Changwoo Baek

I'm a master's student working on Efficient Multimodal LLMs in the Department of Electronics Engineering at Pusan National University.

My goal is to advance algorithmic efficiency, making AI models lightweight, fast, and reliable enough to run on edge devices (e.g., Mobile, NPU, Robotics platforms). I’m particularly interested in uncovering how (M)LLMs work internally, using that understanding to design generalizable lightweighting algorithms rather than relying on task-specific heuristics.

Research Interests:

Efficient (M)LLMs
Robotic Intelligence / Physical AI
Token Pruning
KV Cache Compression
Knowledge Distillation

News

[2026/06] Our paper HYBRIDKV is accepted at ICML 2026 Workshop AdaptFM

[2026/05] Our paper TA-OCD is accepted at IEEE Robotics and Automation Letters (RA-L)

[2026/01] Our paper AgilePruner is accepted at ICLR 2026

[2025/06] Our paper KDLR is accepted at IEEE Signal Processing Letters (SPL)

Educations

Pusan National University, Busan, Republic of Korea (Mar. 2025 - Feb. 2027 (Expected))
M.S. Department of Electronics Engineering
Advisor: Prof. Kyeongbo Kong

Pusan National University, Busan, Republic of Korea (Mar. 2019 - Feb. 2025)
B.S. Department of Electronics Engineering

Selected Publications

(* equally-contributed, † corresponding author)

International Conference

[W1] HYBRIDKV: Exploiting Head-Dominant Reconstruction for Efficient Query-Agnostic KV Cache Compression

Changwoo Baek, Kyeongbo Kong†

ICML 2026 Workshop AdaptFM, Jul. 2026

KV Cache Compression [LLM]

[C1] AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

Changwoo Baek*, Jouwon Song*, Sohyeon Kim*, Kyeongbo Kong†

ICLR 2026, Apr. 2026 [Github]

Training-free Visual Token Pruning [MLLM]

International Jounals

[J2] Target-Aware Change Detection for Efficient VLM Gating in Mobile Robots

Changwoo Baek*, Taehoon Kim*, Woojin Lee*, Jungkwan Son, Seoyoung Lee, Jiyoung Kim, Kyeongbo Kong†

IEEE Robotics and Automation Letters (RA-L), Jun. 2026 (ICRA 2027 Presentation)

Efficient Architecture for Change Detection [Robot Vision]

[J1] Unsupervised Knowledge Distillation via Local Representations for Vision-Language Models

Changwoo Baek, Jouwon Song, Kyeongbo Kong†

IEEE Signal Processing Letters (SPL), Aug. 2025

Knowledge Distillation for Image Classification [VLM]

Projects

Developed vision-language model-based technologies for visual perception and situation awareness in home robot systems

Collaborating with LG Electronics, Seoul, Korea (June. 2025 - )

Development of Anomaly and Environment Detection Technology for Home Robot Applications

Collaborating with LG Electronics, Seoul, Korea (June. 2025 - Nov. 2025)

Development of Nighttime Human Detection and Daytime Face Recognition Enhancement for Home Robot Environments

Collaborated with LG Electronics, Seoul, Korea (Dec. 2023 - Dec. 2024)

Awards

Outstanding Award, Industrial AI Convergence Club

Industrial AI Specialized Talent Development Program, Pusan National University, 2024

Reviewers

Conferences: NeruIPS'26
Journals: IEEE Transactions on Image Processing

Extra

Hardware Experiences

Robotics platform

NVIDIA Jetson Thor

Qualcom series

RTX 4090, PRO 6000, B200, ...

Rebellion ATOM+

Teaching Experiences

[EE1600575] C Programming, Teaching Assistant

Dept. of EE, Pusan National University, Spring 2025

[EE3100695] Digital Circuits Laboratory, Teaching Assistant

Dept. of EE, Pusan National University, Fall 2025

Scholarship

Graduate Research Encouragement Scholarship

National Research Foundation of Korea (NRF), 2025

Programming Skills

Python, Pytorch, C, C++, ROS2

Page updated

Google Sites

Report abuse