{"674419":{"#nid":"674419","#data":{"type":"event","title":"PhD Proposal by Gaurav Verma","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E:\u0026nbsp;Robust and Efficient Vision-Language Learning for Equity, Safety, and Well-Being\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E:\u0026nbsp;Thursday, May 02, 2024\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E:\u0026nbsp;11:15 AM to 1:00 PM Eastern Time (US)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E:\u0026nbsp;Coda C1315\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EVirtual Meeting\u003C\/strong\u003E: \u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/99750215357?pwd=SmJraGU2OCtsdUE5VjQ4dlJSdzVBZz09\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/99750215357?pwd=SmJraGU2OCtsdUE5VjQ4dlJSdzVBZz09\u0022\u003EZoom\u003C\/a\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EGaurav Verma\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/gaurav22verma.github.io\/\u0022\u003Ehttps:\/\/gaurav22verma.github.io\/\u003C\/a\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECS Ph.D. Student\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Computational Science and Engineering\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECollege of Computing\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E:\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Srijan Kumar - Advisor, Georgia Tech, Computational Science \u0026amp; Engineering\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Munmun De Choudhury - Georgia Tech, School of Interactive Computing\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Duen Horng (Polo) Chau - Georgia Tech, Computational Science \u0026amp; Engineering\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Ani Nenkova - Adobe Research\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E:\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe long-term goal of developing Artificial Intelligence (AI) systems is to enable broadly useful human-AI interactions for individuals, groups, and societies. The future of such AI systems is inherently multimodal, and the current shift in the landscape of AI research and development is a great illustration\u2013powerful systems that reason over and generate vision, language, audio, and other forms of unstructured data are emerging rapidly. The robustness and efficiency of multimodal AI are imperative for enabling its widespread adoption. Furthermore, since AI tools are socio-technical systems, it is also critical that societal dimensions like equity, safety and well-being are prioritized among its applications. To this end, the objective of this thesis proposal is to evaluate and efficiently strengthen the robustness of vision-language learning to steer AI development towards enhancing language equity, online safety, and individual \u0026amp; public well-being.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EHow far are we from achieving \u0027three nines\u0027 reliability in multimodal AI systems? How do we get there? \u003C\/em\u003EIt is important that the underlying vision-language models that power AI applications are robust to both unintentional and intentional variations in input data. This requires systematic and efficient approaches to evaluate their robustness and overcome observed vulnerabilities.\u0026nbsp;This thesis proposal presents work that develops systematic methods to \u003Cstrong\u003Eevaluate the robustness of vision-language learning models\u003C\/strong\u003E\u0026nbsp;to \u003Cem\u003Eplausible\u003C\/em\u003E\u0026nbsp;changes in the input data \u2013 specifically, cross-modal dilutions and insertions. Furthermore, we propose \u003Cstrong\u003Emodeling of text visualness as an efficient approach to perform text-to-image mapping\u003C\/strong\u003E\u0026nbsp;in long-form content generation tasks.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EArtificial Intelligence for Equity, Safety, and Well-Being.\u003C\/em\u003E\u0026nbsp;This thesis proposal aims to deliver three-pronged advances along important societal dimensions: \u003Cem\u003E(i) \u003C\/em\u003Ehighlighting the \u003Cstrong\u003Elanguage inequities \u003C\/strong\u003Ethat could be propagated by the use of\u0026nbsp;language-only models and proposing vision-language learning as an approach to enable more equitable outcomes across English and non-English languages, \u003Cem\u003E(ii) \u003C\/em\u003Edeveloping AI approaches to enhance the \u003Cstrong\u003Esafety \u003C\/strong\u003Eof online spaces in a community-centric manner, specifically by characterizing and detecting malicious speech and actors, and \u003Cem\u003E(iii) \u003C\/em\u003Eusing language models to discover insights that can inform policies for improving individual and public \u003Cstrong\u003Ewell-being\u003C\/strong\u003E.\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ERobust and Efficient Vision-Language Learning for Equity, Safety, and Well-Being\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"Robust and Efficient Vision-Language Learning for Equity, Safety, and Well-Being"}],"uid":"27707","created_gmt":"2024-04-26 22:14:35","changed_gmt":"2024-04-26 22:15:24","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-05-02T11:15:27-04:00","event_time_end":"2024-05-02T13:00:00-04:00","event_time_end_last":"2024-05-02T13:00:00-04:00","gmt_time_start":"2024-05-02 15:15:27","gmt_time_end":"2024-05-02 17:00:00","gmt_time_end_last":"2024-05-02 17:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Coda C1315","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":""}}}