{"693752":{"#nid":"693752","#data":{"type":"event","title":"CSIP Seminar | Yuheng Bu","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETalk Title:\u003C\/strong\u003E Rethinking LLM Watermarking: From Theory to In-Context Methods\u003Cbr\u003E\u003Cstrong\u003ESpeaker: \u003C\/strong\u003EYuheng Bu, Assistant Professor in the Department of Computer Science at the University of California, Santa\u003Cbr\u003EBarbara\u003Cbr\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E Friday, November 13, 2026\u003Cbr\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E 3:00 p.m. - 4:00 p.m.\u003Cbr\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E CSIP Library \u2014 Room 5126, Centergy One, 5th Floor\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E LLM watermarking has emerged as a promising tool for attributing AI-generated text, but its practical deployment\u003Cbr\u003Eremains limited. In this talk, I will first present a unified theoretical framework that jointly optimizes watermark\u003Cbr\u003Edesign and detection, characterizing the fundamental trade-off between detectability, false positive control, and text\u003Cbr\u003Edistortion. While this formulation yields sharp optimality insights, it typically requires the LLM provider to implement\u003Cbr\u003Ethe watermark during generation, which has limited its deployment in practice. I will then discuss the reasons\u003Cbr\u003Ebehind this gap, emphasizing stakeholder incentives and real-world deployment constraints. Motivated by these\u003Cbr\u003Echallenges, I will present in-context watermarking, a model-agnostic approach that embeds detectable signals\u003Cbr\u003Ethrough prompts rather than decoding-time access. This perspective suggests that effective watermarking requires\u003Cbr\u003Enot only strong algorithms, but also incentive-aligned designs tailored to practical domains such as peer review\u003Cbr\u003Eand education.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio: \u003C\/strong\u003EYuheng Bu is an Assistant Professor in the Department of Computer Science at the University of California, Santa\u003Cbr\u003EBarbara. His research lies at the intersection of information theory, machine learning, and trustworthy AI. He\u003Cbr\u003Ereceived the NSF CAREER Award in 2026. Before joining UC Santa Barbara, he was an Assistant Professor in the\u003Cbr\u003EDepartment of Electrical and Computer Engineering at the University of Florida. Prior to that, he was a Postdoctoral Research Associate at the Research Laboratory of Electronics and the Institute for Data, Systems, and Society at the Massachusetts Institute of Technology. He received his Ph.D. in 2019 from the Coordinated Science Laboratory and the Department of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign. He earned his B.S. degree with honors in Electronic Engineering from Tsinghua University in 2014.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EJoin University of California, Santa Barbara Computer Science Assistant Professor Yuheng Bu for a talk on Rethinking LLM Watermarking.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Join University of California, Santa Barbara Computer Science Assistant Professor Yuheng Bu for a talk on Rethinking LLM Watermarking."}],"uid":"36558","created_gmt":"2026-11-03 22:46:48","changed_gmt":"2026-11-03 22:50:23","author":"zwiniecki3","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-11-13T15:00:00-05:00","event_time_end":"2026-11-13T16:00:00-05:00","event_time_end_last":"2026-11-13T16:00:00-05:00","gmt_time_start":"2026-11-13 20:00:00","gmt_time_end":"2026-11-13 21:00:00","gmt_time_end_last":"2026-11-13 21:00:00","rrule":null,"timezone":"America\/New_York"},"location":"CSIP Library \u2014 Room 5126, Centergy One, 5th Floor","extras":["free_food"],"groups":[{"id":"1255","name":"School of Electrical and Computer Engineering"}],"categories":[],"keywords":[{"id":"5611","name":"CSIP Seminar Series"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"194683","name":"Talk"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}