Junha Song

Identifiers

No identifiers captured yet.

Papers (2)

1. Learning to See What You Need: Gaze Attention for Multimodal Large Language Models cs.CV · 2026 · author #1
2. RL makes MLLMs see better than SFT cs.CV · 2025 · author #1

Mentions

No mention provenance yet.

Frequent Coauthors

• Byeongho Heo 2 shared papers
• Dongyoon Han 2 shared papers
• Jaegul Choo 2 shared papers
• Sangdoo Yun 2 shared papers
• Geonmo Gu 1 shared papers