Bio
I am an Assistant Professor in the Department of Software and Computer Engineering at Ajou University. Prior to joining Ajou University, I was a Postdoctoral Fellow at the AI Institute for Seoul National University (AIIS). In 2025, I earned my Ph.D. in AI from Seoul National University under the supervision of Prof. Byoung-Tak Zhang. I was selected as RSS Pioneers in 2025 and as a Youlchon AI Star Fellow in 2024.
My research lies at the intersection of multimodal AI and robotics. Specifically, I aim to advance robot learning and human-robot interaction by leveraging semantic, generalizable priors from multimodal AI models.
News
- [May 2026] I gave a talk at Korea Institute of Science and Technology (KIST).
- [March 2026] I'm joining as an Assistant Professor of Software at Ajou University.
Recent Publications [Full List]
- Junghyun Kim*, Ngseo Kim*, ChungWoo Lee, Seoyeon Lee, Woo-Jeong Baek, Adam Zhou, Chip Huyen, Jun-Ki Lee†, Gi-Cheon Kang†, Byoung-Tak Zhang†, Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead, in CoRL 2026
- Seongjun Jeong, Gi-Cheon Kang, Seongho Choi, Joochan Kim, Byoung-Tak Zhang, Continual Vision-and-Language Navigation, in BMVC 2025
- Gi-Cheon Kang*, Junghyun Kim*, Kyuhwan Shim, Jun Ki Lee, Byoung-Tak Zhang, CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision, in RSS 2025 (Oral)
- Suyeon Shin, Sujin Jeon*, Junghyun Kim*, Gi-Cheon Kang*, Byoung-Tak Zhang, Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following, in ICRA 2025
- Junghyun Kim, Gi-Cheon Kang*, Jaein Kim*, Seoyoon Yang, Minjoon Jung, Byoung-Tak Zhang, PGA: Personalizing Grasping Agents with Single Human-Robot Interaction, in IROS 2024
- Gi-Cheon Kang, Junghyun Kim, Jaein Kim, Byoung-Tak Zhang, PROGrasp: Pragmatic Human-Robot Communication for Object Grasping, in ICRA 2024 (Oral)
- Gi-Cheon Kang, Sungdong Kim*, Jin-Hwa Kim*, Donghyun Kwak*, Byoung-Tak Zhang, The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training, in CVPR 2023
- Junghyun Kim, Gi-Cheon Kang*, Jaein Kim*, Suyeon Shin, Byoung-Tak Zhang, GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation, in IROS 2023 (Oral)
- Gi-Cheon Kang, Junseok Park, Hwaran Lee, Byoung-Tak Zhang*, Jin-Hwa Kim*, Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer, in EMNLP Findings 2021
- Ahjeong Seo, Gi-Cheon Kang, Joonhan Park, Byoung-Tak Zhang, Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering, in ACL 2021
- Taehyeong Kim, Injune Hwang, Gi-Cheon Kang, Won-Seok Choi, Hyunseo Kim, Byoung-Tak Zhang, Label Propagation Adaptive Resonance Theory for Semi-Supervised Continuous Learning, in ICASSP 2020
- Gi-Cheon Kang, Jaeseo Lim, Byoung-Tak Zhang, Dual Attention Networks for Visual Reference Resolution in Visual Dialog, in EMNLP 2019
Service
Reviewing
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
- IEEE Transactions on Robotics (T-RO), 2025
- Conference on Robot Learning (CoRL), 2026
- Robotics: Science and Systems (RSS), 2026
- Neural Information Processing Systems (NeurIPS), 2023-2025
- International Conference on Learning Representations (ICLR), 2024-2026
