Publications

We primarily aim to publish our work in top-tier venues in the computer science field, such as:

• AI and ML: NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, etc.
• Mobile, Ubiquitous, and Edge Systems: MobiCom, MobiSys, SenSys, UbiComp, etc.

Top conf: Top-tier CS conferences (CSRankings, KIISE (2024) S Tiers, BK21 (2018)).  *: Co-primary authors; †: Co-corresponding authors

Preprints & Under Review

• Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete
  Joonha Park, Jiseung Jeong, Taesik Gong
  [PDF] [ArXiv]
• Topic: Efficient LLM Adaptation
  Ahin Lee, Sehyun Yun, Joonha Park, Taesik Gong
  Under review at Top conf.
• Topic: Efficient Mobile AI Agent
  Jeonghoon Park, Mingyu Kim, Hojun Lee, Taesik Gong
  Under review at Top conf.
• Topic: Robustness for Industrial Applications
  Hakan Kayan, Nhat Pham, Taesik Gong, Charith Perera
  Under review at Top conf.
• Topic: Efficient Test-Time Adaptation of VLMs
  Huiwon Gwon, Taesik Gong, Seungjoon Yang
  Under review at Top conf.
• Topic: Real-World Test-Time Adaptation
  Jae-Won Yang, Taesik Gong†, Jae-Young Sim†
  Under review at Top conf.
• Topic: Robustness Against Domain Shift
  Eunsu Baek, Keondo Park, Ji-yoon Kim, Sojung Kim, Taesik Gong, Hyung-Sin Kim
  Under review at Top conf.
• Frequency Composition for Compressed and Domain-Adaptive Neural Networks
  Yoojin Kwon, Hongjun Suh, Wooseok Lee, Taesik Gong, Songyi Han, Hyung-Sin Kim
  [PDF] [ArXiv]
• An AI-Native Runtime for Multi-wearable Environments
  Chulhong Min, Utku Günay Acer, SiYoung Jang, Sangwon Choi, Diana A. Vasile, Taesik Gong, Juheon Yi, Fahim Kawsar
  [PDF] [ArXiv]

Conferences & Journals

• From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
  Changmin Lee, Jaemin Kim, Taesik Gong
  (Top conf.) ICML 2026
  [PDF] [ArXiv]
• ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues
  Yeji Park, Jiwon Tark, Taesik Gong
  (Top conf.) ACL 2026 (main track, long paper)
  [PDF] [ArXiv]
  🏆 SAC Highlight Award (top 2%, 255 / 12,148) · 🏆 Oral Presentation (top 4%, 485 / 12,148)
• SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
  Hyeongheon Cha, Dong Min Kim, Hye Won Chung, Taesik Gong†, Sung-Ju Lee†
  (Top conf.) NeurIPS 2025
  [PDF] [ArXiv]
• Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
  Eunsu Baek, Keondo Park, Jeonggil Ko, Min-hwan Oh, Taesik Gong, Hyung-Sin Kim
  (Top conf.) NeurIPS 2025
  [PDF] [ArXiv]
• Test-Time Adaptation with Binary Feedback
  Taeckyung Lee, Sorn Chottananurak, Junsu Kim, Jinwoo Shin, Taesik Gong†, Sung-Ju Lee†
  (Top conf.) ICML 2025
  [PDF] [ArXiv]
• Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables
  Taesik Gong, SiYoung Jang, Utku Günay Acer, Fahim Kawsar, Chulhong Min
  (SCI) IEEE Transactions on Mobile Computing (TMC) 2025 (JCR '23 IF < 5%)
  [PDF] [ArXiv]
• From Vision to Motion: Translating Large-Scale Knowledge for Data-Scarce IMU Applications
  Hyungjun Yoon, Hyeongheon Cha, Canh Hoang Nguyen, Taesik Gong, Sung-Ju Lee
  (SCI) IEEE Transactions on Mobile Computing (TMC) 2025 (JCR '23 IF < 5%)
  [PDF]
• Adaptive Camera Sensor for Vision Models
  Eunsu Baek, Sung-Hwan Han, Taesik Gong†, Hyung-Sin Kim†
  (Top conf.) ICLR 2025
  [PDF] [ArXiv]
• SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replay
  HyungJun Yoon, Jaehyun Kwak, Biniyam Aschalew Tolera, Gaole Dai, Mo Li, Taesik Gong, Kimin Lee, Sung-Ju Lee
  (Top conf.) SenSys 2025
  [PDF] [ArXiv]
• DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
  Taesik Gong, Fahim Kawsar, Chulhong Min
  (Top conf.) NeurIPS 2024
  [PDF] [ArXiv]
• By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting
  Hyungjun Yoon, Biniyam Aschalew Tolera, Taesik Gong, Kimin Lee, Sung-Ju Lee
  (Top conf.) EMNLP 2024 (main track, long paper)
  [PDF] [ArXiv]
  🏆 Qualcomm Innovation Fellowship Winner
• AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation
  Taeckyung Lee, Sorn Chottananurak, Taesik Gong, Sung-Ju Lee
  (Top conf.) CVPR 2024
  [PDF] [ArXiv]
• MIRROR: Towards Generalizable On-Device Video Virtual Try-On for Mobile Shopping
  Dongsig Kang, Eunsu Baek, Sungwook Son, Youngki Lee, Taesik Gong, Hyung-Sin Kim
  (Top conf.) UbiComp (IMWUT) 2024
  [PDF]
• SoTTA: Robust Test-Time Adaptation on Noisy Data Streams
  Taesik Gong*, Yewon Kim*, Taeckyung Lee*, Sorn Chottananurak, Sung-Ju Lee
  (Top conf.) NeurIPS 2023
  [PDF] [ArXiv]
• DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
  Taesik Gong, Yewon Kim, Adiba Orzikulova, Yunxin Liu, Sung Ju Hwang, Jinwoo Shin, Sung-Ju Lee
  (Top conf.) UbiComp (IMWUT) 2023
  [PDF] [ArXiv]
• LanSER: Language-Model Supported Speech Emotion Recognition
  Taesik Gong, Josh Belanich, Krishna Somandepalli, Arsha Nagrani, Brian Eoff, Brendan Jou
  INTERSPEECH 2023
  [PDF] [ArXiv]
  🏆 Oral Presentation
• Tailoring Interactions: Exploring the Opportune Moment for Remote Computer-mediated Interactions with Home-alone Dogs
  Yewon Kim, Taesik Gong, Sung-Ju Lee
  CHI EA 2023
  [PDF]
• NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
  Taesik Gong, Jongheon Jeong, Taewon Kim, Yewon Kim, Jinwoo Shin, Sung-Ju Lee
  (Top conf.) NeurIPS 2022
  [PDF] [ArXiv]
  🏆 Qualcomm Innovation Fellowship Finalist
• MyDJ: Sensing Food Intakes with an Attachable on Your Eyeglass Frame
  Jaemin Shin, Seungjoo Lee, Taesik Gong, Hyungjun Yoon, Hyunchul Roh, Andrea Bianchi, Sung-Ju Lee
  (Top conf.) CHI 2022
  [PDF] [Video]
  🏆 Honorable Mention
• Adapting to Unknown Conditions in Learning-based Mobile Sensing
  Taesik Gong, Yeonsu Kim, Ryuhaerang Choi, Jinwoo Shin, Sung-Ju Lee
  (SCI) IEEE Transactions on Mobile Computing (TMC) 2022 (JCR '22 IF < 7%)
  [PDF]
• Messaging Beyond Texts with Real-time Image Suggestions
  Joon-Gyum Kim, Taesik Gong, Kyungsik Han, Juho Kim, JeongGil Ko, Sung-Ju Lee
  MobileHCI 2020
  [PDF]
• No More One Liners: Bringing Context into Emoji Recommendations
  Joon-Gyum Kim, Taesik Gong, Bogoan Kim, JaeYeon Park, Woojeong Kim, Evey Huang, Kyungsik Han, Juho Kim, JeongGil Ko, Sung-Ju Lee
  ACM Transactions on Social Computing (TSC) 2020
  [PDF]
• AudiDoS: Real-Time Denial-of-Service Adversarial Attacks on Deep Audio Models
  Taesik Gong, Alberto Gil C. P. Ramos, Akhil Mathur, Sourav Bhattacharya, Fahim Kawsar
  ICMLA 2019
  [PDF]
  🏆 Oral Presentation
• MetaSense: Few-Shot Adaptation to Untrained Conditions in Deep Mobile Sensing
  Taesik Gong, Yeonsu Kim, Jinwoo Shin, Sung-Ju Lee
  (Top conf.) SenSys 2019
  [PDF] [Video]
• Knocker: Vibroacoustic-based Object Recognition with Smartphones
  Taesik Gong, Hyunsung Cho, Bowon Lee, Sung-Ju Lee
  (Top conf.) UbiComp (IMWUT) 2019
  [PDF] [Video] [Data]
• Use MU-MIMO at Your Own Risk – Why We Don't Get Gb/s Wi-Fi
  Hyunwoo Choi, Taesik Gong, Jaehun Kim, Jaemin Shin, Sung-Ju Lee
  (SCIE) Ad Hoc Networks 2019
  [PDF]
• Identifying Everyday Objects with a Smartphone Knock
  Taesik Gong, Hyunsung Cho, Bowon Lee, Sung-Ju Lee
  CHI EA 2018
  [PDF] [Video]
• Enjoy the Silence: Noise Control with Smartphones
  Taesik Gong, Jun Hyuk Chang, Joon-Gyum Kim, Soowon Kang, Donghwi Kim, Sung-Ju Lee
  ICCCN 2017
  [PDF]

Workshops, Posters, Demos, and Videos

• EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning
  Ahin Lee, Sehyun Yun, Taesik Gong
  EIFCOM 2026 (co-located with MobiSys '26)
  [PDF] [ArXiv]
  🏆 Best Paper Award
• TinyMem: Boosting Multi-DNN Inference on Tiny AI Accelerators with Weight Memory Virtualization
  Changmin Jeon, Taesik Gong, Juheon Yi, Fahim Kawsar, Chulhong Min
  HotMobile 2025
  [PDF]
• Energy Characterization of Tiny AI Accelerator-Equipped Microcontrollers
  Yushan Huang, Taesik Gong, SiYoung Jang, Fahim Kawsar, Chulhong Min
  HumanSys 2024 (co-located with SenSys '24)
  [PDF]
  🏆 Best Paper Award
• Time-Efficient Sparse and Lightweight Adaptation for Real-Time Mobile Applications
  Hyeongheon Cha, Taesik Gong, Sung-Ju Lee
  MobiSys 2024
  [PDF]
• Real-Time Object Identification with a Smartphone Knock
  Taesik Gong, Hyunsung Cho, Bowon Lee, Sung-Ju Lee
  MobiSys 2019
  [PDF] [Video]
  🏆 Best Video Award
• Towards Condition-Independent Deep Mobile Sensing
  Taesik Gong, Yeonsu Kim, Jinwoo Shin, Sung-Ju Lee
  MobiSys 2019
  [PDF]
• Dissecting 802.11ac Performance – Why We Should Turn Off MU-MIMO
  Hyeonwoo Choi, Taesik Gong, Jaehun Kim, Jaemin Shin, Sung-Ju Lee
  MobiSys 2019
  [PDF]
• Bringing Context into Emoji Recommendations
  Joon-Gyum Kim, Taesik Gong, Bogoan Kim, JaeYeon Park, Woojeong Kim, Evey Huang, Kyungsik Han, Juho Kim, JeongGil Ko, Sung-Ju Lee
  MobiSys 2019
  [PDF]