{"683131":{"#nid":"683131","#data":{"type":"event","title":"PhD Defense by Pramod Chunduri","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E: Enabling Semantically Richer Queries over Unstructured Data\u003C\/p\u003E\u003Cp\u003E\u003Cbr\u003E\u003Cstrong\u003EPramod Chunduri\u003C\/strong\u003E\u003Cbr\u003EPh.D. Candidate\u003C\/p\u003E\u003Cp\u003ESchool of Computer Science\u003C\/p\u003E\u003Cp\u003ECollege of Computing\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E: Wednesday, July 23, 2025\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E: 2:00 PM - 4:00 PM ET\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E: Klaus 3100\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOnline\u003C\/strong\u003E:\u0026nbsp;\u003Ca href=\u0022https:\/\/teams.microsoft.com\/l\/meetup-join\/19%3ameeting_YWJlOGE4YjktM2Y4MS00YTVmLWIyNjUtOWE3OGZjMmMzMjAz%40thread.v2\/0?context=%7b%22Tid%22%3a%22482198bb-ae7b-4b25-8b7a-6d7f32faa083%22%2c%22Oid%22%3a%221bd9e6ce-aac7-482a-b32e-21f38a0d6c53%22%7d\u0022\u003EMicrosoft Teams\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EDr. Joy Arulraj (advisor), School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Kexin Rong, School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Xu Chu, School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Shamkant Navathe, School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Ali Payani, Cisco Research\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EQuerying unstructured data such as video, audio, text is critical for domains ranging from traffic surveillance to healthcare and finance. Modern AI models (e.g., vision and language models) unlock significant potential for extracting fine-grained information from unstructured data. However, existing data systems that leverage these models primarily focus on efficiently executing semantically simple queries.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis thesis argues that enabling semantically rich queries over unstructured data requires rethinking both the query execution strategies and the query interfaces. To this end, we introduce three systems designed to support the efficient and accurate processing of semantically rich queries over unstructured data.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFirst, we present Zeus, a video analytics system that efficiently localizes complex actions in videos using a reinforcement learning (RL)-based query executor. By using accuracy-based rewards during query planning, Zeus significantly improves efficiency while meeting user-specified accuracy targets.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENext, we introduce SketchQL, a visual query interface that allows users to sketch complex video moments. SketchQL maps these sketches to fine-grained video moments using a transformer model trained on synthetically generated data. SketchQL significantly enhances the usability and accuracy of fine-grained video moment retrieval.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFinally, we present Halo, a long-context question answering (QA) framework designed for domain-augmented queries. Halo incorporates domain knowledge into the QA pipeline via a Domain Hints interface, allowing users to specify structured suggestions that augment the original query. A three-stage execution pipeline then applies these hints automatically and optimally, improving both the efficiency and accuracy of long-context QA.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EEnabling Semantically Richer Queries over Unstructured Data\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Enabling Semantically Richer Queries over Unstructured Data"}],"uid":"27707","created_gmt":"2025-07-14 19:49:55","changed_gmt":"2025-07-14 19:50:26","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-07-23T14:00:00-04:00","event_time_end":"2025-07-23T16:00:00-04:00","event_time_end_last":"2025-07-23T16:00:00-04:00","gmt_time_start":"2025-07-23 18:00:00","gmt_time_end":"2025-07-23 20:00:00","gmt_time_end_last":"2025-07-23 20:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Klaus 3100 Online: Microsoft Teams","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":""}}}