I'm excited for #CogSci2025 in SF this week! I would love to meet more people thinking about language and cognition, especially signed languages! Please feel free to reach out :)
Kayo Yin
@kayoyin.bsky.social
PhD student at UC Berkeley. NLP for signed languages and LLM interpretability. kayoyin.github.io 🏂🎹🚵♀️🥋
Happy to announce the first workshop on Pragmatic Reasoning in Language Models — PragLM @ COLM 2025! 🎉 How do LLMs engage in pragmatic reasoning, and what core pragmatic capacities remain beyond their reach? 🌐 sites.google.com/berkeley.edu/praglm/ 📅 Submit by June 23rd
PragLM @ COLM '25
IMPORTANT DATES
sites.google.com
More evidence of the importance of training analysis for interp! Induction heads might serve as *preliminary* function vector heads (which directly compute in-context learning tasks). Ultimately, LMs rely on FV heads more than IH heads for ICL. from @kayoyin.bsky.social
Which Attention Heads Matter for In-Context Learning?
Large language models (LLMs) exhibit impressive in-context learning (ICL) capability, enabling them to perform new tasks using only a few demonstrations in the prompt. Two different mechanisms have be...
arxiv.org
On Nov. 7th, I told my sociolinguistics students this was going to happen. They did an activity on language policy and one of the lessons was that repressive regimes always try to criminalize languages that are not ideologically associated with nationalism. I’m sorry I was right.
NBC News@nbcnews.com · 2y agoBREAKING: President Trump expected to sign an executive order to make English the official U.S. language for the first time in history, according to a White House official. nbcnews.to/43gRPGH
Induction heads are commonly associated with in-context learning, but are they the primary driver of ICL at scale? We find that recently discovered "function vector" heads, which encode the ICL task, are the actual primary mechanisms behind few-shot ICL! arxiv.org/abs/2502.14010 🧵👇
I’m visiting pittsburgh this Sunday until next Tuesday, I’d love to catch up with friends and meet new people! DM me :) this will be my first time back since I graduated 🫶
I'm presenting this virtually at #TISLR15 very soon at 2:35pm today Ethiopia time (3:35am Pacific 😀) !
Kayo Yin@kayoyin.bsky.social · 2y ago✨TISLR 15 stage presentation✨ Spoken languages exhibit communicative efficiency by minimizing speaker+listener effort. What about signed languages? ASL handshapes reflect efficiency pressures - but only in native signs, not signs borrowed from English! aclanthology.org/2024.acl-lon... 🧵
took my dog to the beach today. His name is apollo and he’s 14 years old :)
My latest talk on NLP for signed languages presented at the Japanese NLP colloquium doesn’t have an English version yet, maybe you can fix this by inviting me to give a talk :D
Just watched @kayoyin.bsky.social's fantastic talk at the Japanese NLP colloquium on sign language processing. It broadened my perspective on what language is and how AI can support Deaf and hard-of-hearing communities. Highly recommended! youtu.be/7dD8wu-Chbo
第67回: 手話の自然言語処理
YouTube video by NLPコロキウム
youtu.be
this is driving me crazy, does anyone recognize this song?? It’s stuck in my head but I can’t remember where I heard it
multiple people told me I seem to be in a visibly better mood the past 2 days which coincides perfectly with Berkeley finally getting rainy weather
✨TISLR 15 stage presentation✨ Spoken languages exhibit communicative efficiency by minimizing speaker+listener effort. What about signed languages? ASL handshapes reflect efficiency pressures - but only in native signs, not signs borrowed from English! aclanthology.org/2024.acl-lon... 🧵
whenever I open this app I can’t help but sing “heyy there mister blue” in my head
🚨New dataset + challenge🚨 We release ASL STEM Wiki: the first signing dataset of STEM articles! 📰 254 Wikipedia articles 📹 ~300 hours of ASL interpretations 👋 New task: automatic sign suggestion to make STEM education more accessible microsoft.com/en-us/resear... 🧵 #EMNLP2024
