@ysu_nlp : Here is my best-effort account of what may be happening: - Fine-tuning as a term peaked in the BERT times. In LLMs, it's mostly used in the SFT context. - Fine-tuning for task specialization has been fading away, partly because most frontier LLMs are closed-source and • TwiCopy

Yu Su @#ICLR2025

@ysu_nlp

+ Follow

Prof.@OhioState, co-director @osunlp. author of Mind2Web, SeeAct, MMMU, HippoRAG, BioCLIP, UGround. manifesting my thinking of intelligence into language agents

ID: 1240355312

linkhttp://ysu1989.github.io calendar_today04-03-2013 02:58:16

1,1K Tweet

9,9K Takipçi

926 Takip Edilen

Yu Su @#ICLR2025

@ysu_nlp

3 months ago

Here is my best-effort account of what may be happening: - Fine-tuning as a term peaked in the BERT times. In LLMs, it's mostly used in the SFT context. - Fine-tuning for task specialization has been fading away, partly because most frontier LLMs are closed-source and

thumb_up_off_alt13

chat_bubble_outline1

repeat2

shareShare