today local_bar

Junmo Kim

Full Professor, Korea Advanced Institute of Science and Technology

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Preference Distillation via Value based Reinforcement Learning

#1911 · Minchan Kwon, Junwon Ko, Kangil Kim, Junmo Kim

Using teacher value function and PBRS, propose a theoretically grounded method for preference distillation

Frequency-Aware Token Reduction for Efficient Vision Transformer

#5109 · Dong-Jae Lee, Jiwan Hur, Jaehyun Choi, Jaemyung Yu, Junmo Kim

Token reduction with mitigating rank-collapsing (over-smoothing) through high-frequency token preservation

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision

#3611 · Chenshuang Zhang, Kang Zhang, Joon Son Chung, In So Kweon, Junmo Kim, Chengzhi Mao