BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260929T210111Z
UID:3BB4AA12-02B1-4766-AB59-9973B50BE927
DTSTART;TZID=America/Chicago:20261009T145000
DTEND;TZID=America/Chicago:20261009T160000
DESCRIPTION:Abstract: Modern computing is often optimized in isolated layer
 s\, with separate tools for interfaces\, software\, and hardware. In this 
 talk\, we will start with expertise-driven design acceleration and expand 
 to automated optimization. We show that large language model (LLM) agents 
 can iteratively generate\, test\, and improve GPU kernels by reading hardw
 are feedback\, from single kernels to full end-to-end GPU programs. We the
 n broaden the picture by showing how agents can more accurately ground int
 erface elements and carry out computer interaction step by step\, giving t
 hem the ability to operate real software\, hardware environments\, and app
 lications.\n\nBio: Caiwen Ding is an Associate Professor in the Department
  of Computer Science & Engineering at the University of Minnesota Twin Cit
 ies\, which he joined in August 2024. He had been an Assistant Professor i
 n the School of Computing at the University of Connecticut from 2019-2024.
  He received his Ph.D. from Northeastern University\, Boston in 2019. His 
 research interests span algorithm–system co-design for machine learning 
 and artificial intelligence\, privacy-preserving machine learning\, machin
 e learning for electronic design automation (EDA). Dr. Ding’s research h
 as been\npublished in leading venues across systems\, architecture\, and A
 I/ML—including DAC\, ICCAD\, ASPLOS\, ISCA\, MICRO\, HPCA\, SC\, FPGA\, 
 MLSys\, NeurIPS\, ICML\, CVPR\, ACL\, EMNLP\, and IJCAI. He is a recipient
  of the NSF CAREER Award\, Amazon Research Award\, and Cisco Research Awar
 d. He has received multiple paper distinctions\, including the Best Paper 
 Award at the 2025 IEEE International Conference on LLM-Aided Design (ICLAD
 )\, the Best Paper Award at the 2023 AAAI DCAA workshop\, Outstanding Stud
 ent Paper at HPEC 2023\, Best Paper Award Nominations at DATE 2018 and DAT
 E 2021\, and a publicity paper at DAC 2022.\n\nSpeaker(s): Caiwen Ding\, \
 , \n\nVirtual: https://events.vtools.ieee.org/m/580877
LOCATION:Virtual: https://events.vtools.ieee.org/m/580877
ORGANIZER:parhi@umn.edu
SEQUENCE:26
SUMMARY:Agentic AI for Modern Computing
URL;VALUE=URI:https://events.vtools.ieee.org/m/580877
X-ALT-DESC:Description: <br /><p>Abstract: Modern computing is often optimi
 zed in isolated layers\, with separate tools for interfaces\, software\, a
 nd hardware. In this talk\, we will start with expertise-driven design acc
 eleration and expand to automated optimization. We show that large languag
 e model (LLM) agents can iteratively generate\, test\, and improve GPU ker
 nels by reading hardware feedback\, from single kernels to full end-to-end
  GPU programs. We then broaden the picture by showing how agents can more 
 accurately ground interface elements and carry out computer interaction st
 ep by step\, giving them the ability to operate real software\, hardware e
 nvironments\, and applications.</p>\n<p>&nbsp\;</p>\n<p>Bio: Caiwen Ding i
 s an Associate Professor in the Department of Computer Science &amp\; Engi
 neering at the University of Minnesota Twin Cities\, which he joined in Au
 gust 2024. He had been an Assistant Professor in the School of Computing a
 t the University of Connecticut from 2019-2024. He received his Ph.D. from
  Northeastern University\, Boston in 2019. His research interests span alg
 orithm&ndash\;system co-design for machine learning and artificial intelli
 gence\, privacy-preserving machine learning\, machine learning for electro
 nic design automation (EDA). Dr. Ding&rsquo\;s research has been<br>publis
 hed in leading venues across systems\, architecture\, and AI/ML&mdash\;inc
 luding DAC\, ICCAD\, ASPLOS\, ISCA\, MICRO\, HPCA\, SC\, FPGA\, MLSys\, Ne
 urIPS\, ICML\, CVPR\, ACL\, EMNLP\, and IJCAI. He is a recipient of the NS
 F CAREER Award\, Amazon Research Award\, and Cisco Research Award. He has 
 received multiple paper distinctions\, including the Best Paper Award at t
 he 2025 IEEE International Conference on LLM-Aided Design (ICLAD)\, the Be
 st Paper Award at the 2023 AAAI DCAA workshop\, Outstanding Student Paper 
 at HPEC 2023\, Best Paper Award Nominations at DATE 2018 and DATE 2021\, a
 nd a publicity paper at DAC 2022.</p>
END:VEVENT
END:VCALENDAR