BEGIN:VCALENDAR
PRODID:-//github.com/ical-org/ical.net//NONSGML ical.net 4.0//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T020000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T020000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:"Learning to Reason with Multimodal Large Language Models" by 
 Jingyi Zhang\, PhD\, postdoctoral associate in biomedical informatics & d
 ata science Multimodal large language models (MLLMs) have demonstrated re
 markable capabilities across a wide range of vision and language tasks. H
 owever\, developing MLLMs with strong human-like reasoning abilities rema
 ins a key challenge\, especially in complex\, real-world domains such as 
 healthcare. In this talk\, I will share my recent exploration of enhancin
 g the reasoning capabilities of MLLMs. I will first introduce our efforts
  to improve the general reasoning ability of MLLMs through supervised fin
 e-tuning on high-quality multimodal chain-of-thought (CoT) data\, which a
 re searched and generated using a novel tree search algorithm across a wi
 de range of application domains. Moving further\, I will introduce our st
 udy on exploiting online reinforcement learning techniques (e.g.\, GRPO) 
 that incentivize the model to actively explore alternative reasoning path
 s\, unlocking deeper reasoning capabilities through self-improvement. Fin
 ally\, I will discuss whether synthetic data is ready to address data sca
 rcity and the high cost of data annotation in MLLMs\, with a focus on dev
 eloping effective data synthesis methods that can automatically generate 
 multimodal training data to improve MLLMs’ ability to solve complex real-
 world tasks.\n\nSpeaker:\nJingyi Zhang\n\nAdmission:\nFree\n\nFood:\nSnac
 ks\n\nDetails URL:\nhttps://medicine.yale.edu/event/ai-frontiers-6-1-2026
 /\n
DTEND;TZID=America/New_York:20260601T170000
DTSTAMP:20260610T030344Z
DTSTART;TZID=America/New_York:20260601T160000
LOCATION:Join our mailing list to receive Zoom Link & Passcode: https://ma
 ilman.yale.edu/mailman/listinfo/nlp-llm-ig
SEQUENCE:0
STATUS:Confirmed
SUMMARY:AI Frontiers: Hosted by NLP/LLM Interest Group
UID:59e8f679-fec3-4672-b189-91309a8f723e
END:VEVENT
END:VCALENDAR