The secret behind this demo by Sudharshan Suresh #RSS2025 Keypoints, object poses, defined grasps and MPC

Checkout DemoDiffusion from Homanga Bharadhwaj! The key idea is quite simple: denoise from human trajectories instead of random noise! I am hopeful to see this scaled up to more complex embodiments!

Research arc: ⏪ 2 yrs ago, we introduced VRB: learning from hours of human videos to cut down teleop (Gibson🙏) ▶️ Today, we explore a wilder path: robots deployed with no teleop, no human demos, no affordances. Just raw video generation magic 🙏 Day 1 of faculty life done! 😉

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the

Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos Kaihua Chen, Tarasha Khurana, Deva Ramanan tl;dr: in title; fine-tune CogVideoX->train 2D video-inpainter arxiv.org/abs/2507.12646

Cool work! Diffusion models have been used for out and in painting 2d images already. Quite smart to use these priors for automatically completing unseen regions in dynamic scenes. I can see this being a quick boost for many robotics applications!

Absolutely love viser! It's so easy to setup both robot and computer vision visualizations with it, and it can directly make it to the paper as well :) Thanks Brent Yi and co

As promised, we are starting to dive deep, beginning with Skild AI Brain's general-purpose perceptive locomotion capability. Mesmerizing to see a full-size humanoid go over any obstacles effortlessly. All through a single end-to-end model: from pixels to action.

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters…

Sparsh-X is our new 'multi-sensory' rep model showing the power of encoding multiple tactile modalities for dexterity. We saw performance for plug insertion go up to 90% success with all modalities, and higher robustness with sim-to-real policies adapted to use Sparsh-X!

I am particularly excited about how Sparsh-X enables easy sim-to-real transfer of proprioception-only dexterous manipulation policies through tactile adaptation and a few real rollouts x.com/carohigueraria…

With the release of Sparsh-X, we have also finally released the code & dataset for Sparsh-skin in tandem as well! Sparsh-X tweet thread: x.com/carohigueraria… Code: github.com/facebookresear… Both papers will be at CoRL (as Oral and Poster respectively) this year!

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art

Introducing: Hyperscape Capture 📷 Last year we showed the world's highest quality Gaussian Splatting, and the first time GS was viewable in VR. Now, capture your own Hyperscapes, directly from your Quest headset in only 5 minutes of walking around. meta.com/experiences/87…

Flying out for CoRL from Pittsburgh today! It's already exciting to hear robotics conversations around. Looking forward to see both new and familiar faces. I will be presenting Sparsh-X (Oral presentation session 3) and Sparsh-skin (Poster session 3)!

Finally had a chance to listen through this pod with Sutton, which was interesting and amusing. As background, Sutton's "The Bitter Lesson" has become a bit of biblical text in frontier LLM circles. Researchers routinely talk about and ask whether this or that approach or idea

Very proud of the first work on legged humanoids from our newly founded Amazon FAR team!

CogNVS was accepted to NeurIPS Conference 2025! 🎉We are releasing the code today for you all to try: 🆕Code: github.com/Kaihua-Chen/co… Paper: arxiv.org/pdf/2507.12646 With CogNVS, we reformulate dynamic novel-view synthesis as a structured inpainting task: (1) we reconstruct input

A reminder that accurate motion estimation sparse visual SLAM has been in the domain of industry for many years now, and what you might often see in academic papers as the "state of the art" is fairly meaningless. (From Paul-Edouard Sarlin @pesarlin.bsky.social.bsky.social)

One of the reasons for spending sabbatical time at CMU, was to meet new people. Just finished a GREAT walk and talk with Tarasha Khurana It was a pleasure meeting you Tarasha, keep in touch! Check out her work: cs.cmu.edu/~tkhurana/