4 papers
MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation
Haoyu Yang, Meixing Shi, Zengjie Chen +5
Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack pre…
REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering
Caijun Yan, Yang Zhou, Meixing Shi +4
Recently, retrieval-augmented and memory-augmented methods have emerged as two promising paradigms for long-video question answering. However, existing methods typically rely on ri…
EliSeg: Verified Target Construction for Report-Grounded Abnormality Segmentation
Chengyi Peng, Haoyu Yang, Meixing Shi +2
Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertain, or irrelevant findings, whi…
Continual Video-MLLM Adaptation over Evolving Domains
Rui Cheng, Meixing Shi, Yuxiang Cai +3
Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-wor…