Woongyeong Yeo — accepted AI-conference papers

2026

WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

Woongyeong Yeo, Kangsan Kim, Jaehong Yoon, Sung Ju Hwang

CVPR 2026

Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss of critical visual details during abstraction. Existing memor

Cited by 0 Source ↗Scholar ↗

2025

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding

Kangsan Kim, Geon Park, Youngwan Lee, Woongyeong Yeo, Sung Ju Hwang

CVPR 2025poster

Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in training data. Traditional methods like fine-tuning on OOD da…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗