Byonghyo Shim

Full Professor, Seoul National University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

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

Exhibit Hall C,D,E

Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs

#5001 Spotlight · Insu Lee, Wooje Park, Jaeyun Jang, Minyoung Noh, Kyuhong Shim, Byonghyo Shim

We introduce E3VQA, a multi-view QA benchmark, and M3CoT, a prompting method that improves LVLM reasoning by combining egocentric and exocentric views.