AI4Meder 医学人工智能资源平台

ICLR 2026 Poster accepted paper at ICLR 2026. The ability to distinguish subtle differences between visually similar images is essential for diverse domains such as industrial anomaly detection, medical imaging, and aerial surveillance. While comparative reasoning benchmarks for vision-language models (VLMs) have recently emerged, they primarily focus on images with large, salient differences and fail to capture the nuanced reasoning required for real-world applications. In this work, we introduce **VLM-SubtleBench**, a benchmark designed to evaluate VLMs on *subtle comparative reasoning*. Our benchmark covers ten difference types—Attribute, State, Emotion, Temporal, Spatial, Existence, Quantity, Quality, Viewpoint, and Action—and curate paired question–image sets reflecting these fine-grained variations.

1月 2026

医学影像计算医疗多模态

Dyslexify：CLIP 中抵御排版攻击的机制性防御

ICLR 2026 Poster - 2026

ICLR 2026 Poster accepted paper at ICLR 2026. Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model jailbreaks. In this work, we analyze how CLIP vision encoders behave under typographic attacks, locating specialized attention heads in the latter half of the model's layers that causally extract and transmit typographic information to the cls token. Building on these insights, we introduce Dyslexify - a method to defend CLIP models against typographic attacks by selectively ablating a typographic circuit, consisting of attention heads. Without requiring finetuning, dyslexify improves performance by up to 22.06\% on a typographic variant of ImageNet-100, while reducing standard ImageNet-100 accuracy by less than 1\%, and demonstrate its utility in a medical foundation model for skin lesion diagnosis.

1月 2026

开源数据

查看全部

critical care time-series variables and outcomes

PhysioNet/CinC 2012 ICU 时间序列数据集

ICU time-series benchmark dataset

The PhysioNet/CinC Challenge 2012 dataset contains ICU time-series records used for mortality prediction and patient-specific outcome modeling. It remains a useful benchmark for clinical time-series modeling, missingness-aware learning, and early warning model development.

Chinese community medical questions and answers

cMedQA2：中文社区医学问答数据集

Chinese medical QA dataset

cMedQA2 is an updated Chinese community medical question answering dataset for question-answer matching and medical QA research. It is useful for training and evaluating Chinese medical retrieval, ranking, and answer selection models.

abdominal CT and MRI with multi-organ annotations

AMOS 腹部多器官分割基准

abdominal multi-organ segmentation benchmark

AMOS is an abdominal multi-organ segmentation benchmark with CT and MRI cases for evaluating versatile medical image segmentation models. It supports abdominal organ segmentation, modality-general segmentation, and benchmarking of robust 3D segmentation methods.