PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts

Bowen LIU, Qixiang ZHANG*, Xiaomeng LI

Under Review 2026

[Preprint] WSI Analysis Benchmark MLLM

KHiM-Mamba: Injecting Pathology Knowledge into Mamba via Hidden-State Modulation for Whole Slide Image Analysis

Qixiang ZHANG*, Yi LI, Tianqi XIANG, Haonan WANG, Mengjiao WEI, Bo XU, Xiaomeng LI

Under Review 2026

[Preprint] WSI Analysis

Towards generalizable pathology reports via a multimodal LLM with the multicenter in-context learning

Yi LI, Zhihao LIN, Qixiang ZHANG*, Xinpeng DING, Honglong YANG, Linjing PIN, Wei YUAN, Yongqin WEN, Lingliang GUO, Qingling ZHANG, Xiaomeng LI

Medical Image Analysis (MedIA) SCI Q1 2026

[Paper] [Code] WSI Analysis

PRET is a few-shot system for pan-cancer recognition without example training

Yi Li, Ziyu Ning, Tianqi Xiang, Qixiang Zhang, Yi Min, Zhihao Lin, Feiyan Feng, Baozhen Zeng, Xuexia Qian, Lu Sun, Jiace Qin, Ling Xiang, Chao Fan, Tian Qin, Qian Wang, Xiu-Wu Bian, Qingling Zhang, Xiaomeng Li

Nature Cancer SCI Q1 2026

……本文提出了一种新范式——无需训练的示例驱动泛癌识别（Pan-cancer Recognition via Examples without Training, PRET）。PRET 在推理阶段从少量示例中学习，无需对模型进行微调，仅用单一模型即可灵活、可扩展且有效地识别不同器官、不同医院与不同任务中的癌症。在跨国际医院与多种基准的大量评测中，我们的方法在 20 项任务上超越了现有方法，在 15 个基准上取得了超过 97% 的性能，最大提升达 36.76%……

[Paper] [Codes] WSI Analysis

A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding

Jingyu LU, Haonan WANG, Qixiang ZHANG*, Xiaomeng LI

International Conference of Learning Representations (ICLR) CCF-A 2026

[Preprint] [Code] AI for Neural Science

Read like a Pathologist: Enhancing Mamba with Pyramid Router for Whole Slide Image Analysis

Qixiang ZHANG, Yi LI, Tianqi XIANG, Haonan WANG, Xiaomeng LI

Under review 2025

WSI Analysis

S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation

Qixiang ZHANG*, Haonan WANG*, Yi LI, Xiaomeng LI (* 同等贡献)

IEEE Transactions on Medical Image (TMI) SCI Q1. 2025

[Paper] [Code] Segmentation

UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation

Yi LI, Haonan Wang, Qixiang Zhang, Boyu Xiao, Chenchang Hu, Hualiang Wang, Xiaomeng Li

Submitted to Annual Conference on Neural Information Processing Systems (NeurIPS) 2025

[Preprint] [Code] Benchmark MLLM

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

Haonan WANG*, Qixiang ZHANG*, Lehan WANG, Xuanqi HUANG, Xiaomeng LI (* 同等贡献)

International Conference of Computer Vision (ICCV) CCF-A 2025

[Preprint] [Code] AI for Neural Science

MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification

Tianqi XIANG, Yi LI, Qixiang ZHANG, Haonan WANG, Xiaomeng LI

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2025

[Paper] [Code] WSI Analysis

Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration

Honglong Yang, Shanshan Song, Yi Qin, Lehan Wang, Haonan Wang, Xinpeng Ding, Qixiang Zhang, Bodong Du, Xiaomeng Li

Under Review 2025

通用医学 AI 系统已在生物医学感知任务中展现出专家级性能，但其临床实用性仍受限于多模态可解释性不足与预后能力欠佳。为此，我们提出 XMedGPT——一个以临床医生为中心的多模态 AI 助手，融合文本与视觉可解释性，以支持透明、可信的医疗决策。XMedGPT 不仅能生成准确的诊断与描述性输出，还能将所引用的解剖部位在医学图像中进行定位接地，弥补了可解释性上的关键缺口并提升了临床可用性。该模型在 141 个解剖区域上取得 0.703 的交并比（IoU），Kendall’s tau-b 达到 0.479，表明视觉依据与临床结局之间具有很强的一致性。在生存期与复发预测任务中，其性能超越此前领先模型 26.9%……

[Preprint] MLLM Benchmark

Reinforced Correlation Between Vision and Language for Precise Medical AI Assistant

Haonan Wang, Jiaji Mao, Lehan Wang, Qixiang Zhang, Marawan Elbatel, Yi Qin, Huijun Hu, Baoxun Li, Wenhui Deng, Weifeng Qin, Hongrui Li, Jialin Liang, Jun Shen, Xiaomeng Li

Submitted to Nature Communication Under Review. 2025

……我们提出 RCMed，一个在输入与输出两端同时强化多模态对齐的全栈式 AI 助手，通过层次化的视觉—语言接地，为临床医生提供精确的解剖结构勾画、准确的定位与可靠的诊断。RCMed 在包含 2000 万组「图像—掩膜—描述」三元组的数据集上训练，在刻画不规则病灶与细微解剖边界方面达到当前最优精度，并在涵盖 9 种模态的 165 项临床任务中表现优异……

[Preprint] [Demo] SegmentationMLLM

GlandSAM: Injecting Morphology Knowledge into Segment Anything Model for Label-free Gland Segmentation

Qixiang ZHANG, Yi LI, Cheng XUE, Haonan WANG, Xiaomeng LI

IEEE Transactions on Medical Image (TMI) SCI Q1 2024

[Paper] [Code] Segmentation

AllSpark: Reborn labeled features from unlabeled in transformer for semi-supervised semantic segmentation

Haonan WANG*, Qixiang ZHANG*, Yi LI, Xiaomeng LI (* 同等贡献)

Conference on Computer Vision and Pattern Recognition (CVPR) CCF-A 2024

[Paper] [Code] Segmentation

Few-Shot Lymph Node Metastasis Classification Meets High Performance on Whole Slide Images via the Informative Non-parametric Classifier

Yi LI, Qixiang ZHANG, Tianqi XIANG, Xiaomeng LI

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2024

[Paper] [Code] WSI Analysis

Morphology-inspired unsupervised gland segmentation via selective semantic grouping

Qixiang ZHANG, Yi LI, Xiaomeng LI

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023

[Paper] [Code] Segmentation

Dual Teacher Sample Consistency Framework for Semi-Supervised Medical Image Classification

Qixiang Zhang, Yuxiang Yang, Chen Zu, Jianjia Zhang, Xi Wu, Jiliu Zhou, Yan Wang

IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI) 2023

[Paper] Segmentation