Paperplaza overloaded! Hopefully they extend the deadline. When will ICRA move to something like OpenReview, though?
Paperplaza has been notoriously bad for years, and I still wonder why such an outdated site is used in 2026. I feel like I travel back in time to the 2000s when
🚨Final call to submit papers to ICRA 2027!
Today is the last day to submit your papers on PaperPlaza before the portal closes tonight at 11:59 PM PST.
🔗 Submit Here: loom.ly/ua0r_CA
Return of the King! I was fortunate to work with Won during his later years of PhD. He made dexterous manipulation look unfairly easy until I tried it myself. Won’s robots move like how I would want them around my future kids. Congrats!!!
Spent the past six years creating DenseTact sensors, thinking about what happens at our fingertips. Humans make dexterous manipulation look almost unfairly easy: we can pick up and reorient objects without thinking, yet explaining exactly how we do it is surprisingly hard.
I think the “why” of robotics models will always be an important question in research even as models like Astra get better and better. Great work and would be cool to see this SAE paradigm applied to WAMs etc!
Your VLA works. Do you know why?
We use mechanistic interpretability to decompose π0.5 and OpenVLA into sparse features that separate general manipulation primitives from episode-specific memorization, all without running a single rollout.
Introducing Dr. VLA 🩺 #CoRL2026
🧵👇
Lots of people saying ChatGPT moment for robotics. These claims are still quite extreme. The sense of touch is seemingly forgotten in all of this. Tasks like cooking, cleaning those annoying stains, cutting food, picking up fragile objects, require a sense of touch.
Very
