Tran Dinh Phu

Tran Dinh Phu

He/His

Ph.D. Student at KAIST. Low-level vision & efficient multimodal models.

Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering

Published in Under review, 2026

Recommended citation: Dinh Phu Tran, Jihoon Jeong, Saad Wazir, Seongah Kim, Thao Do, Cem Subakan, and Daeyoung Kim. "Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering." Under review, 2026.