TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models

• URL: http://arxiv.org/abs/2609.04071v1
• Date: Thu, 03 Sep 2026 16:43:36 GMT
• Title: TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models
• Abstract summary: We propose TAP-Path, a task-adaptive compression framework that restructures a pretrained Virchow2 encoder rather than distilling it into a separate student.<n>Across three task-head optimization seeds, TAP-Path achieved $87.98 pm 0.067%$ test accuracy, $81.26 pm 0.49% balanced accuracy, and $82.38 pm 0.48%$ macro-F1 on a 32-class histopathology benchmark.<n>Results show that task-adaptive structural and token sparsification can improve the accuracy-efficiency trade-off of large pathology foundation models.
• Score: 3.7851234061033856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pathology foundation models improve transferable representation learning for histopathology, but recent gains often rely on encoders with hundreds of millions of parameters and high inference cost. We propose TAP-Path, a task-adaptive compression framework that directly restructures a pretrained Virchow2 encoder rather than distilling it into a separate student. TAP-Path combines validation-driven transformer-block selection, physical removal of redundant blocks, input-adaptive patch-token pruning, multi-depth feature recovery, and a lightweight gated task head. The final model retains 24 of 32 transformer blocks and 70% of patch tokens after pruning, reducing encoder parameters by 24.96% (631.24M to 473.70M) and analytical encoder compute by 35.20% (340.13G to 220.40G FLOPs). Across three task-head optimization seeds, TAP-Path achieved $87.98 \pm 0.067%$ test accuracy, $81.26 \pm 0.49%$ balanced accuracy, and $82.38 \pm 0.48%$ macro-F1 on a 32-class histopathology benchmark, compared with 86.89% for full Virchow2 and 87.67% for UNI2-h. TAP-Path achieved a Brier score of $0.1800 \pm 0.0005$ and failure-detection AUROC of $0.9047 \pm 0.0060$. A validation-only rare-aware objective improved rare-class balanced accuracy in a secondary operating analysis. Frozen external evaluation on 433 CPTAC samples yielded $91.22 \pm 0.83%$ accuracy and $91.10 \pm 0.81%$ balanced accuracy. These results show that task-adaptive structural and token sparsification can improve the accuracy-efficiency trade-off of large pathology foundation models while preserving reliability under internal and external evaluation.

Related papers

• Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair [44.80087038178069]
  We introduce Teleological Reasoning Infilling (TRI), a training framework that endows decoder-only transformers with a native emphgoal-conditioned bridging capability.<n>At inference, TRI operates as a surgical repair module within a dual-system loop.<n>Experiments on three benchmarks demonstrate that TRI achieves state-of-the-art performance across all tasks, while reducing per-problem token expenditure by 31.2%.
  arXiv  Detail & Related papers  (2026-06-03T15:58:48Z)
• Physics-Informed Learning of Effective Error Processes from Limited Noisy Transmon Measurements for Robust QAOA Reliability [0.0]
  We present a physics-informed pipeline for learning effective quantum error processes from finite-shot measurements.<n>The learned representations are compact effective models: local affine Bloch channels for each qubit and, in the three-qubit extension, pairwise residuals that capture correlated errors.<n>Results support effective error-process learning as a hardware-aware route toward more reliable variational quantum algorithms.
  arXiv  Detail & Related papers  (2026-05-29T20:58:00Z)
• From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models [0.0]
  We propose a five-stage methodology for causal feature analysis in transformer language models.<n>We demonstrate it end-to-end on GPT-2 small performing the Indirect Object Identification (IOI) task.
  arXiv  Detail & Related papers  (2026-05-21T13:25:16Z)
• From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents [56.31499185764872]
  Supervised fine-tuning (SFT) on long teacher trajectories is the dominant way to instill investigation and reasoning in open software-engineering (SWE) agents.<n>We propose Patches-to-Trajectories (P2T), which uses $pstar$ as privileged information during curation and formulates trajectory construction as bi-objective optimization over per-step effectiveness and trajectory length.
  arXiv  Detail & Related papers  (2026-05-21T04:54:55Z)
• Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance [0.0]
  Federated learning (FL) enables privacy-preserving predictive maintenance across distributed aerospace fleets.<n>This paper investigates the impact of symmetric uniform quantization on the accuracy--efficiency trade-off of a custom-designed lightweight convolutional model.<n>Int4 achieves accuracy emphstatistically indistinguishable from FP32 on both FD001 and FD002.
  arXiv  Detail & Related papers  (2026-04-09T17:13:15Z)
• A Deployment-Friendly Foundational Framework for Efficient Computational Pathology [48.3868019137117]
  We present LitePath, a framework designed to mitigate model over- parameterization and patch level redundancy.<n> LitePath integrates LiteFM, a compact model distilled from three large PFMs, using 190 million patches.<n> LitePath processes 208 slides per hour, 104.5x faster than Virchow2, and consumes 0.36 kWh per 3,000 slides.
  arXiv  Detail & Related papers  (2026-02-15T06:31:50Z)
• Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG [0.46976113832881716]
  This study proposes a deep learning framework for accurate gesture recognition using only two surface electromyography (sEMG) channels.<n>We present a few-shot transfer learning protocol that improved performance on unseen subjects from a baseline of 35.1% $pm$ 3.1% to 92.3% $pm$ 0.9% with minimal calibration data.
  arXiv  Detail & Related papers  (2026-01-30T14:21:46Z)
• CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning [62.56541355300587]
  We introduce a general test-time calibration framework that adaptively modifies the model toward high-reward reasoning paths.<n>Within this framework, we propose CarBoN, a two-phase method that first explores the solution space and then learns a calibration of the logits.<n>Experiments on MATH-500 and AIME-2024 show that CarBoN improves efficiency, with up to $4times$ fewer rollouts to reach the same accuracy.
  arXiv  Detail & Related papers  (2025-10-17T14:04:37Z)
• A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning [40.6234318894435]
  Large language models split into two families: reasoning-centric LLMs and agentic LLMs.<n>This divide arises from fundamentally different training objectives, leading to mismatched strengths and inefficiency on simple queries.<n>We present Adaptive Agent Foundation Model (A$2$FM), a unified framework that follows a route-then-align principle.
  arXiv  Detail & Related papers  (2025-10-13T17:08:25Z)
• LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs [0.0]
  We show how Linear Probes can be used to provide an estimation on the performance of a compressed large language model.<n>We also show their suitability to set the cut-off point when applying layer pruning compression.<n>Our approach, dubbed $LPASS$, is applied in BERT and Gemma for the detection of 12 of MITRE's Top 25 most dangerous vulnerabilities on 480k C/C++ samples.
  arXiv  Detail & Related papers  (2025-05-30T10:37:14Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers [44.344548601242444]
  We introduce a novel framework, Weakly-supervised RESidual Transformer (WeakREST), to achieve high anomaly detection accuracy.<n>We reformulate the pixel-wise anomaly localization task into a block-wise classification problem.<n>We develop a novel ResMixMatch algorithm, capable of handling the interplay between weak labels and residual-based representations.
  arXiv  Detail & Related papers  (2023-06-06T08:19:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.