Kangsan Kim (김강산) (kangsan.kim [at] kaist [dot] ac [dot] kr), and here is my CV (Curriculum Vitae).

I am a Ph.D. student at the Graduate School of AI at KAIST (MLAI lab), fortunate to be advised by Prof. Sung Ju Hwang. I am currently working as an Applied Scientist Intern at Amazon, mentored by Jayakrishnan Unnikrishnan and Bhagyashree Puranik. I have also been a visiting scholar at New York University, where I collaborated with Prof. Mengye Ren.

My research focuses on developing autonomous AI agents that can perceive, reason, and act in the real world, spanning coding, computer use, and embodied agents. I have previously worked on building memory in these agents that accumulates from past experience, enabling self-evolution, as well as retrieving knowledge from heterogeneous multimodal sources. Recently, I have also been interested in training agents through reinforcement learning to optimize behavior for specific tasks and objectives.

🔥 News

2026.09: Started my internship at Amazon in Seattle!
2026.08: 🇭🇺 Memory Transfer Learning got accepted to EMNLP 2026 Main and Agent Memory Distillation to EMNLP 2026 Findings!
2026.05: 📖 LearnWeak and SelfCI are released on arxiv.
2026.05: 🥈Selected as a Silver Reviewer of ICML 2026!
2026.04: 📖 Memory Transfer Learning, which studies cross-domain memory transfer in coding agents, is released on arxiv.
2026.04: 🇺🇸 UniversalRAG got accepted to ACL 2026 Main!
2026.03: 📖 MA-EgoQA: Multi-Agent Egocentric Video QA is released on arxiv.
2026.02: 🇺🇸 WorldMM got accepted to CVPR 2026 Highlight, and HoliSafe got accepted to CVPR 2026 Findings!

📝 Publications

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
[project page] [paper] [code]
Taeil Kim*, Kangsan Kim*, Sung Ju Hwang
EMNLP Findings 2026
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
[project page] [paper] [code]
Suji Kim*, Kangsan Kim*, Sung Ju Hwang
Preprint 2026
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
[paper] [code]
Sangwoo Park*, Woongyeong Yeo*, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek†, Seong Joon Oh†, Sung Ju Hwang†
Preprint 2026
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
[project page] [paper] [code]
Kangsan Kim, Minki Kang, Taeil Kim, Yanlai Yang, Mengye Ren†, Sung Ju Hwang†
EMNLP 2026
MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
[project page] [paper] [code]
Kangsan Kim, Yanlai Yang, Suji Kim, Woongyeong Yeo, Youngwan Lee, Mengye Ren†, Sung Ju Hwang†
Preprint 2026
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
[project page] [paper] [code]
Woongyeong Yeo*, Kangsan Kim*, Jaehong Yoon†, Sung Ju Hwang†
CVPR 2026 Highlight
HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model
[project page] [paper] [code]
Youngwan Lee, Kangsan Kim, Kwanyong Park, Ilchae Jung, Sujin Jang, Seanie Lee, Yong-Ju Lee, Sung Ju Hwang
CVPR Findings 2026
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
[project page] [paper] [code]
Woongyeong Yeo*, Kangsan Kim*, Soyeong Jeong, Jinheon Baek†, Sung Ju Hwang†
ACL 2026 Oral
VideoRAG: Retrieval-Augmented Generation over Video Corpus
[paper] [poster] [code]
Soyeong Jeong*, Kangsan Kim*, Jinheon Baek*, Sung Ju Hwang
ACL Findings 2025
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
[paper] [poster] [code]
Kangsan Kim*, Geon Park*, Youngwan Lee, Woongyeong Yeo, Sung Ju Hwang
CVPR 2025

(*: equal contribution, †: equal advising)

💻 Experiences

Applied Scientist Intern, Amazon
2026.09 - Current, Seattle, WA, USA
Mentor: Jayakrishnan Unnikrishnan and Bhagyashree Puranik
Studying long-video reasoning agents under latency budgets at Amazon Prime Video.
Visiting Ph.D. Student, New York University
2025.07 - 2025.10, Brooklyn, NY, USA
Advisor: Prof. Mengye Ren
Studying question answering over egocentric video streams from multiple embodied agents. (MA-EgoQA)
Computer Vision Engineer Intern, B GARAGE
2022.10 - 2023.07, San Jose, CA, USA
Developed an ultra-fast edge instance segmentation model that can segment anything in the warehouse.
Machine Learning(NLP) Scientist Intern, NAVER
2021.07 - 2021.10, Remote
Built and improved end-to-end Korean-English speech translation model at PAPAGO.

📖 Educations

2024.03 - Current, Ph.D. in Artificial Intelligence, Korea Advanced Institute of Science and Technology (KAIST).
2018.03 - 2024.02, B.S. in Computer Science, Korea Advanced Institute of Science and Technology (KAIST).

🏆 Honors and Awards

2023.06 Qualcomm-KAIST Innovation Award.
2020.09 Dean’s List, College of Engineering.

💬 Invited Talks

WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
2026.01, Multimodal Weekly hosted by TwelveLabs, Online | [post]
VideoRAG: Retrieval-Augmented Generation over Video Corpus, and Beyond
2025.09, Multimodal Weekly hosted by TwelveLabs, Online | [post]
Video as a Knowledge Source: Video-based Retrieval-Augmented Generation in Diverse Scenarios
2025.09, NYU Global AI Frontier Lab, Brooklyn, NY, USA

💯 Academic Service

Reviewer of ARR 2026, ICML 2026 (Silver Reviewer), NeurIPS 2026, and AAAI 2027