Abstract Robust and trustworthy biomedical question answering (QA) remains a critical challenge for large language models (LLMs), especially in complex domains such as rare diseases, where information is fragmented across multiple sources. MedHopQA 2025 benchmark introduces 10 000 multi-step reasoning questions curated...
Jongmyung Jung, Hyeon Hwang, Yein Park et al.· Database: The Journal of Bio...· 0 citations
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.
Causal interventions further show that predictions remain sensitive to recurrent content when the question is held fixed, and that persistent visual evidence causally revises the recurrent trajectory.
Suhyeong Park, Jun-Ha Jung, Jaewoo Kang· 1 citation
SaMer is proposed, an object-aware token merging framework that compresses image-side post-projector tokens into representative centroids while preserving the original late-interaction interface, and outperforms compression baselines and shows stronger phrase-level grounding, suggesting that efficient multi-vector retr...
Suhyeong Park, Junha Jung, Jungwoo Park et al.· arXiv.org· 1 citation
A mechanistic intervention framework for identifying and transferring task-relevant sparse latent features across languages and reframes some cross-lingual reasoning gaps as failures of mechanism elicitation rather than capability absence, and offers a causally testable route to feature-mediated transfer without transl...
Minju Song, Hyeon Hwang, Junhyun Lee et al.· 0 citations
On HealMed, performance declined most in low-resource languages, although the size of the gap varied markedly across languages and models, whereas many open-source and medically specialized models showed larger and less consistent gaps.
Yingjian Chen, Fan Gao, Sherry T. Tong et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
