In LLM land, a slow model is annoying. In robotics, a slow model can be disastrous! Visible pauses at best, dangerously jerky motions at worst. But large VLAs are slow by nature. What can we do about this? An in-depth 🧵:

Had a great time at this CVPR community-building workshop---lots of fun discussions and some really important insights for early-career researchers. I also gave a talk on "Research as an Infinite Game." Here are the slides: canva.com/design/DAGp0iR…

🥋 We're excited to share judo: a hackable toolbox for sampling-based MPC (SMPC), data collection, and more, designed to make it easier to experiment with high-performance control. Try it: pip install judo-rai

Everyone knows action chunking is great for imitation learning. It turns out that we can extend its success to RL to better leverage prior data for improved exploration and online sample efficiency! colinqiyangli.github.io/qc/ The recipe to achieve this is incredibly simple. 🧵 1/N

Had so much fun working on this😊 PyTorch and JAX implementations are both out!

Excited to share Flow Matching Policy Gradients: expressive RL policies trained from rewards using flow matching. It’s an easy, drop-in replacement for Gaussian PPO on control tasks.

Viser: Imperative, Web-based 3D Visualization in Python Brent Yi, Chung Min Kim, Justin Kerr, Gina Wu, Rebecca Feng, Anthony Zhang, Jonas Kulhanek, Hongsuk Benjamin Choi, Yi Ma, Matthew Tancik, Angjoo Kanazawa tl;dr: in title arxiv.org/abs/2507.22885

Anything is possible with Viser!

Congrats to Viser 1.0.0! Such a gift to the open source community from Brent Yi !

Viser is an incredibly powerful and easy-to-use 3D visualization tool for robotics and 3D vision research. You can visualize 3D videos, interact with IsaacGym and MuJoCo robots, and much more — all with an intuitive and customizable interface. This is a game changer for anyone

viser has been the biggest quality of life improvement for me in years for visualising robotic data & sim / debugging policies. congrats to brent on the release and check it out!

Brent makes *really* high quality software and viser is no exception. I’ve learned so much from him over the years! Congrats on this significant milestone ❤️

🤖 Initial code release is up for VideoMimic Real2Sim! github.com/hongsukchoi/Vi… VideoMimic is a real-to-sim-to-real pipeline for deploying humanoids in the real world. It supports: - Human motion capture from video - Environment reconstruction for simulation from video -

I often find myself using #Genie3 for virtual tourism, or to revisit places from my past. Here's a world that I built to look like my hometown (San Juan, Puerto Rico). There's no place like (actual) home, but this helps scratch the itch when a 13-hour trip isn't an option.

Very handy and well-engineered toolbox run with speed-of-light. Led by Jiahui Huang at NVIDIA AI. Project page: research.nvidia.com/labs/toronto-a…

Viser completely changed the way we do research. Before viser, it was hard to visualize 3D/4D data, let alone share it. Now it’s all just in a browser! It’s amazingly powerful and looks awesome. It’s how we render our results and videos. We love it and hope you will too!

Want to achieve extreme performance in motion tracking—and go beyond it? Our preprint tech report is now online, with open-source code available!

Introducing Masquerade 🎭: We edit in-the-wild videos to look like robot demos, and find that co-training policies with this data achieves much stronger performance in new environments. ❗Note: No real robots in these videos❗It’s all 💪🏼 ➡️ 🦾 🧵1/6