BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.5//EN TZID:America/Los_Angeles X-WR-TIMEZONE:America/Los_Angeles BEGIN:VEVENT UID:0-1875@hmc.edu DTSTART;TZID=America/Los_Angeles:20261116T163000 DTEND;TZID=America/Los_Angeles:20261116T173000 DTSTAMP:20261106T004412Z URL:https://www.hmc.edu/calendar/events/cs-colloquium-rooting-generative-a i-in-cultural-knowledge-artist-centric-pipelines-for-representing-diverse- hair-types-on-screen-sarah-jobalia/ SUMMARY:CS Research Talk– “Rooting Generative AI in Cultural Knowledge: Artist-Centric Pipelines for Representing Diverse Hair Types on Screen\, ” Sarah Jobalia DESCRIPTION:Machine Learning often relies on massive amounts of data to cap ture relevant patterns. In contexts where experts are performing highly-sk illed tasks\, however\, large datasets can be hard to create\, and seeming ly small miscalculations on the model's part can be disproportionately pro blematic.\n\nSarah Jobalia\, a Stanford University PhD candidate\, will fo cus on the design of virtual 3D hair as a case study to show how grounding AI pipelines in cultural\, scientific and social knowledge produces more realistic\, diverse and reliable results. Virtual hair\, which is both com putationally complex and culturally important to represent faithfully\, is central to adding depth and nuance to the stories we see on screen. In he r research\, she draws upon interdisciplinary insights to define strand te xture as the various distinctive patterns that are formed by forces intern al to a hair strand\, presenting a novel taxonomy for rigorously and conci sely describing texture. Mirroring social understandings of hair\, Jobalia disentangles this texture from the hair’s overall style\, which describ es where the strands fall in relation to the head. Through learning and ge nerating texture and style separately\, she highlights two fundamental but separate aspects of hair\, enabling generation that can capture the essen ce of desired hairstyles. This both yields fast generation of the curly an d afro-textured hair types that previous works struggle to capture and all ows for intuitive user interaction and compatibility with existing artist workflows. Broadly\, these insights show how grounding AI tools in existin g knowledge not only improves results but allows tools to support\, rather than replace\, experts.\nSpeaker\nSarah Jobalia is a PhD candidate in Sta nford University's Computer Science Department\, advised by Ron Fedkiw. He r research centers on building more accessible tools for animation artists to represent characters of all backgrounds on screen. Specifically\, thro ugh the study of hair- both on- and off-screen\, Jobalia uses a combinatio n of computer graphics and machine learning to automatically generate 3D h air styles from just a few images of any subject. By focusing on how hair type affects the way hair looks and moves\, she builds tools that are equi tably representative of all styles. CATEGORIES:Faculty,Staff,Students LOCATION:Galileo Hall\, 240 Platt Blvd.\, Claremont\, CA\, 91711\, United S tates X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=240 Platt Blvd.\, Claremont \, CA\, 91711\, United States;X-APPLE-RADIUS=100;X-TITLE=Galileo Hall:geo: 0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/Los_Angeles X-LIC-LOCATION:America/Los_Angeles BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 TZNAME:PST END:STANDARD END:VTIMEZONE END:VCALENDAR