Tae Soo Kim @tae_skim

PhD Student in @kixlab_kaist at KAIST | HCI + NLP taesookim.com Daejeon, South Korea Joined April 2022

Tweets

181
Followers

743
Following

502
Likes

1K

Ian Arawjo @IanArawjo

3 days ago

Want to chart the future of human-AI interaction? Montréal HCI is ⭐️recruiting⭐️! We are looking for prospective PhD students to work on topics around AI memory and intent tracking over long time-frames. If interested, reach out by email or approach me at #UIST2025 for a chat!

0 8 30 2K 9

Yoonseo Choi @UIST2025 @yoon0u0

6 days ago

Are you heading to Busan? 🏄‍♀️🌴🇰🇷 I'll present our paper 🪷BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents at #UIST2025! 📍Oct 1 · 11:12–11:24 AM (Miami Room)

1 11 38 2K 6

Download Image

Jingyu Tang @JingyuTang621

2 weeks ago

Digital tasks are increasingly delegated to GUI agents. Can they resist dark patterns? Not always. Our research found GUI agents fail by prioritizing task completion over safety. While human oversight can help, it introduces costs such as attentional tunneling and cognitive load.

2 11 12 2K 0

Download Video

Yoonjoo Lee @yoonjoo_le2

a month ago

🎓I officially defended my PhD! Huge thanks to my amazing advisor @juhokim and committee @eytanadar @aliceoh @tongshuangwu @seo_minjoon. This fall, I'm excited to join @UMichCSE as a postdoc with @QVeraLiao to continue my research in human-centered AI and cognitive alignment!💙

48 11 325 24K 32

Download Image

Sangho Suh @sangho_suh

a month ago

🚨 How can we enable exploration & iteration in the design process — across personas, problem statements, solution ideas, and scenarios? Our #UIST2025 paper tackles this with AI and propagation-based mechanisms ⤵️/⤴️. 🌐 storyensemble-research.github.io 🎥 shorturl.at/EvuI1 🧵👇

2 8 31 5K 8

Yoonjoo Lee @yoonjoo_le2

a month ago

How well do LLMs handle personalized and contextual interaction? Our COLM paper, led by @tae_skim, introduces CUPID, a benchmark of interaction histories testing whether models can infer and apply user preferences across contexts. Current models still struggle (<50% P, <65% R).

Tae Soo Kim @tae_skim

a month ago

4 23 67 13K 22

Download Image

1 9 40 5K 18

Kevin Feng @kjfeng_

2 months ago

📢 New paper, published by @knightcolumbia. We often talk about AI agents augmenting vs. automating work, but how exactly can different configurations of human-agent interaction look like? We introduce a 5-level framework for AI agent autonomy to unpack this. 🧵👇

3 13 45 5K 35

Download Image

KIXLAB @kixlab_kaist

3 months ago

Huge congratulations to @tilekbayb on successfully defending his M.S. thesis! Bekzat will be joining KIXLAB as a Ph.D. student this Fall!

0 5 40 2K 0

Download Image

Haijun Xia @HaijunXia

4 months ago

Please RT! We're seeking data analysts using AI in their workflows. We would love to observe your process and learn what has been exciting or challenging. Your insights will help us build better tools. If you are willing to sit down with us (on zoom) for a couple of hours…

2 13 21 3K 4

Peiling Jiang @peilingjiang

4 months ago

AI should not replace browsing, but scale it. #Orca turns the web into your canvas and personal workspace. Work across dozens of pages, delegate to AI agents by your side, and synthesize on the fly. Welcome to 𝗕𝗿𝗼𝘄𝘀𝗶𝗻𝗴 𝗮𝘁 𝗦𝗰𝗮𝗹𝗲 hci.ucsd.edu/orca w/@HaijunXia

3 17 109 7K 39

Download Video

Yoonseo Choi @UIST2025 @yoon0u0

4 months ago

안녕하세요, @kixlab_kaist 에서 만든 📢 공약쏙쏙 시스템📢을 소개합니다! (promisescope.com) 🤔공약쏙쏙? #대선2025 공약을 바탕으로 공약이 가져올 수 있는 사회적 영향, 그리고 '나'에게 어떤 변화가 생길 수 있을지 LLM (GPT-4o) 을 활용해 자동으로 보여주는 시스템입니다. (1/3)

1 27 36 4K 10

Philippe Laban @PhilippeLaban

5 months ago

🆕paper: LLMs Get Lost in Multi-Turn Conversation In real life, people don’t speak in perfect prompts. So we simulate multi-turn conversations — less lab-like, more like real use. We find that LLMs get lost in conversation. 👀What does that mean? 🧵1/N 📄arxiv.org/abs/2505.06120

4 34 129 10K 80

Download Image

Yoonseo Choi @UIST2025 @yoon0u0

5 months ago

I'm in Yokohama for #CHI2025 to present my work #Proxona! 😊 I'll be presenting at 9:12 AM in Room G314+G315. If you're interested in user simulation & prototyping, data-driven personas, conversational interactions, or supporting sensemaking and ideation, please come!