Jinwoo Chung

I am an M.S. student in Computer Engineering at Kookmin University, advised by Prof. Jangho Kim. I received my B.S. in Artificial Intelligence from Kookmin University in 2025.

My research focuses on efficient and trustworthy foundation models, especially quantization and model compression for VLMs, diffusion models, video models, and low-bit deployment. Recently, I have been studying how quantization changes model behavior, including generative diversity and cross-modal attention routing.

Publications

Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

Jinwoo Chung, Jangho Kim

NeurIPS 2026

Temporal-Aware Quantization via Sequence-Wise Quantizer Bounds Ensembling for Real-World Video Super-Resolution

Jinwoo Chung, Sangho An, Sungyeop Jung, Jangho Kim

ECCV 2026

paper / code

SR-BEVS: Sparse Recovery Bird’s-Eye View Model Soup for Robust Camera-Based 3D Object Detection

Jinwoo Chung, Sangho An, Hyunsung Park, Jangho Kim

IROS 2026

Quantized Model Soup Shake-Up: Weight Perturbation for Enhanced Ensemble Diversity

Jinwoo Chung, Sungyeop Jung, Weronika Czorapinska, Jangho Kim

KDD 2026

paper / code

SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

HyeonJun Lee^*, Hyeonsik Jo^*, Jinwoo Chung, Jangho Kim

AISTATS 2026

Honors & Awards

Outstanding Paper Award, ICROS 2026

Awarded for “Reinforcement Learning-Based Quantization Scale Optimization for Low-Bit Vision Transformers.”

2026

Education

Kookmin University — M.S. in Computer Engineering, GPA: 4.31/4.5
Advisor: Prof. Jangho Kim

Aug. 2025 – Feb. 2027 (expected)

Kookmin University — B.S. in Artificial Intelligence, GPA: 4.0/4.5

Mar. 2022 – Aug. 2025