SVC-Probe shows that 98.6% accuracy distinguishing drug conditions in embeddings does not imply reliable cross-drug perturbation prediction, dropping to 0.30 cosine similarity in leave-one-drug-out tests.
Y., Song, A
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Haiku aligns mIF spatial proteomics, H&E histology, and clinical metadata via contrastive learning to enable retrieval, improved survival prediction, zero-shot biomarker inference, and counterfactual exploration in cancer.
GLMP generates robust pathology embeddings by routing histology images through an intermediate textual representation produced by general-purpose MLLMs to mitigate batch effects.
Proposes the AIVT conceptual framework for unified AI-driven tissue state representation, molecular/morphological prediction, and spatiotemporal simulation from spatial multimodal data.
citing papers explorer
-
SVC-Probe: A Framework for Evaluating Perturbation Generalization in Spatial Foundation-Model Embeddings
SVC-Probe shows that 98.6% accuracy distinguishing drug conditions in embeddings does not imply reliable cross-drug perturbation prediction, dropping to 0.30 cosine similarity in leave-one-drug-out tests.
-
Linking spatial biology and clinical histology via Haiku
Haiku aligns mIF spatial proteomics, H&E histology, and clinical metadata via contrastive learning to enable retrieval, improved survival prediction, zero-shot biomarker inference, and counterfactual exploration in cancer.
-
Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation
GLMP generates robust pathology embeddings by routing histology images through an intermediate textual representation produced by general-purpose MLLMs to mitigate batch effects.
-
Building artificial intelligence virtual tissue (AIVT) for tissue state representation, feature prediction, and dynamic simulation
Proposes the AIVT conceptual framework for unified AI-driven tissue state representation, molecular/morphological prediction, and spatiotemporal simulation from spatial multimodal data.