Thrilled to introduce our new work RACER ! 🌟A great journey with Jayjun Lee @ CoRL 2025 to explore the role of rich language guidance for failure recovery in robotic manipulation. Exciting times to work on VLM+robotics🤖🚀

Do Vision-Language Models represent space, and how? Spatial terms like "left" or "right" may not be enough to match images with spatial descriptions, as we often overlook the different frames of reference (FoR) used by speakers and listeners. See Figure 1 for examples!

Thanks for the award!

Do Vision-Language Models represent space, and how? Introducing 🛋️COnsistent Multilingual Frame Of Reference Test (COMFORT), an evaluation protocol to assess the spatial reasoning in VLMs under ambiguities. 🌐 spatial-comfort.github.io 📄 arxiv.org/abs/2410.17385 More👇

COMFORT got accepted to ICLR 2026 #ICLR2025!

Oral presentation at ICLR!

Atlas is demonstrating reinforcement learning policies developed using a motion capture suit. This demonstration was developed in partnership with Boston Dynamics and RAI Institute.

We’re presenting RACER today 3:25 pm in Room 411 @ #ICRA2025! Check out our work if you’re interested in steering policies with language and System 1-System 2 frameworks for robot learning! Come say hi!

👀🤚 Robots that see and feel at once! ViTaSCOPE fuses point-cloud vision with high-res tactile shear to nail in-hand 6-DoF pose plus contact patches—trained entirely in sim, zero-shot on hardware. Dive into the demos 👇 jayjunlee.github.io/vitascope/ #RSS2025 #robotics #tactileSensing

Exciting to see the VIRDO framework extend to both (1) in-hand pose + extrinsic contact estimation and (2) high-res tactile sensing — very interesting direction!

Just gave my first oral presentation today in Manipulation I session at RSS! Come check out my poster at #6 too!

Thanks AK for sharing our work! The core takeaway from AimBot is straightforward: explicit spatial cues (as shooting lines & scope reticles) are strong 2.5D augmentations that enhance the spatial grounding of any VLA models. These cues are interpretable and also

Thanks AK for posting our work! And I'm happy to share that AimBot 🎯 is accepted to CoRL 2025 Conference on Robot Learning! See you in Seoul! Project webpage: aimbot-reticle.github.io Thanks to my amazing co-lead Yinpei Dai, co-authors, and our advisors Nima Fazeli, Michigan SLED Lab

I’m co-organizing the H2R workshop and we’re starting soon! Come join our session in Room E3. sites.google.com/view/h2r-corl2…