AI-Augmented Inquiry and Regulation in Hybrid Systems: A Control Allocation Architecture for Preserving Epistemic Agency in Hybrid Human-AI Cognition
论文提出AIRIS框架，通过分配控制权来解决在混合人机认知系统中因外部生成能力增加导致的认知参与度下降问题。
0 citationsRead paper
Selected work
Representative Papers
Transformation Behavior of Images in Latent Space
This study systematically investigates the impact of classical image transformations on the latent representations of histopathology image encoders, evaluating their degree of invariance to label-irrelevant augmentations. By measuring embedding-space distances among original images, standardly augmented variants, and randomly unrelated images, we conduct a comparative analysis using both general-purpose and pathology-specific encoders—namely those from Lunit, Bioptimus, and Meta—on colorectal H&E-stained whole-slide images and TCGA datasets. Our work quantitatively reveals, for the first time, that current encoders exhibit only partial invariance to common augmentation strategies, with notable differences between general and domain-specific models. Crucially, we find that post-transformation embeddings remain significantly closer to their originals than to random samples, thereby elucidating a key mechanism through which data augmentation enhances model performance.
0 citationsRead paper
Recent publications
Latest Papers
AI-Augmented Inquiry and Regulation in Hybrid Systems: A Control Allocation Architecture for Preserving Epistemic Agency in Hybrid Human-AI Cognition
论文提出AIRIS框架，通过分配控制权来解决在混合人机认知系统中因外部生成能力增加导致的认知参与度下降问题。
0 citationsRead paper
Transformation Behavior of Images in Latent Space
This study systematically investigates the impact of classical image transformations on the latent representations of histopathology image encoders, evaluating their degree of invariance to label-irrelevant augmentations. By measuring embedding-space distances among original images, standardly augmented variants, and randomly unrelated images, we conduct a comparative analysis using both general-purpose and pathology-specific encoders—namely those from Lunit, Bioptimus, and Meta—on colorectal H&E-stained whole-slide images and TCGA datasets. Our work quantitatively reveals, for the first time, that current encoders exhibit only partial invariance to common augmentation strategies, with notable differences between general and domain-specific models. Crucially, we find that post-transformation embeddings remain significantly closer to their originals than to random samples, thereby elucidating a key mechanism through which data augmentation enhances model performance.
0 citationsRead paper