BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hackathonmaxxing//EN
CALSCALE:GREGORIAN
X-WR-CALNAME:Hackathons in San Francisco
BEGIN:VEVENT
UID:luma:evt-LxRSyOBELspHQ0t@hackathonmaxxing
DTSTAMP:20261122T163144Z
DTSTART:20261122T220000Z
DTEND:20261123T010000Z
SUMMARY:Sundae Robotics 11: Beyond the Gripper — Teaching Robots Dexterity Through Touch\, Vision\, and Play
URL:https://lu.ma/nsqliiuv?utm_source=hackathonmaxxing&utm_medium=referral&utm_campaign=san-francisco
LOCATION:San Francisco\, CA
DESCRIPTION:🤖🍨 Grab a sundae and join Sundae Robotics\, a private\, invite-only Sunday series bringing together robotics researchers\, founders\, and builders working at the frontier of physical intelligence.\n\nSundae Robotics 11Dexterous Manipulation\, Tactile Perception & Robot LearningFeatured Talk: Beyond the Gripper — Teaching Robots Dexterity Through Touch\, Vision\, and Play\n\nBeyond the Gripper: Teaching Robots Dexterity Through Touch\, Vision\, and Play\n\nKeynote: Akash SharmaResearch Scientist\, Amazon Frontier AI & Robotics · CMU Robotics Institute PhD\n\nRobots that impress in demos still mostly use parallel-jaw grippers\, and true in-hand dexterity remains out of reach. The two standard routes each face fundamental limitations: demonstrations often force humans to act like robots\, while simulation cannot faithfully model touch or real-world vision.\n\nIn this talk\, Akash will present four ingredients that aim to close those gaps.\n\nFirst\, he will introduce PTLD\, which learns tactile policies without ever simulating a tactile sensor by distilling a privileged simulation-trained teacher on real hardware.\n\nHe will then discuss INVAR\, which learns visual invariance once from clean and randomized simulation pairs\, allowing policies trained on clean simulation to transfer zero-shot.\n\nNext\, Akash will present CARD\, which retargets human video\, glove\, and motion-capture demonstrations according to what the hand touches rather than simply how the hand moves.\n\nFinally\, he will discuss DSP\, which turns minutes of human play into goal-conditioned dexterity through autonomous play\, world models\, and distillation.\n\nTogether\, these works point toward a common recipe for scaling dexterous manipulation: let humans be humans\, use a privileged teacher\, scale with the robot's own experience\, and distill what is learned into a deployable policy.\n\nAkash Sharma is a Research Scientist at Amazon Frontier AI & Robotics (FAR)\, where he works with Jitendra Malik on robot hands and dexterous manipulation.\n\nHe r https://lu.ma/nsqliiuv?utm_source=hackathonmaxxing&utm_medium=referral&utm_campaign=san-francisco
END:VEVENT
END:VCALENDAR
