홈 › Papers

To What Extent Do Token-Level Representations from Pathology Foundation Models Improve Dense Prediction?

2026-02-03 · Weiming Chen, Xitong Ling, Xidong Wang, Zhenyang Cai, Yijia Guo, Mingxi Fu, Ziyi Zeng, Minxi Ouyang, Jiawen Li, Yizhi Wang, Tian Guan, Benyou Wang, Yonghong He arxiv

Pathology foundation models (PFMs) have rapidly advanced and are becoming a common backbone for downstream clinical tasks, offering strong transferability across tissues and institutions. However, for dense prediction (e.g., segmentation), practical deployment still lacks a clear, reproducible understanding of how different PFMs behave across datasets and how adaptation choices affect performance and stability. We present PFM-DenseBench, a large-scale benchmark for dense pathology prediction, evaluating 17 PFMs across 18 public segmentation datasets. Under a unified protocol, we systematically assess PFMs with multiple adaptation and fine-tuning strategies, and derive insightful, practice-oriented findings on when and why different PFMs and tuning choices succeed or fail across heterogeneous datasets. We release containers, configs, and dataset cards to enable reproducible evaluation and informed PFM selection for real-world dense pathology tasks. Project Website: https://m4a1tastegood.github.io/PFM-DenseBench

📄 PDF Abstract BibTeX arXiv:2602.03887

Code (0)

등록된 구현이 없습니다.

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

2026-06-04 · Gizem Yüce, Giorgos Nikolaou, Nicolas Flammarion arxiv

Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities. For autoregressive language models, not all tokens in a forget sample are equally relevant to forgettin…

DaX: Learning General Pathology Representations Across Scales

2026-06-05 · Bokai Zhao, Yiyang Zhang, Long Bai, Tai Ma 외 arxiv

Computational pathology requires visual representations that transfer across diverse clinical endpoints and remain robust to variation in magnification, staining, scanner type, slide preparation, and input resolution. We…

Self-Supervised Learning

Rep2Text: Decoding Full Text from a Single LLM Token Representation

2025-11-09 · Haiyan Zhao, Zirui He, Yiming Tang, Fan Yang 외 arxiv

Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their internal mechanisms remain largely opaque. In this work, we investigate a fundamental question: to what extent can the origin…

PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization

2025-03-09 · Honglin Li, Zhongyi Shui, Yunlong Zhang, Chenglu Zhu 외

Computational pathology and whole-slide image (WSI) analysis are pivotal in cancer diagnosis and prognosis. However, the ultra-high resolution of WSIs presents significant modeling challenges. Recent advancements in path…

Prognosis Quantization Self-Supervised Learning

Large Language Models Encode Semantics and Alignment in Linearly Separable Representations

2025-07-13 · Baturay Saglam, Paul Kassianik, Blaine Nelson, Sajana Weerawardhena 외 arxiv

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related …