Masoud Moghani

Simulations scale for rigid objects, but deformable objects remain an open frontier. SoftMimicGen generates large-scale training data from just a handful of demonstrations. softmimicgen.github.io

@aaronistan 👌🏻

We are hosting the largest showing of Lume in Palo Alto Bring your own laundry Details below

SONIC training code + Finetuning checkpoint + VLA data collection scripts are open-sourced. Little easter egg on the GEAR-SONIC website too :) github.com/NVlabs/GR00T-W…

@aaronistan pretty cool, congrats!!

Introducing Lume. A lamp that does your chores. Order now. Shipping this summer.

Deformable tasks hit a data and sim bottleneck. SoftMimicGen is a step toward fixing it.

Very cool results from @MasoudMoghani! Some evidence that Point Bridge can enable zero-shot sim2real transfer for deformable objects. x.com/haldar_siddhan…

Deformable manipulation has long stalled simulation adoption. SoftMimicGen reduces this barrier with 4 embodiments, scalable data generation, and proven sim-to-real results. Check out Masoud’s thread below for more!

@Stone_Tao thanks @Stone_Tao

@MasoudMoghani awesome to see this released!

Simulations scale for rigid objects, but deformable objects remain an open frontier. SoftMimicGen generates large-scale training data from just a handful of demonstrations. softmimicgen.github.io

This was a team effort! Great collaborators: Mahdi Azizian, @animesh_garg, @yukez, Sean Huver, @AjayMandlekar Paper: arxiv.org/abs/2603.25725 Website: softmimicgen.github.io Environments and pipeline will be released.

SoftMimicGen is a strict generalization of MimicGen! It handles deformable AND rigid objects. We show this on a rigid cube stacking task. Any task MimicGen can do, SoftMimicGen can do too, plus the entire world of soft object manipulation.

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with. And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far: - We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. - CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. - CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. - CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. - CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap. 3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs. Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real! Link in thread:

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From @NVIDIA @Berkeley_AI @CMU_Robotics @StanfordAILab capgym.github.io 🧵

@bowenwen_me Great work, congrats!

Our paper has been accepted to CVPR 2026🎊. Code will be released very soon! Stay tuned at github.com/NVlabs/Fast-Fo…

Proud to introduce EgoScale: We pretrained a GR00T VLA model on 20K+ hours of egocentric human video and discovered that robot dexterity can be scaled, not with more robots, but with more human data. A thread on 🧵what we learned. 👇

SONIC is now open-source! Generalist whole-body teleoperation for EVERYONE! Our team has long been building comprehensive pipelines for whole-body control, kinematic planner, and teleoperation, and they will all be shared. This will be a continuous update; inference code + model already there, training code and gr00t integration coming soon! Code: github.com/NVlabs/GR00T-W… Docs: nvlabs.github.io/GR00T-WholeBod… Site: nvlabs.github.io/GEAR-SONIC/