They say the best time to tweet about your research was 1 year ago, the second best time is now. With RAI formerly known as Boston Dynamics AI Institute, we present DiffuseCloC - the first guidable physics-based diffusion model. diffusecloc.github.io/website/

Inherent biases and imbalances in robot data can make training steerable VLA policies challenging. We introduce CAST, a method to augment datasets with counterfactuals to induce better language following cast-vla.github.io ← paper, code, data, and more available here! 🧵

Republican and Democratic voters share common ground when it comes to the University of California: Both sides express widespread support for UC, its research, medical centers and ability to elevate the lives of students, a statewide poll shows. (via Los Angeles Times)

Want more scaling laws for value-based RL? Preston and I analyzed scaling model size! Larger models predictably improve data efficiency, performance, reduce overfitting, and allow using larger batch size. After this, I am now more optimistic than ever abt TD-learning.

Ever wish a robot could just move to any goal in any environment—avoiding all collisions and reacting in real time? 🚀Excited to share our #CoRL2025 paper, Deep Reactive Policy (DRP), a learning-based motion planner that navigates complex scenes with moving obstacles—directly

Happy to announce that we have finally open sourced the code for DextrAH-RGB along with Geometric Fabrics: github.com/NVlabs/DEXTRAH github.com/NVlabs/FABRICS

Come find us at CoRL!

It’s live! 🎉 🗺️ It was very fun working with Nikhil Keetha and our team Meta for this release. I’m excited to see how the community uses it. 😃

Should robots have eyeballs? Human eyes move constantly and use variable resolution to actively gather visual details. In EyeRobot (eyerobot.net) we train a robot eyeball entirely with RL: eye movements emerge from experience driven by task-driven rewards.

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

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.

Best student paper at CoRL 🎉 Not pictured but not possible without Junyi Zhang Anthony Zhang

Clean and well-executed new work from Danijar Hafner Wilson Yan , and it's cool to see shortcut models working at scale! The exciting finding is that you can train the world model largely on *unlabelled* videos, and only need a small action-anchoring dataset.

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR

📢 SceneComp @ ICCV 2025 🏝️ 🌎 Generative Scene Completion for Immersive Worlds 🛠️ Reconstruct what you know AND 🪄 Generate what you don’t! 🙌 Meet our speakers Angela Dai, Aleksander Holynski, Varun Jampani, Zan Gojcic Andrea Tagliasacchi 🇨🇦, Peter Kontschieder scenecomp.github.io #ICCV2025

Teaching a humanoid just from a random iPhone recording? The Conference on Robot Learning's best student paper, VideoMimic, does just that: takes a video of a human acting, and teaches a robot do the same. How? (1/5) 🧵

A nice surprise! Fully open source reproduction of Decentralized Diffusion Models. Congrats to the team!

Everyone says they want general-purpose robots. We actually mean it — and we’ll make it weird, creative, and fun along the way 😎 Recruiting PhD students to work on Computer Vision and Robotics UMD Department of Computer Science for Fall 2026 in the beautiful city of Washington DC!

✨Introducing ECHO, the newest in-the-wild image generation benchmark! You’ve seen new image models and new use cases discussed on social media, but old benchmarks don’t test them! We distilled this qualitative discussion into a structured benchmark. 🔗 echo-bench.github.io

Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵