Yali Bi — accepted AI-conference papers

2026

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

Juntao Jiang, Jiangning Zhang, Yali bi, BAI Jinsheng, Weixuan Liu, Weiwei Jin +4

ICLR 2026poster

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, and recent advances have extended this paradigm to Multimodal Large Language Models (MLLMs). In the medical domain, where diagnostic decisions depend on nuance…

Cited by 0 Source ↗Scholar ↗

2025

Multi-Prototype-based Embedding Refinement for Medical Image Segmentation

Yali Bi, Enyu Che, Yinan Chen, Yuanpeng He, Jingwei Qu

ICASSP 2025accepted

Medical image segmentation aims to identify anatomical structures at the voxel-level. Segmentation accuracy relies on distinguishing voxel differences. Compared to advancements achieved in studies of the inter-class variance, the intra-class variance receives less attention. Moreover, traditional li…

Cited by 0 Source ↗Scholar ↗