BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:65623632-3063-4062-b030-396366383538
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Self-Play Fine-Tuning Converts Weak Language Models to Strong 
 Language Models - Quanquan Gu\, Associate Professor\, UCLA
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20251102T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20231105T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20241103T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20230312T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20240310T020000
RDATE:20250309T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:2bc3224f-ea08-445e-a657-5bf620416f49
DTSTAMP:20260327T115315Z
CLASS:PUBLIC
CREATED:20240209T230336Z
DESCRIPTION:Zoom Link Abstract: Harnessing the power of human-annotated dat
 a through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Lang
 uage Models (LLMs). In this paper\, we delve into the prospect of growing 
 a strong LLM out of a weak one without the need for acquiring additional h
 uman-annotated data. We propose a new fine-tuning method called Self-Play 
 fIne-tuNing (SPIN)\, which starts from a supervised fine-tuned model. At t
 he heart of SPIN lies a self-play mechanism\, where the LLM refines its ca
 pability by playing against instances of itself. More specifically\, the L
 LM generates its own…
DTSTART;TZID=America/Vancouver:20240227T130000
DTEND;TZID=America/Vancouver:20240227T140000
LAST-MODIFIED:20240221T233645Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:Self-Play Fine-Tuning Converts Weak Language Models to Strong Langu
 age Models - Quanquan Gu\, Associate Professor\, UCLA
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/self-play-fine-tuning-converts-weak-language
 -models-strong-language-models-quanquan-gu
END:VEVENT
END:VCALENDAR