Bekzat Tilekbay

Ph.D student, KIXLAB, KAIST

[Tae Soo Kim @tae_skim]

Ask an LLM for a "post that'll pop off". Output misses so you say "more unique." It asks "unique how?" but you don't know yet.

DiscoverLLM (ICML'26): trains LLMs to help users discover their intents, not just execute them.

📑 https://t.co/K9iaaJQzAV
🌐 https://t.co/7Khdsc7u97

[Kihoon Son @kihoon_son]

Pleased to share our upcoming #CHI2026 workshop: Herding CATs: Making Sense of Creative Activity Traces. 📈🎨🐈‍⬛

We invite 2-4 page position papers on analyzing and understanding the creative process through digital traces.

🔗 https://t.co/MwwNZVCjzT📅 Due: Feb 12, 2026

[Kihoon Son @kihoon_son]

Are you interested in capturing professionals' tacit knowledge—like implicit decisions—and reusing it in generative agents 🤖 to better support creative work 👨🏻‍🎨?

👉 I will present my thesis work at UIST25 Doctoral Symposium (Poster: Tue evening).

See you in Busan! 🇰🇷 #UIST2025

[Bekzat Tilekbay @tilekbayb]

Thank You!

[KIXLAB @kixlab_kaist]

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

[Yoonsu Kim @yoons__u]

🔎 How can we make LLM interactions more cooperative and human-like?
We applied Gricean Maxims — principles for good conversation — to human-LLM interaction and derived 9 design insights!
Come see our LBW poster on Wed at #CHI2025! Let’s talk on #HAI, #AIAlignment, #UserIntent 😆

[DaEun Choi @daeun_choi_]

Are you interested in expanding your design ideas with generative AI? 🎨🚀
Come check out our LBW poster on Expandora at #CHI2025 on Wed. We explored how structured input and a mindmap-style interface can enable broader exploration. Love to chat about #GenAI #Creativity #Design

[Saelyne Yang @saelyne_yang]

When learning new skills, people often watch *multiple* how-to videos to understand different approaches and details.
In our #IUI2025 paper, we introduce VideoMix — a system that uses vision-language models to aggregate videos into one organized, easy-to-digest experience.

[Hyunwoo Kim @hyunwoo_iam]

📢 Do you frequently participate in online discussions? Do you try to change the opinions of others in discussions? Please share your experiences and challenges with us and receive a $8 gift card.
👇Interested? Fill out the form: https://t.co/Ao89LLzvtt

[Hyunwoo Kim @hyunwoo_iam]

💬You’re welcome if you frequently participate in online discussions in social media or online communities and can share your experience with 2-3 online discussions you recently participated in!
🕒 Approx. 45 min Zoom interview, $8 gift card

[Hyunwoo Kim @hyunwoo_iam]

[#KAIST 전산학부 인터뷰 참여자 모집]

📢 온라인 토론에 자주 참여하시나요? 온라인 토론에서 다른 사람의 의견을 바꿔보려 하시나요? 토론에 참여하셨던 경험을 들려주시고, 참여 보상 받아가세요!

👇 참여 신청: https://t.co/Ao89LLA3j1

[Juho Kim @imjuhokim]

At #DIS2024, we present AINeedsPlanner: a workbook to support effective collaboration between AI experts and clients. Upon analyzing AI app planning practices and info needs of AI experts, we developed a workbook that can be adopted in various AI app planning scenarios.

[Jihyeong Hong 홍지형 @paperandi]

How can we keep newbies of metaverse from feeling helpless during their own journey? Check out my work on NPC pipeline that monitors user context to initiate conversation, interpret questions, and customize responses.
#DIS2024 #acmdis

[Seulgi Choi @igules8925]

If you are interested in results and technical details, please check out our paper!

This work was done with my amazing collaborators, Hyewon, Yoonjoo(@yoonjoo_le2 ), and Juho(@imjuhokim ). Also, I really appreciate KIXLAB (@kixlab_kaist) members who gave me helpful feedback.

[HyoungWook Jin @HyoungWookJin]

🤖🧑‍🎓 Can students learn by teaching ChatGPT?

Our recent #CHI2024 work explored the design space of using LLMs as teachable agents.

📄 Paper: https://t.co/x7vVhusscd
🛝 Interactive demo: https://t.co/kuiIsnc23W
🌐 Project website: https://t.co/ijQlqO85UM

[Juho Kim @imjuhokim]

<Summer Research Internship at @kixlab_kaist>
I'm looking for undergrad research interns to join my research group (https://t.co/DNwp61bVAd) this summer. Most projects this round are about human-AI interaction. Please share broadly!

https://t.co/TuRipFjMNS

[Yoonseo Choi @yoon0u0]

(재업로드)[#KAIST 전산학부 연구 참여자 모집]

가상의 시청자와 대화하며 내 시청자들을 이해하고, 비디오 스토리라인을 기획해보세요!

자세한 사항은 아래 링크를 통해 확인해주세요.
✅ 설문 링크: https://t.co/3zQzUPI5D7
✅ 중요 조건: 1년 이상 채널을 운영한 YouTube 크리에이터

[Juho Kim @imjuhokim]

ExpressEdit https://t.co/PaKpQLTEu6 enables multimodal editing of informational videos by combining vision models and LLM. It supports editing queries like "whenever advice is given in the video, put a blue text overlay with a transparent background" w/ user-drawn bounding box.

[Saelyne Yang @saelyne_yang]

What if we can edit videos with natural language and sketch (e.g., "whenever a tip is mentioned, put a text box at the bottom with the content")? In our #IUI2024 paper led by @tilekbayb, we present ExpressEdit, a system that enables editing videos via NL text and sketching.