Gavriel State

@KyleMorgenstein @LouisLeLay4 @ChongZitaZhang MJWarp definitely has more knobs that can be turned, and I do expect that most projects will want to tune a few of them. The main point though is that we’re providing flexibility here. You can still stick with PhysX only and existing parameters if you want too

@gavrielstate @LouisLeLay4 @ChongZitaZhang do you think for most use cases (assuming you want to deploy on real robot) people will leave the defaults vs tune? from the migration docs it looked like the “after” code is almost strictly longer/more verbose than “before” but that’s also because it’s supporting more etc

This is why we need Newton

@KyleMorgenstein @LouisLeLay4 @ChongZitaZhang We're going to see if we can simplify this for PyTorch, but warp arrays as the main interface enables using a fullly graphed warp front end. That provides significant speedups - 30-50% or more in our tests.

@LouisLeLay4 @ChongZitaZhang also you have to cast from warp to torch like shrapnel everywhere

@KyleMorgenstein @LouisLeLay4 @ChongZitaZhang Hey @KyleMorgenstein - this is verbose because it shows tuned Newton/MJWarp parameters. If you don’t need multi-backend presets and defaults are ok, you can keep it minimal. Presets are there for flexibility, not a requirement.

@LouisLeLay4 @ChongZitaZhang :( #migrating-to-isaaclab-3-0" target="_blank" rel="nofollow noopener">isaac-sim.github.io/IsaacLab/devel…

We have seen rapid progress in humanoid control — specialist robots can reliably generate agile, acrobatic, but preset motions. Our singular focus this year: putting generalist humanoids to do real work. To progress toward this goal, we developed SONIC (nvlabs.github.io/GEAR-SONIC/), a Behavior Foundation Model for real-time, whole-body motion generation that supports teleoperation and VLA inference for loco-manipulation. Today, we’re open-sourcing SONIC on GitHub. We are excited to see what the community builds upon SONIC and to collectively push humanoid intelligence toward real-world deployment at scale. 🌐 Paper: arxiv.org/abs/2511.07820 📃 Code: github.com/NVlabs/GR00T-W…

@AKurian001 Are you using an iPhone with local tonemapping turned on? PPISP does not model that. You can use different camera apps to try disabling that functionality.

This journey started for us attempting reconstruction of multicamera AV scenes with huge photometric differences like the one below. We wanted a principled way to handle ISP effects in #3DGS, which became PPISP. Big congrats to Isaac Deutsch, Nicolas Moenne-Loccoz and @ZGojcic !

@siddancha I consider that part of my professional responsibility…😀

Am I the only one who sees a robotics paper on Twitter and the first thing I search is what simulator was used to produce those visuals? 🤖

I'm super excited for the future of Real2Sim2Real workflows on top of our new VoMP pipeline. There's still work ahead to integrate it into Isaac Lab through solvers in Newton and get simulation running fast enough for RL, but this is an important start. Congrats @rishit_dagli!

Great new blog post from Isaac Deutsch and Wonsik Han on the NVIDIA NuRec team showing how to generate a high quality 3D reconstruction for use with Isaac Sim and Isaac Lab!

Penetration-free for free, you need OGC. I released the code of our SIGGRAPH 2025 paper: Offset Geometric Contact, where we made real-time, penetration free simulation possible, with @JerryHsu32 @zihengliu @milesmacklin @YinYang24414350 @cem_yuksel Page: ankachan.github.io/Projects/OGC/i…

Let's hear it for the community. 🎉 The Newton project, an open-source physics engine for robotics simulation, is now part of the @linuxfoundation. This is a huge step toward building a truly community-driven future for robotics research and development.

@ChongZitaZhang It should be up on arXiv in a few more days after we get done with some last tweaks…

Finally we don't need to cite orbit

Very happy to share our new Isaac Lab white-paper that @yukez just announced at CoRL! research.nvidia.com/publication/20… This is the product of a tremendous amount of work from many teams at NVIDIA plus many folks from RAI and ETH. Congrats to the whole team!

Our latest work performs sim2real dexterous grasping using end-to-end depth RL.

I’m looking forward to chatting with anyone going to CoRL about Isaac Lab and Newton! The meetings we had at CoRL last year were key to some of the decisions we’ve made since then, including starting the Newton project. Sign up below!

Together with Aaron Lefohn and Sanja Fidler, we will give a special address at SIGGRAPH. Specifically, I will give an update on our vision and our current work in enabling Physical AI. Please join us. nvidia.com/en-us/events/s…

The Dex team at NVIDIA is defining the bleeding edge of sim2real dexterity. Take a look below 🧵 There's a lot happening at NVIDIA in robotics, and we’re looking for good people! Reach out if you're interested. We have some big things brewing (and scaling :)

@wang_jianren It looks like you were not able to reproduce our DexPBT results for PBT with some of the tasks, like dual-arm regrasping and reorientation. We had significantly better results with PBT compared to what you show. Did you have some trouble with the code?

(1/n) Since its publication in 2017, PPO has essentially become synonymous with RL. Today, we are excited to provide you with a better alternative - EPO.

#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 ➡️nvda.ws/4n0XN6g #GTCParis #VivaTech

Join experts Yuval Tassa from @GoogleDeepMind and Miles Macklin from NVIDIA at #GTCParis to learn about Newton, an open-source, extensible physics engine for robotics simulation, co-developed by Disney Research, Google DeepMind and NVIDIA. Gain insights into breakthroughs in #humanoidrobot development and the collaboration that’s bridging simulation, AI, and #robotics. Learn more ➡️nvda.ws/4467f0A #VivaTech