BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:224081
DTSTAMP:20250916T125900Z
DTSTART;TZID=America/New_York:20250929T120000
DTEND;TZID=America/New_York:20250929T125000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/bme-seminar-series-ba
 shima-islam-phd-wpi-ece-mindfulness-sensing-multimodal-reasoning-toward-se
 nsor
SUMMARY:BME Seminar Series: Bashima Islam, PhD: WPI ECE: “From Mindfulness 
 Sensing to Multimodal Reasoning: Toward Sensor-Language Intelligence Beyon
 d Vision”
DESCRIPTION:\n\n\n      \n      \n\n\n\nSeminar Series \n“From Mindfulness 
 Sensing to Multimodal Reasoning: Toward Sensor-Language Intelligence Beyon
 d Vision”\n\n\n\n\n      \n      \n\n\n\nBashima Islam, PhD\nAssistant Pro
 fessor of Electrical and Computer Engineering\nWorcester Polytechnic Insti
 tute\n\nAbstract: The rapid growth of multimodal AI opens new opportunitie
 s for sensing, reasoning, and interaction, yet most systems still focus na
 rrowly on vision and overlook signals critical for human-centered applicat
 ions. In this talk, I will present three recent projects from my group tha
 t collectively broaden the scope of multimodal intelligence. First, I will
  introduce our work on mindfulness and respiration sensing, where we desig
 n smartphone-based algorithms that track respiration rate and estimate min
 dfulness skill progression using only accelerometer data. This study demon
 strates how sensor feedback can enhance usability and engagement in digita
 l mindfulness training, providing a compelling case for health-oriented mu
 ltimodal AI. Next, I will present RAVEN, a unified architecture for multim
 odal question answering. At its core is QuART, a query-conditioned token g
 ating module that learns to assign relevance scores across modalities, ena
 bling the system to amplify informative cues while suppressing distractors
 . Through a staged training pipeline, RAVEN achieves robust reasoning acro
 ss video, audio, and sensor streams. Finally, I will discuss LLaSA, the La
 rge Language and Sensor Assistant, which extends multimodal research to we
 arable sensing. LLaSA introduces new datasets and evaluation frameworks fo
 r aligning sensor signals with language, offering the first general-purpos
 e assistant that reasons jointly over sensor data and natural language que
 ries. Together, these projects chart a path toward sustainable multimodal 
 systems that hear, sense, and reason with the world, advancing both human-
 centered applications and core AI methods.\nBio: Dr. Bashima Islam is an A
 ssistant Professor of Electrical and Computer Engineering at Worcester Pol
 ytechnic Institute, with affiliations in Computer Science and Data Science
 . Her research transforms AI through the fusion of sensors, speech, and la
 nguage to build sustainable, intelligent systems for the edge. She focuses
  on bridging AI with real-world impact that advance acoustic understanding
 , behavioral health monitoring, and real-world multimodal intelligence whi
 le considering resource constrained of low-power devices. She has been rec
 ognized with several prestigious honors, including the NSF CRII Award, mul
 tiple NIH research grants, and selection to Forbes 30 Under 30 in Science.
 \nFor a zoom link please contact Kate Harrison at kharrison@wpi.edu\n
END:VEVENT
END:VCALENDAR