BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20241209T140000
RDATE:20250309T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20251102T010000
RDATE:20260308T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20261101T010000
RDATE:20270314T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20271107T010000
RDATE:20280312T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20281105T010000
RDATE:20290311T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T030000
RDATE:20251102T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20261101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20270314T030000
RDATE:20271107T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20280312T030000
RDATE:20281105T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:4c865e36ecdc893e5fa1693146ab6ce4
CATEGORIES:Lean Seminar
CREATED:20251129T164343
SUMMARY:Hybrid Learning Machines Bridge AI and Physical Modeling
LOCATION:CoRE 431
DESCRIPTION:<p><span data-olk-copy-source="MessageBody" style="color: #212121; font-siz
 e: 11pt;">Recent progress in LLMs has transformed text and code generation,
  yet models still falter on PDEs (partial differential equation) where corr
 ectness, constraints, and physical consequences are critical. This talk exp
 lores how formal LLM reasoning can advance symbolic PDE modeling. First, ou
 r PDE-Controller formalizes informal PDEs, synthesizes solver-ready code, a
 nd plans subgoals to tackle nonconvex control via interactions with externa
 l solvers. Second, our Lean Finder accelerates PDE formalization with a sem
 antics-aware search engine for Lean/Mathlib that retrieves relevant theorem
 s, outperforming GPT models and earning strong reception in the AI-for-math
  community. Together these efforts, our aim is to design a semantics-first 
 LLM (large language model) that autoformalizes informal PDE problems into m
 achine-checked specifications, synthesizes solver-ready code, and plans sub
 goals, closing the loop between formal analysis and LLM reasoning and surpa
 ssing human heuristics across diverse PDEs.</span></p>
CONTACT:Wuyang Chen (Simon Fraser University)
DTSTAMP:20260929T072902
DTSTART;TZID=America/New_York:20251210T140000
DTEND;TZID=America/New_York:20251210T150000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR