Loading video...

Video Failed to Load

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

Just started experimenting with 2D Cloth Physics Simulation using #raylib and #cplusplus 🧵🪡 By the way, there's a clear, concise article that's an excellent starting point: #gamedev #physics #simulation #verletintegration

Claudio Z.

1,368 subscribers

36,354 views • 1 year ago •via X (Twitter)

Arts Gaming Science & Technology #raylib #cplusplus #gamedev #physics #simulation #verletintegration

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

As a learning test, I ported part of my 2D Cloth Physics Simulation to the web using #Rust 🦀 🧪 Try the mini demo: Real-time simulation with Verlet integration, touch/mouse interaction, and web delivery. #gamedev #physics #simulation #verletintegration

As a learning test, I ported part of my 2D Cloth Physics Simulation to the web using #Rust 🦀 🧪 Try the mini demo: Real-time simulation with Verlet integration, touch/mouse interaction, and web delivery. #gamedev #physics #simulation #verletintegration

Claudio Z.

90,790 views • 1 year ago

ChatGPT 5.1 vs. Claude Opus 4.5 vs. DeepSeek-V3.2 (left) (middle) (right) prompt I used: Create a single HTML file containing a realistic cloth simulation using HTML5 Canvas and JavaScript. The cloth should be a grid of points connected by constraints using Verlet integration. Implement gravity and mouse interaction: the user should be able to click and drag particles to tear the cloth. The physics must remain stable without exploding.

ChatGPT 5.1 vs. Claude Opus 4.5 vs. DeepSeek-V3.2 (left) (middle) (right) prompt I used: Create a single HTML file containing a realistic cloth simulation using HTML5 Canvas and JavaScript. The cloth should be a grid of points connected by constraints using Verlet integration. Implement gravity and mouse interaction: the user should be able to click and drag particles to tear the cloth. The physics must remain stable without exploding.

God of Prompt

96,685 views • 7 months ago

There's a lot of speculation about whether OpenAI's video generation model Sora has a 'physics engine' (bolstered by OAI's own claims about 'world simulation'). Like the debate about world models in LLMs, this question is both genuinely interesting and somewhat ill-defined. 🧵1/

There's a lot of speculation about whether OpenAI's video generation model Sora has a 'physics engine' (bolstered by OAI's own claims about 'world simulation'). Like the debate about world models in LLMs, this question is both genuinely interesting and somewhat ill-defined. 🧵1/

Raphaël Millière @ ICML 2026

617,438 views • 2 years ago

NVIDIA GEAR lab is breaking new ground. With just 1.5M parameters, HOVER proves that mastering complex motor skills doesn’t require huge models. Using NVIDIA simulation suite, which accelerates physics by 10,000x, humanoids can learn a year’s worth of motion in under an hour.

NVIDIA GEAR lab is breaking new ground. With just 1.5M parameters, HOVER proves that mastering complex motor skills doesn’t require huge models. Using NVIDIA simulation suite, which accelerates physics by 10,000x, humanoids can learn a year’s worth of motion in under an hour.

The Humanoid Hub

126,265 views • 1 year ago

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

82,124 views • 4 months ago

Tonight at the house: An intimate AI x Physics Dinner with Prof. Steve Hsu from Manifold steve hsu, Alex Morisse, Alex Morisse, PhD, Jasper Jasper, and Jeremy Nixon - Automating AI Research. We started off with Alex casually explaining the science behind his stealth deeptech start-up on physics textbooks. A thread on the important questions in AI X physics.🧵

Tonight at the house: An intimate AI x Physics Dinner with Prof. Steve Hsu from Manifold steve hsu, Alex Morisse, Alex Morisse, PhD, Jasper Jasper, and Jeremy Nixon - Automating AI Research. We started off with Alex casually explaining the science behind his stealth deeptech start-up on physics textbooks. A thread on the important questions in AI X physics.🧵

AGI House SF

10,763 views • 5 months ago

We gave Grok 4.5 and GPT-5.6 Sol the exact same prompt and compared the outputs side by side. The task: generate a fully interactive HTML5 glass bridge simulation with realistic physics, structural failure, cinematic visuals, polished UI, and smooth animations. The difference is actually visible.

We gave Grok 4.5 and GPT-5.6 Sol the exact same prompt and compared the outputs side by side. The task: generate a fully interactive HTML5 glass bridge simulation with realistic physics, structural failure, cinematic visuals, polished UI, and smooth animations. The difference is actually visible.

Entelligence AI

71,177 views • 10 days ago

With the recent three-mesh-bvh changes you can finally make a full scene-wide BVH to accelerate physics, raycasting, etc. And at some point Pathtracing 😁 Its just a prototype so far but it "just works" with objects and batched instances in a single structure. #threejs #gamedev

With the recent three-mesh-bvh changes you can finally make a full scene-wide BVH to accelerate physics, raycasting, etc. And at some point Pathtracing 😁 Its just a prototype so far but it "just works" with objects and batched instances in a single structure. #threejs #gamedev

Garrett Johnson

32,495 views • 6 months ago

Robora Sim: A PyBullet-Powered Environment for Learning Robotic Physical Intelligence We are currently building our Robora simulation environment setup for our sim based learning, leveraging PyBullet, an industry-standard physics engine widely used in AI-driven robotics research and development. The environment is optimized with GPU-accelerated learning algorithms, enabling high-speed imitation learning and reinforcement learning within a safe and controlled virtual setup before shipping out to real world. This simulation platform allows our models to learn, adapt, and generalize across different robot morphologies, terrain types and task objectives - all before deployment to the real world. At it's core, the system combines a VLA-powered high-level planner with low-level motion control algorithms, working cohesively to produce emergent, physically intelligent behaviors. This synergy between simulation, learning, and real-world transfer marks a major step forward in our pursuit of adaptive and intelligent robotic systems. Through advanced domain randomization and synthetic data generation, the Robora Simulation Environment ensures that policies trained in simulation transfer effectively to real-world robots, minimizing the sim-to-real gap. Moreover, users will be able to test and integrate their own hardware kits within selected simulation environments in the Robora Dapp, ensuring seamless compatibility and safer real-world implementation.

Robora Sim: A PyBullet-Powered Environment for Learning Robotic Physical Intelligence We are currently building our Robora simulation environment setup for our sim based learning, leveraging PyBullet, an industry-standard physics engine widely used in AI-driven robotics research and development. The environment is optimized with GPU-accelerated learning algorithms, enabling high-speed imitation learning and reinforcement learning within a safe and controlled virtual setup before shipping out to real world. This simulation platform allows our models to learn, adapt, and generalize across different robot morphologies, terrain types and task objectives - all before deployment to the real world. At it's core, the system combines a VLA-powered high-level planner with low-level motion control algorithms, working cohesively to produce emergent, physically intelligent behaviors. This synergy between simulation, learning, and real-world transfer marks a major step forward in our pursuit of adaptive and intelligent robotic systems. Through advanced domain randomization and synthetic data generation, the Robora Simulation Environment ensures that policies trained in simulation transfer effectively to real-world robots, minimizing the sim-to-real gap. Moreover, users will be able to test and integrate their own hardware kits within selected simulation environments in the Robora Dapp, ensuring seamless compatibility and safer real-world implementation.

Robora

23,489 views • 9 months ago

🚨 BREAKING: Electrons just stopped behaving like particles, and started flowing like a perfect liquid. In graphene, scientists just observed a Dirac fluid a state where electrons move collectively with almost zero resistance. Even crazier? It breaks a fundamental law of physics (the Wiedemann–Franz law) by over 200x. This isn’t just a material discovery. It means: Electricity can behave like fluid dynamics Heat and charge can decouple Quantum systems can act like perfect liquids Now think bigger: If electrons can flow like this. what else in physics isn’t actually “particle-based” at all? Follow me this is where physics starts rewriting itself.

🚨 BREAKING: Electrons just stopped behaving like particles, and started flowing like a perfect liquid. In graphene, scientists just observed a Dirac fluid a state where electrons move collectively with almost zero resistance. Even crazier? It breaks a fundamental law of physics (the Wiedemann–Franz law) by over 200x. This isn’t just a material discovery. It means: Electricity can behave like fluid dynamics Heat and charge can decouple Quantum systems can act like perfect liquids Now think bigger: If electrons can flow like this. what else in physics isn’t actually “particle-based” at all? Follow me this is where physics starts rewriting itself.

TheNewPhysics

70,012 views • 3 months ago

For years Yann LeCun has argued that generative video models can't truly learn physics. DeepMind's Physics-IQ benchmark proved him right, reporting "a striking lack of physical understanding in current generative video models". The best one scored just 29.5%. This CVPR 2026 paper finds the fix in LeCun's own playbook. "Inference-time Physics Alignment" doesn't retrain the generator. It steers a video model's denoising at inference using a reward from VJEPA-2, LeCun's Joint Embedding Predictive Architecture. - Won first place in the ICCV 2025 PhysicsIQ Challenge with a 62.64% score, beating the previous state of the art by 7.42%. - Repurpose VJEPA-2's "surprise" score as a reward, then search and rank multiple candidate denoising trajectories at test time. - Why it matters: It's a neat vindication of LeCun's thesis. The pixel-prediction generator alone doesn't get physics, but the JEPA world model approach he champions supplies the physics the video model lacks.

For years Yann LeCun has argued that generative video models can't truly learn physics. DeepMind's Physics-IQ benchmark proved him right, reporting "a striking lack of physical understanding in current generative video models". The best one scored just 29.5%. This CVPR 2026 paper finds the fix in LeCun's own playbook. "Inference-time Physics Alignment" doesn't retrain the generator. It steers a video model's denoising at inference using a reward from VJEPA-2, LeCun's Joint Embedding Predictive Architecture. - Won first place in the ICCV 2025 PhysicsIQ Challenge with a 62.64% score, beating the previous state of the art by 7.42%. - Repurpose VJEPA-2's "surprise" score as a reward, then search and rank multiple candidate denoising trajectories at test time. - Why it matters: It's a neat vindication of LeCun's thesis. The pixel-prediction generator alone doesn't get physics, but the JEPA world model approach he champions supplies the physics the video model lacks.

Vai Viswanathan

44,186 views • 1 month ago

𝗣𝗼𝗽𝘂𝗹𝗮𝗿 𝗼𝗽𝗶𝗻𝗶𝗼𝗻: "𝗝𝘂𝘀𝘁 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗺𝗼𝗿𝗲 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗱𝗮𝘁𝗮." After working with many 𝗿𝗼𝗯𝗼𝘁 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 teams who've fallen into the simulation trap, here's what I've learned: Simulation teaches your robot to be really, really good at simulation. Unlike blind locomotion policies that can get away with sim-to-real transfer because they rely mainly on proprioception and contact forces, 𝘃𝗶𝘀𝗶𝗼𝗻-𝗴𝘂𝗶𝗱𝗲𝗱 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝗲𝘅𝘁𝗿𝗲𝗺𝗲𝗹𝘆 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗲 𝘁𝗼 𝘃𝗶𝘀𝘂𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻 𝗴𝗮𝗽. The subtle differences accumulate: - Simulated friction vs real surface textures - Perfect lighting vs shadows, reflections, glare - Ideal object geometries vs manufacturing tolerances - Instantaneous sensor readings vs real-world noise and latency - Clean backgrounds vs cluttered, dynamic environments 𝗧𝗵𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗰 𝗽𝗿𝗼𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: Week 1: "Our model works perfectly in sim!" Week 2: "Let's collect some real data to fine-tune." Week 3: "The real data completely contradicts what the sim taught..." Week 4: "Okay, let's collect way more real data." Month 2: "We basically need to retrain from scratch." 𝗧𝗵𝗲 𝗽𝗮𝗶𝗻𝗳𝘂𝗹 𝘁𝗿𝘂𝘁𝗵: There's no shortcut to real-world data collection for vision-based manipulation. Simulation is amazing for debugging, prototyping, safety testing, and of course to supplement your real data. But it's not a substitute for understanding how your robot actually behaves in the actual environment. 𝗪𝗵𝗮𝘁 𝘄𝗼𝗿𝗸𝘀: Use simulation strategically - for exploring edge cases, testing safety boundaries, and rapid iteration. But build your production models on real data from real environments. The teams that succeed treat simulation as a powerful tool, not a magic solution. This is why Neuracore focuses on making real-world data collection so much easier and faster. Because the physics of your actual environment can't be simulated away. 𝗪𝗼𝗿𝗹𝗱 𝗺𝗼𝗱𝗲𝗹𝘀, 𝘆𝗼𝘂 𝘀𝗮𝘆? 𝗪𝗲𝗹𝗹, 𝗽𝗲𝗿𝗵𝗮𝗽𝘀 𝗺𝗼𝗿𝗲 𝗼𝗻 𝘁𝗵𝗮𝘁 𝗶𝗻 𝗮𝗻𝗼𝘁𝗵𝗲𝗿 𝗽𝗼𝘀𝘁! 𝗪𝗵𝗮𝘁'𝘀 𝗯𝗲𝗲𝗻 𝘆𝗼𝘂𝗿 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 𝘄𝗶𝘁𝗵 𝘀𝗶𝗺-𝘁𝗼-𝗿𝗲𝗮𝗹 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿? 𝗛𝗮𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸𝗲𝗱 𝗮𝘀 𝘄𝗲𝗹𝗹 𝗮𝘀 𝗲𝘅𝗽𝗲𝗰𝘁𝗲𝗱?

𝗣𝗼𝗽𝘂𝗹𝗮𝗿 𝗼𝗽𝗶𝗻𝗶𝗼𝗻: "𝗝𝘂𝘀𝘁 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗺𝗼𝗿𝗲 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗱𝗮𝘁𝗮." After working with many 𝗿𝗼𝗯𝗼𝘁 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 teams who've fallen into the simulation trap, here's what I've learned: Simulation teaches your robot to be really, really good at simulation. Unlike blind locomotion policies that can get away with sim-to-real transfer because they rely mainly on proprioception and contact forces, 𝘃𝗶𝘀𝗶𝗼𝗻-𝗴𝘂𝗶𝗱𝗲𝗱 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝗲𝘅𝘁𝗿𝗲𝗺𝗲𝗹𝘆 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗲 𝘁𝗼 𝘃𝗶𝘀𝘂𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻 𝗴𝗮𝗽. The subtle differences accumulate: - Simulated friction vs real surface textures - Perfect lighting vs shadows, reflections, glare - Ideal object geometries vs manufacturing tolerances - Instantaneous sensor readings vs real-world noise and latency - Clean backgrounds vs cluttered, dynamic environments 𝗧𝗵𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗰 𝗽𝗿𝗼𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: Week 1: "Our model works perfectly in sim!" Week 2: "Let's collect some real data to fine-tune." Week 3: "The real data completely contradicts what the sim taught..." Week 4: "Okay, let's collect way more real data." Month 2: "We basically need to retrain from scratch." 𝗧𝗵𝗲 𝗽𝗮𝗶𝗻𝗳𝘂𝗹 𝘁𝗿𝘂𝘁𝗵: There's no shortcut to real-world data collection for vision-based manipulation. Simulation is amazing for debugging, prototyping, safety testing, and of course to supplement your real data. But it's not a substitute for understanding how your robot actually behaves in the actual environment. 𝗪𝗵𝗮𝘁 𝘄𝗼𝗿𝗸𝘀: Use simulation strategically - for exploring edge cases, testing safety boundaries, and rapid iteration. But build your production models on real data from real environments. The teams that succeed treat simulation as a powerful tool, not a magic solution. This is why Neuracore focuses on making real-world data collection so much easier and faster. Because the physics of your actual environment can't be simulated away. 𝗪𝗼𝗿𝗹𝗱 𝗺𝗼𝗱𝗲𝗹𝘀, 𝘆𝗼𝘂 𝘀𝗮𝘆? 𝗪𝗲𝗹𝗹, 𝗽𝗲𝗿𝗵𝗮𝗽𝘀 𝗺𝗼𝗿𝗲 𝗼𝗻 𝘁𝗵𝗮𝘁 𝗶𝗻 𝗮𝗻𝗼𝘁𝗵𝗲𝗿 𝗽𝗼𝘀𝘁! 𝗪𝗵𝗮𝘁'𝘀 𝗯𝗲𝗲𝗻 𝘆𝗼𝘂𝗿 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 𝘄𝗶𝘁𝗵 𝘀𝗶𝗺-𝘁𝗼-𝗿𝗲𝗮𝗹 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿? 𝗛𝗮𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸𝗲𝗱 𝗮𝘀 𝘄𝗲𝗹𝗹 𝗮𝘀 𝗲𝘅𝗽𝗲𝗰𝘁𝗲𝗱?

Stephen James

31,009 views • 11 months ago

In a masterclass at Sequoia Capital AI Ascent, Jim Fan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook. 🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics. 🔹 Teleop → EgoScale: Replacing manual data with human egocentric video. 🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments. "Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics." He believes that robots will pass the Physical Turing Test in the coming 2–3 years.

In a masterclass at Sequoia Capital AI Ascent, Jim Fan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook. 🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics. 🔹 Teleop → EgoScale: Replacing manual data with human egocentric video. 🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments. "Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics." He believes that robots will pass the Physical Turing Test in the coming 2–3 years.

Humanoids daily

12,123 views • 2 months ago

If you are using an if statement inside a for loop, did you know there's a better way of doing this is Swift? I'm talking about the where clause. Using the where clause in a for loop can provide several benefits over using an if statement inside a for loop: Readability: It explicitly states the condition that must be met for an element to be processed, making the purpose of the loop clearer to anyone reading the code. Efficiency: When using a where clause, the filtering of elements is done at the level of the sequence, which can be more efficient than filtering within the loop with an if statement. Brevity: Using a where clause often results in more concise code, as it eliminates the need for an if statement and associated braces. This can make the code more manageable and easier to maintain.

If you are using an if statement inside a for loop, did you know there's a better way of doing this is Swift? I'm talking about the where clause. Using the where clause in a for loop can provide several benefits over using an if statement inside a for loop: Readability: It explicitly states the condition that must be met for an element to be processed, making the purpose of the loop clearer to anyone reading the code. Efficiency: When using a where clause, the filtering of elements is done at the level of the sequence, which can be more efficient than filtering within the loop with an if statement. Brevity: Using a where clause often results in more concise code, as it eliminates the need for an if statement and associated braces. This can make the code more manageable and easier to maintain.

Everton Carneiro

23,416 views • 2 years ago

🚨 SCIENTISTS MAY HAVE DISCOVERED AN ENTIRELY NEW TYPE OF MAGNET. It’s called an altermagnet. And it behaves in a way physicists thought shouldn’t be possible. Unlike normal magnets… the material has almost ZERO net magnetism yet it still behaves electronically like a ferromagnet. That means it may combine: • the stability of antiferromagnets • with the speed and functionality of ferromagnets Researchers just observed a giant magneto-optical Kerr effect inside hematite one of Earth’s most common iron minerals. Why this matters: This could open the door to: • ultra-fast memory • low-power computing • next-generation spintronics • advanced quantum materials • AI hardware beyond silicon The strangest part? The magnetism is hidden in the material’s symmetry itself. Not in obvious magnetic alignment. Physics may have just uncovered an entirely new way matter can store and process information. We are entering the era of programmable quantum materials. Follow for more future physics and technology breakthroughs.

🚨 SCIENTISTS MAY HAVE DISCOVERED AN ENTIRELY NEW TYPE OF MAGNET. It’s called an altermagnet. And it behaves in a way physicists thought shouldn’t be possible. Unlike normal magnets… the material has almost ZERO net magnetism yet it still behaves electronically like a ferromagnet. That means it may combine: • the stability of antiferromagnets • with the speed and functionality of ferromagnets Researchers just observed a giant magneto-optical Kerr effect inside hematite one of Earth’s most common iron minerals. Why this matters: This could open the door to: • ultra-fast memory • low-power computing • next-generation spintronics • advanced quantum materials • AI hardware beyond silicon The strangest part? The magnetism is hidden in the material’s symmetry itself. Not in obvious magnetic alignment. Physics may have just uncovered an entirely new way matter can store and process information. We are entering the era of programmable quantum materials. Follow for more future physics and technology breakthroughs.

TheNewPhysics

26,251 views • 2 months ago

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 views • 7 months ago

Reppo is going multichain, powered by Spicenet will be available to users across Ethereum, Arbitrum, Avalanche, Polygon, Monad, and BNB Chain by mid Feb 2026 We’ve always believed the right way to build in crypto is: Users → Scale → Chain → Accelerate We started by solving real user problems. Now we scale real usage. Only then do chains become an accelerator — not the starting point. Mid-February marks the beginning of our scale phase on steroids. We’re opening the doors to TVL from multiple ecosystems and inviting liquidity, users, and builders to grow with us — together. This is just the beginning. 🚀

Reppo is going multichain, powered by Spicenet will be available to users across Ethereum, Arbitrum, Avalanche, Polygon, Monad, and BNB Chain by mid Feb 2026 We’ve always believed the right way to build in crypto is: Users → Scale → Chain → Accelerate We started by solving real user problems. Now we scale real usage. Only then do chains become an accelerator — not the starting point. Mid-February marks the beginning of our scale phase on steroids. We’re opening the doors to TVL from multiple ecosystems and inviting liquidity, users, and builders to grow with us — together. This is just the beginning. 🚀

Reppo

23,151 views • 5 months ago

New nature paper today : Sony's Ace robot beats 3 of 5 elite table tennis players. Loses to professionals. Human players win points with faster-than-average shots (p<0.001 between won vs returned). Ace wins with ordinary shots. Same speed and spin profile whether it wins or loses the rally (p=0.88). It's playing a completely different sport than the humans are. Trained entirely in simulation. Zero sim-to-real tricks beyond good physics modeling and asymmetric actor-critic (critic sees ground truth, actor sees noisy sensors). Best part — after watching a point, 1992 Olympian Kinjiro Nakamura said: "I didn't think it was possible. But the fact that it was possible... means that there is a possibility that a human could do it too." Code: Paper:

Bo Wang

100,049 views • 2 months ago

🚨 SCIENTISTS JUST WATCHED ATOMS DO SOMETHING THAT LOOKS IMPOSSIBLE Researchers have directly observed atoms inside a crystal transferring angular momentum and then reversing their direction of rotation. Like microscopic Ferris wheels suddenly spinning the opposite way. Using ultra-powerful terahertz laser pulses, physicists tracked atoms moving in precise circular paths inside a quantum material. But during the transfer process, something bizarre happened: The rotational direction flipped. Physicists describe the effect almost like: 1 + 1 = −1 The reversal comes from the hidden symmetry of the crystal itself a quantum effect never directly observed before. Why this matters: • It reveals new foundations of magnetism • It could help scientists control quantum materials • It may lead to ultrafast future memory devices • It exposes deeper rules governing matter itself The strangest part? The atoms weren’t breaking physics. They were obeying an even deeper layer of it. We are starting to see the hidden mechanics underneath reality. Follow for more future physics and quantum breakthroughs.

🚨 SCIENTISTS JUST WATCHED ATOMS DO SOMETHING THAT LOOKS IMPOSSIBLE Researchers have directly observed atoms inside a crystal transferring angular momentum and then reversing their direction of rotation. Like microscopic Ferris wheels suddenly spinning the opposite way. Using ultra-powerful terahertz laser pulses, physicists tracked atoms moving in precise circular paths inside a quantum material. But during the transfer process, something bizarre happened: The rotational direction flipped. Physicists describe the effect almost like: 1 + 1 = −1 The reversal comes from the hidden symmetry of the crystal itself a quantum effect never directly observed before. Why this matters: • It reveals new foundations of magnetism • It could help scientists control quantum materials • It may lead to ultrafast future memory devices • It exposes deeper rules governing matter itself The strangest part? The atoms weren’t breaking physics. They were obeying an even deeper layer of it. We are starting to see the hidden mechanics underneath reality. Follow for more future physics and quantum breakthroughs.

TheNewPhysics

26,543 views • 2 months ago

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

Jim Fan

594,014 views • 2 years ago