BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Eastern Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN=Crystal D O'Neal:mailto:cdoneal@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=bmegradst udents-list@ecn.purdue.edu:mailto:bmegradstudents-list@ecn.purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Audrey H Sherwood:mailto:asherwo@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Darla Daw n Wetli:mailto:ddwetli@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Robin D T erwilliger:mailto:rterwill@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Rebecca P eer:mailto:peerb@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Leza R De llinger:mailto:lrdellin@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Teresa L DeMien:mailto:tdemien@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Victoria Ann Wunderlich:mailto:vwunder@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Lisa A St acey:mailto:staceyl@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Joshua Go nzalez:mailto:jgonzal@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Kellie A Reece:mailto:kreece@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Lori Elai ne Griffey:mailto:legriffe@purdue.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN="Jurss, Ka ren L":mailto:kjurss@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=bmefacult y-list@ecn.purdue.edu:mailto:bmefaculty-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Luis Solo rio:mailto:lsolorio@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Ilias Bil ionis:mailto:ibilion@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Fang Huan g:mailto:huang892@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Hector Go mez:mailto:hectorgomez@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Arezoo Ar dekani:mailto:ardekani@purdue.edu ATTACH:CID:34839B0608E77A40A7795943DB006A31@namprd22.prod.outlook.com ATTACH:CID:895C9029AE357C468CD252EC4E809B42@namprd22.prod.outlook.com ATTACH:CID:image001.jpg@01DCAFB0.3F50FF50 DESCRIPTION;LANGUAGE=en-US:Please feel free to share with any/all who may b e interested.\n\nBME Seminar\nMonday\, March 9\, 2026\n2:00 – 3:00 pm\, MJIS 2001\nMicrosoft Teams meeting\nJoin: https://teams.microsoft.com/meet /29576486050725?p=8x7wzEiwd7p8GmY4WA \nMeeting ID: 295 764 860 507 25\nPasscode: XW9iM6sh\n\n“Generative AI f or 3D Reconstruction in Cryo-Electron Microscopy”\n\n[cid:image001.jpg@0 1DCAFB0.3F50FF50]\n\nYilai Li\, PhD\nResearch Scientist\, ByteDance Seed\, AI-for-Science\n\n\nAbstract: Single-particle cryo-electron microscopy (c ryo-EM) determines 3D biomolecular structure by computationally reconstruc ting it from extremely noisy experimental 2D projections of individual par ticles with unknown orientations. In real datasets\, reconstructions are o ften limited by dataset-specific corruptions such as anisotropy from uneve n viewing angles or spatially varying signal-to-noise ratios\; more fundam entally\, cryo-EM 3D reconstruction is an ill-posed inverse problem that b enefits from informative priors. In this talk\, I will introduce cryoFM\, a generative foundation model trained on large collections of experimental electron density maps\, and serves as a Bayesian prior for cryo-EM 3D rec onstruction. By pairing this learned prior with different explicit measure ment models\, we use posterior sampling to address a range of reconstructi on and map-improvement tasks. I will highlight representative examples whe re our approach improves cryo-EM 3D reconstruction under challenging condi tions\, and conclude with broader directions for extending generative prio rs and inference beyond the current reconstruction setting.\n\n\nBio: Dr. Yilai Li is a Research Scientist at ByteDance Seed developing AI/ML method s for cryo-electron microscopy (cryo-EM) reconstruction. He received his P h.D. in Biophysics and completed postdoctoral training at the University o f Michigan\, where he worked on computational and automated methods for cr yo-EM data acquisition and processing. His research focuses on combining m odern AI with principled modeling to make cryo-EM analysis more accurate\, robust\, and accessible.\n\n\n___________________________________________ _____________________________________\nMicrosoft Teams meeting\nJoin: http s://teams.microsoft.com/meet/29576486050725?p=8x7wzEiwd7p8GmY4WA\nMeeting ID: 295 764 860 507 25\nPasscode: XW 9iM6sh\n________________________________\nNeed help? | System re ference\nDial in by phone\n+1 219-293-4410\,\,50899 930# United States\, Gary\nFind a local numb er\nPhone conference ID: 508 999 30#\nJoin on a video conferencing device\nTenant key: purdue@m .webex.com\nVideo ID: 119 610 093 5\nMore info< https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.webe x.com%2Fmsteams%3Fconfid%3D1196100935%26tenantkey%3Dpurdue%26domain%3Dm.we bex.com&data=05%7C02%7Cbmegradstudents-list%40ecn.purdue.edu%7C899fa35b72f 8487f68e308de7de99cae%7C4130bd397c53419cb1e58758d6d63f21%7C1%7C0%7C6390866 39719070366%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMD AwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata= NFoAkEczuPhvoo8uY%2BgACzHZLS9g5kVE8eFfi7eOmpI%3D&reserved=0>\nFor organize rs: Meeting options | Reset dial-in PIN \n________________________________________________________________________ ________\n\n UID:040000008200E00074C5B7101A82E00800000000A00E6D8408ABDC01000000000000000 0100000008451428B97BEF442999F175A3E8A937C SUMMARY;LANGUAGE=en-US:Yilai Li - Seminar Purdue AI‑Driven Biomolecular D esign\, Biotech & Computational Biology Position DTSTART;TZID=Eastern Standard Time:20260309T140000 DTEND;TZID=Eastern Standard Time:20260309T150000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20260309T143900Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:2 LOCATION;LANGUAGE=en-US:MJIS 2001/Teams X-MICROSOFT-CDO-APPT-SEQUENCE:2 X-MICROSOFT-CDO-OWNERAPPTID:447297514 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-ONLINEMEETINGINFORMATION:{"OnlineMeetingChannelId":null\,"Onlin eMeetingProvider":3} X-MICROSOFT-SKYPETEAMSMEETINGURL:https://teams.microsoft.com/l/meetup-join/ 19%3ameeting_YWEyZWFjN2YtZGZhNy00OWUyLTk4MjgtYmZiMmJhY2ZkZGUy%40thread.v2/ 0?context=%7b%22Tid%22%3a%224130bd39-7c53-419c-b1e5-8758d6d63f21%22%2c%22O id%22%3a%22df347d6f-ac43-4e29-a82a-129a7532453a%22%7d X-MICROSOFT-SCHEDULINGSERVICEUPDATEURL:https://api.scheduler.teams.microsof t.com/teams/4130bd39-7c53-419c-b1e5-8758d6d63f21/df347d6f-ac43-4e29-a82a-1 29a7532453a/19_meeting_YWEyZWFjN2YtZGZhNy00OWUyLTk4MjgtYmZiMmJhY2ZkZGUy@th read.v2/0 X-MICROSOFT-SKYPETEAMSPROPERTIES:{"cid":"19:meeting_YWEyZWFjN2YtZGZhNy00OWU yLTk4MjgtYmZiMmJhY2ZkZGUy@thread.v2"\,"private":true\,"type":0\,"mid":0\," rid":0\,"uid":null} X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:TRUE X-MICROSOFT-REQUESTEDATTENDANCEMODE:DEFAULT X-MICROSOFT-ISRESPONSEREQUESTED:FALSE X-MICROSOFT-LOCATIONS:[ { "DisplayName" : "MJIS 2001/Teams"\, "LocationAnno tation" : ""\, "LocationSource" : 0\, "Unresolved" : true\, "LocationUri" : "" } ] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT15M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR