{"693682":{"#nid":"693682","#data":{"type":"event","title":"PhD Defense by Simar Kareer","body":[{"value":"\u003Cp\u003ETitle: Embodied Intelligence from Human Experience\u003Cbr\u003EDate: Thursday Nov 5 1:00-3:00pm\u003Cbr\u003ELocation: Coda 1015 Vinings\u003C\/p\u003E\u003Cp\u003EZoom: Link\u003Cbr\u003EMeeting ID: 242 927 8475\u003Cbr\u003EPasscode: 423370\u003C\/p\u003E\u003Cp\u003ECommittee:\u003Cbr\u003EJudy Hoffman (Advisor) - School of Information and Computer Science, UC Irvine\u003Cbr\u003EDanfei Xu (Advisor) - School of Interactive Computing, Georgia Tech\u003Cbr\u003ESiddharth Karamcheti - School of Interactive Computing, Georgia Tech\u003Cbr\u003EDhruv Batra - Chief Scientist, Yutori\u003Cbr\u003ESergey Levine - Department of Electrical Engineering and Computer Sciences, UC Berkeley\u003C\/p\u003E\u003Cp\u003EAbstract: Robot foundation models have begun to solve dexterous manipulation tasks with sparks of broad open world generalization. The most promising results are driven by large scale teleoperation, but this data source cannot scale as fast as other sources of data, which has spawned considerable work to learn from human videos. Despite progress here, the human to robot gap makes it difficult to directly transfer capabilities in human video to robot policies, forcing most prior works to introduce some inductive bias. In this thesis, we argue that co-design of training algorithms and data collection systems enables us to directly transfer capabilities from human experience. We begin the thesis by proposing embodied human data, defined as egocentric video paired with 3D hand and head pose tracking, as well as a system to collect it, and an algorithm to train with it. Second, we collect the largest dataset of embodied human data, enabling both controlled scientific exploration as well as large scale training. Third, we find that human to robot transfer emerges in foundation models pretrained across many tasks and embodiments.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EEmbodied Intelligence from Human Experience\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Embodied Intelligence from Human Experience"}],"uid":"27707","created_gmt":"2026-11-02 13:22:42","changed_gmt":"2026-11-02 14:31:06","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-11-05T13:00:00-05:00","event_time_end":"2026-11-05T15:00:00-05:00","event_time_end_last":"2026-11-05T15:00:00-05:00","gmt_time_start":"2026-11-05 18:00:00","gmt_time_end":"2026-11-05 20:00:00","gmt_time_end_last":"2026-11-05 20:00:00","rrule":null,"timezone":"America\/New_York"},"location":"ZOOM","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}