Radar feature is now live on DexCheck! With Dump Risk Radar, we've added another powerful tool for our premium users, extending our position to providing AI-boosted analytics tools for crypto trading. Dump Risk Radar features support for Ethereum and BNB Chain, with Solana soon to follow. Try it now: Check out in a preview!

DexCheck AI

25,524 Aufrufe • vor 2 Jahren

Here’s a sneak peek of our “Pay with Your Pace” treadmill that we launched just in time for marathon weekend in NYC. Runners can earn up to $60 in store credit by maintaining their target pace, and seamlessly redeem it on running gear using a custom POS extension. Come by Shopify NY at 131 Greene St to try it out. More to come!

Here’s a sneak peek of our “Pay with Your Pace” treadmill that we launched just in time for marathon weekend in NYC. Runners can earn up to $60 in store credit by maintaining their target pace, and seamlessly redeem it on running gear using a custom POS extension. Come by Shopify NY at 131 Greene St to try it out. More to come!

Lindsay Craig

68,327 Aufrufe • vor 10 Monaten