7 papers · 1 filter
Pathway-Structured Privileged Distillation for Deployable Computational Pathology
Yongxin Guo, Hao Lu, Onur Koyun +2
Integrating transcriptomics and histopathology can improve cancer risk modelling, yet practical use is constrained by the limited availability of RNA profiling in routine settings.…
NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization
Hao Lu, Yongxin Guo, Onur Koyun +3
Vector quantization is central to modern generative modeling pipelines, but large-codebook VQ models often suffer from codebook collapse. We identify encoder drift as a key driver…
MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction
Hikmat Khan, Usama Sajjad, Metin N. Gurcan +4
Background: Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide. Accurate survival prediction is essential for treatment stratification, yet exist…
Momentum Memory for Knowledge Distillation in Computational Pathology
Yongxin Guo, Hao Lu, Onur C. Koyun +3
Multimodal learning that integrates genomics and histopathology has shown strong potential in cancer diagnosis, yet its clinical translation is hindered by the limited availability…
Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization
Hao Lu, Onur C. Koyun, Yongxin Guo +3
Vector Quantization (VQ) underpins many modern generative frameworks such as VQ-VAE, VQ-GAN, and latent diffusion models. Yet, it suffers from the persistent problem of codebook co…
Hyperparameter Optimization and Reproducibility in Deep Learning Model Training
Usman Afzaal, Ziyu Su, Usama Sajjad +4
Reproducibility remains a critical challenge in foundation model training for histopathology, often hindered by software randomness, hardware non-determinism, and inconsistent hype…