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:20241103T010000
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:20240416T123000
RDATE:20241103T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
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:919b0b327035c3c96aa3f7913be2ef51
CATEGORIES:Special Seminar
CREATED:20250412T231834
SUMMARY:Advancing Complex Reasoning with Language Models and Agentic Systems
LOCATION:https://rutgers.zoom.us/j/96753161671?pwd=SzV0OUsrUUpVT0FITVhoQ3doaWkwdz09.
  Passcode: 142980
DESCRIPTION:Complex reasoning is fundamental to human intelligence and plays a crucial 
 role in advancing education, science, and technology. This talk explores th
 e development of language model systems that exhibit robust mathematical re
 asoning and facilitate scientific reasoning, marking a significant step tow
 ard general artificial intelligence. We introduce novel multi-modal and kno
 wledge-intensive benchmarks designed to assess the reasoning capabilities o
 f large language models (LLMs) and vision-language models (VLMs) in real-wo
 rld scenarios, including those involving visual data, tabular information, 
 and scientific applications. The talk highlights recent advancements in mat
 hematical reasoning within visual contexts and addresses key unresolved cha
 llenges. Additionally, we present cutting-edge retrieval and tool-augmented
  algorithms that significantly enhance LLM performance in mathematical reas
 oning tasks. Finally, we explore how agentic systems, leveraging test-time 
 optimization and external tools, can further advance mathematical reasoning
  and scientific discovery.\n
X-ALT-DESC;FMTTYPE=text/html:<p><span data-olk-copy-source="MessageBody" style="font-style: normal; font
 -weight: 400; letter-spacing: normal; text-align: start; text-indent: 0px; 
 text-transform: none; white-space: normal; word-spacing: 0px; text-decorati
 on: none; color: black; font-family: Arial, sans-serif; vertical-align: bas
 eline; background-color: transparent;">Complex reasoning is fundamental to 
 human intelligence and plays a crucial role in advancing education, science
 , and technology. This talk explores the development of language model syst
 ems that exhibit robust mathematical reasoning and facilitate scientific re
 asoning, marking a significant step toward general artificial intelligence.
  We introduce novel multi-modal and knowledge-intensive benchmarks designed
  to assess the reasoning capabilities of large language models (LLMs) and v
 ision-language models (VLMs) in real-world scenarios, including those invol
 ving visual data, tabular information, and scientific applications. The tal
 k highlights recent advancements in mathematical reasoning within visual co
 ntexts and addresses key unresolved challenges. Additionally, we present cu
 tting-edge retrieval and tool-augmented algorithms that significantly enhan
 ce LLM performance in mathematical reasoning tasks. Finally, we explore how
  agentic systems, leveraging test-time optimization and external tools, can
  further advance mathematical reasoning and scientific discovery.</span></p
 >
CONTACT:Pan Lu
DTSTAMP:20260828T013839
DTSTART;TZID=America/New_York:20250417T123000
DTEND;TZID=America/New_York:20250417T133000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR