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:From Compound Figures to Composite Understanding: Developing a
  Multi-Modal LLM from Biomedical Literature with Medical Multiple-Image B
 enchmarking and Validation In healthcare\, disease diagnostics and longit
 udinal patient monitoring require clinicians to synthesize information ac
 ross multiple images from different modalities or time points\, yet this 
 multi-image reasoning remains a significant gap for most current multi-mo
 dal LLMs. This capability gap persists due to a critical bottleneck: the 
 lack of large-scale\, high-quality annotated training data for medical mu
 lti-image understanding. This study aims to address this scarcity by leve
 raging compound figures from biomedical literature. We devised a novel fi
 ve-stage\, context-aware instruction generation pipeline to create the PM
 C-MI-Dataset comprising over 260\,000 compound images\, and subsequently 
 developed M³LLM\, a medical multi-image multi-modal LLM. For a comprehens
 ive evaluation\, we also constructed the expert-validated PMC-MI-Bench. M
 ³LLM significantly outperforms state-of-the-art general-purpose and speci
 alized MLLMs\, achieving superior performance on diverse tasks of the PMC
 -MI-Bench and public benchmarks like OmniMedVQA and MMMU-Med. Furthermore
 \, clinical validation on the MIMIC longitudinal chest X-ray dataset conf
 irms its superior performance in real-world tasks\, including disease dia
 gnosis and progression prediction. Our study establishes a scalable parad
 igm for this task\, and the model\, dataset\, and benchmark will be publi
 cly released.\n\nAdmission:\nFree\n\nDetails URL:\nhttps://medicine.yale.
 edu/event/nlpllm-interest-group-7/\n
DTEND;TZID=America/New_York:20251027T170000
DTSTAMP:20260529T175515Z
DTSTART;TZID=America/New_York:20251027T160000
LOCATION:Zoom: Passcode Required\, URL: https://yale.zoom.us/j/93599941969
SEQUENCE:0
STATUS:Confirmed
SUMMARY:NLP/LLM Interest Group
UID:566982a5-6156-4e58-b64e-3d64e8e1504f
END:VEVENT
END:VCALENDAR