Kevin Hyekang Joo


P u b l i c a t i o n s
[8] ARIA: Affect-Responsive Interaction Alignment for Emotional Support Policies via Implicit Multimodal Affective Feedback
Brian Deuksin Kwon, Kevin Hyekang Joo[2], Elena Hayong Lee, Mohammad Soleymani, Gale M. Lucas
EMNLP 2026 - Findings
official source / bibtex
[7] From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration
Ala N. Tak, Teruhisa Misu, Kumar Akash, Zhaobo Zheng, Kevin Hyekang Joo[5], Jonathan Gratch
EMNLP 2026 - Findings
official source / bibtex
[6] Multimodal Behavioral Characterization of Dyadic Alliance in Support Groups
Kevin Hyekang Joo[1], Zongjian Li, Yunwen Wang, Yuanfeixue Nan, Mina Kian, Shriya Upadhyay, Maja Mataric, Lynn Miller, Mohammad Soleymani
ICMI 2025 - Main (Oral Presentation)
official source / bibtex
[5] Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation
Cheng Charles Ma*, Kevin Hyekang Joo*[1], Alexandria K. Vail*, Sunreeta Bhattacharya, Alvaro Garcia, Kailana Baker-Matsuoka, Sheryl Mathew, Lori Holt, Fernando De la Torre
ICMI 2025 - Workshop (Best Paper Award)
official source / bibtex
[4] Optimizing Dataflow Systems for Scalable Interactive Visualization
Junran Yang, Hyekang Kevin Joo[2], Sai S. Yerramreddy, Dominik Moritz, Leilani Battle
SIGMOD 2024 - Main
official source / pdf / bibtex
[3] CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
Hyekang Kevin Joo[1], Khoa Vo, Kashu Yamazaki, Ngan Le
ICIP 2023 - Main (Oral Presentation)
official source / video / github / pdf / bibtex
[2] Demonstration of VegaPlus: Optimizing Declarative Visualization Languages
Junran Yang, Hyekang Kevin Joo[2], Sai S. Yerramreddy, Siyao Li, Dominik Moritz, Leilani Battle
SIGMOD 2022 - Demo
official source / video / github / pdf / bibtex


[1] AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
Khoa Vo, Hyekang Joo[2], Kashu Yamazaki, Sang Truong, Kris Kitani, Minh-Triet Tran, Ngan Le
BMVC 2021 - Main (Oral Presentation)
official source / video / github / pdf / bibtex

(*) Equal contributions

[Note 1] PI & Co-PI are marked green on mouse-hover

[Note 2] As a U.S. Citizen, my  legal name  is  Kevin Hyekang Joo, but I occasionally put my name as  Hyekang Kevin Joo  on papers.

Back to Top