Author

Taeyun Roh

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Across four multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Thinking even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 4.59 points.

Jun-Ha Jung, Minbyul Jeong, Suhyeon Lim et al. · arXiv.org · 2 citations

#artificial intelligence Preprint Mar 2026

BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA

This work hypothesizes and empirically verify that a model genuinely relies on visual evidence only when its multimodal distribution significantly diverges from its text-only distribution and proposes BUZZY, a training-free decoding method that corrects multimodal predictions by subtracting the text-only distribution.

Taeyun Roh, Suhyeong Park, Dongyoung Lee et al. · 0 citations