Changwoo Baek

News

[2026/01] One paper has been accepted at ICLR 2026

[2025/11] One paper has been accepted at NeurIPS 2025 ER Workshop

[2025/06] One paper has been accepted at IEEE Signal Processing Letters 

Educations

• Pusan National University, Busan, Republic of Korea  (Mar. 2025 - )
  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

Publications

(* equal contribution, † corresponding author)

Under Review

• Anonymized Title (Query-agnositc KV Cache Compreesion [LLM])

C. Baek, K. Kong†

• Anonymized Title (Robot Vision)

C. Baek*, T. Kim*, W. Lee*, J. Son, S. Lee, J. Kim, K. Kong†

International Journal

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

C. Baek, J. Song, K. Kong† 

IEEE Signal Processing Letters (SPL), Aug. 2025

International conference

• [C3] An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

C. Baek*, J. Song*, S. Kim*, K. Kong†

ICLR 2026, Apr. 2026 [Github]

*Initial version was presented at NeruIPS Workshop on Efficient Reasoning, Dec. 2025

• [C2] Efficient Token Pruning for Vision-Language Models in Multi-turn Scenarios

C. Baek*, S. Kim*, J. Song*, K. Kong†

IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), Oct. 2025 (Oral)

• [C1] Low-Light Face Recognition for Mobile Robots

C. Baek, J. Song, K. Kong†   

ITC-CSCC, Jul. 2025 (Special session)

Domestic Journal

• [J2] Visual Token Pruning Based on Entropy Dynamics in Vision Encoders of Multimodal LLMs

C. Baek*, S. Kim*, J. Song*, K. Baek, K. Kong†

The Journal of the Korean Institute of Broadcast and Media Engineers (KIBME) Letters, 2026

• [J1] Deep Learning-Based Face Recognition through Low-Light Enhancement 

C. Baek, K. Kong†

IEMEK Journal of Embedded Systems and Applications, Oct. 2024

Domestic Conference

• [C1] Analysis of Visual Token Pruning in Large Vision-Language Models from the Perspectives of Image Complexity and Hallucination Generation 

S. Kim*, C. Baek*, J. Song*,  K. Kong†

The Korean Institute of Electrical Engineers (KIEE) Autumn Conference, Undergraduate Paper Competition, Nov. 2025 (3rd Prize)

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)

Technical Reports

• Coming Soon..

Evaluating MLLM inference optimization techniques on real on-device systems (e.g., HyperCLOVA X SEED 3B, Kanana-1.5-V-3B on NPUs)

Awards

• Outstanding Award, Industrial AI Convergence Club

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

Extra

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

• Signals and Systems, Academic Tutor

Departmental Tutoring Program, Dept. of EE, Pusan National University, Fall 2023

Scholarship

• Graduate Research Encouragement Scholarship

National Research Foundation of Korea (NRF), 2025

Skills

• Python, Pytorch, C, C++, ROS2