Ryuhaerang Choi @CHI2025

I’ll present our #CHI2025 paper, “Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recovery” in LLM for Health session. 🕤9:36 AM Wed 30. Apr 📍Annex Hall F206 📃dl.acm.org/doi/pdf/10.114… Grateful to Taehan, @subin_hci, Prof. Jennifer G Kim, and @wewantsj

Great #CHI2024 talk by @haerang_hci on helping users to control exposure to food content on social media. We are presenting our @RHEDC_Project work on remote healthcare for eating disorders (video stream 4pm tomorrow). Hopefully catch you for a chat to discuss shared interests 😊

What role can AI play in unlocking musical creativity? At #CHI2025 (🥇 Best Paper Award 🥇), we present Amuse: a songwriting tool for musicians that turns photos, sounds, and stories into chords 🎶 📄 arxiv.org/abs/2412.18940 🎧 yewon-kim.com/amuse/

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.

📄Join me for my #NeurIPS2024 poster presentation on 11th Dec! "DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators" 📆 When: Wed 11 Dec 4:30 pm- 7:30 pm 📍 Where: East Exhibit Hall A-C 1405 #NeurIPS #NeurIPS24 #MachineLearning #AI #AIAccelerator

🚀 (FL)² enables 99.9% label-free federated learning! I am on my way to #NeurIPS2024 📍 Catch us at #NeurIPS - Date: Wednesday, Dec 11 - Time: 11 a.m. PST — 2 p.m. PST - Location: East Exhibit Hall A-C #3603 Paper: arxiv.org/abs/2410.23227

SoundCollage explores the new potential for finding hidden classes in existing audio datasets, enabling efficient model training for diverse downstream tasks without new data collection. A great work done by @haerang_hci with @spdimitris, @wewantsj, @raswak and @malekz4deh.

At #UIST2024, I'm presenting two projects: 🎶〰️SonoHaptics and 🔊Auptimize! We tackle perceptual challenges in XR interactions (gaze-based object selection & audio localization) through multisensory feedback - without relying on visual displays. 🧵

[#KAIST 전산학부 연구] 시스템으로 생성한 시청자 페르소나의 품질을 평가하기 위한 평가자를 모집합니다. (비대면 1.5시간, 4.5만원) 자세한 안내와 실험 참여는 아래 링크를 확인해주세요. 설문 링크: forms.gle/U7PdbTy9JzYnge… 중요 조건: 1년 이상 채널을 운영한 유튜브 크리에이터

[#KAIST 전산학부 연구 참여자 모집] 통합검색 및 대화형 검색 품질 평가 실험 AI 기반 생성형 검색 서비스를 직접 사용해보시고, 검색 결과의 품질 및 경험을 평가해주실 참여자를 모집합니다! 자세한 사항은 아래 링크를 통해 확인해주세요 😃 ✅ 실험 참여 링크: bit.ly/cue-sge

저희 연구실에서 학부생 인턴 분들이 [연구자들이 겪는 어려움과 '생각의 구조화' 관련 설문조사] 를 진행하고 있습니다. 연구 경험이 있으신 분들의 많은 참여 부탁드립니다! (예상 소요 시간 5분 이내) 설문 링크: moaform.com/q/DPlphF 상세 내용 (스레드 참고): 👇

#CHI2024 MineXR: Mining Personalized XR Interfaces MineXR enables researchers to collect & analyze personalized XR user interface data. We also contribute a dataset of XR widgets & layouts, and design guidelines for future XR UIs. Paper, code, dataset: bit.ly/minexr

@haerang_hci is on her way to ACM CHI to present the best paper honorable mention award winning paper, FoodCensor! We developed FoodCensor that monitors and hides passively exposed food content on smartphones (e.g., youtube app) and personal computers (via Chrome extension).