PathSelect: Sequential Token Selection for Whole Slide Pathology

• URL: http://arxiv.org/abs/2607.23631v1
• Date: Sun, 26 Jul 2026 12:36:16 GMT
• Title: PathSelect: Sequential Token Selection for Whole Slide Pathology
• Abstract summary: Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths.<n>We reformulate WSI token pruning as a sequential selection process, enabling the model to autonomously learn an optimal routing strategy.
• Score: 0.6362628914555645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gigapixel Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths. Existing approaches predominantly rely on spatial sampling or training-free pruning, which risk diluting weak but informative signals, leading to the loss of critical diagnostic evidence due to the spatially diffuse nature of pathological cues. We reformulate WSI token pruning as a sequential selection process, enabling the model to autonomously learn an optimal routing strategy rather than relying on static heuristics. We herein propose a decoupled routing framework integrated as an active plugin into the fully pre-trained SlideChat base model, leaving both the slide encoder and large language model frozen. To provide continuous gradients for the non-differentiable pruning operation during training, we introduce PathSelect. PathSelect employs a variance-preserving noise gate to modulate each patch's information flow via a differentiable Soft Top-K operator, paired with a diagonal-attention Denoiser that recovers the perturbed representations without semantic leakage. At inference, the PathSelect module is entirely detached. Relying solely on the trained Scorer, a deterministic Hard Top-K operator executes adaptive, data-dependent trajectory termination, significantly accelerating downstream generative processing with exceptionally low sequential token selection latency. Driven by an empirical average of only 44.86 tokens under a maximum constraint of K = 128, our framework achieves 74.00% overall accuracy on SlideBench (TCGA), representing an approximate 36.6x spatial token reduction relative to the uncompressed baseline average while consistently outperforming sampling-based counterparts.

Related papers

• PathGuide: Dynamic Classifier-Free Guidance via On-Policy Transport Alignment [7.359926148820936]
  We introduce PathGuide, a framework that reformulates scalar CFG selection as an on-policy transport problem.<n>We prove that this transport-based selector improves path alignment and sample fidelity over both fixed and state-of-theart adaptive guidance baselines.
  arXiv  Detail & Related papers  (2026-08-29T07:26:21Z)
• Difficulty-Calibrated Interpolation Paths for Conditional Flow Matching [0.0]
  Conditional Flow Matching trains generative models by regressing a network onto the velocity of a prescribed noise-to-data path.<n>We show that the regression difficulty of Conditional Flow Matching varies systematically along the path.<n>We propose Difficulty-Calibrated Flow Matching, which derives the schedule from the model itself.
  arXiv  Detail & Related papers  (2026-08-21T16:42:52Z)
• Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning [8.596353244934853]
  We reformulate token reduction in whole slide images as a trainable sparsification problem.<n>We show that our framework achieves 73.32% overall accuracy on SlideBench (TCGA)<n>This work provides a highly efficient paradigm for end to end gigapixel whole slide image reasoning.
  arXiv  Detail & Related papers  (2026-06-07T14:07:28Z)
• Spectral Guidance for Flexible and Efficient Control of Diffusion Models [25.912824880444262]
  We introduce Spectral Guidance, a framework for controlling diffusion models by leveraging the intrinsic geometry of the generative process.<n>We characterize them as the singular functions of a conditional expectation operator and show that they can be learned via a self-supervised objective.
  arXiv  Detail & Related papers  (2026-05-27T15:11:09Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning [52.41928980786654]
  We propose PathCTM to enable token-efficient scale-space continuous reasoning for gigapixel whole slide images.<n>PathCTM formulates diagnostic inference as a dynamic sequential information pursuit.<n>It reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation.
  arXiv  Detail & Related papers  (2026-05-19T07:46:44Z)
• Self-Adversarial One Step Generation via Condition Shifting [11.426065945265647]
  APEX is a framework for adversarial correction signals extracted endogenously from a flow model.<n>Our 0.6B model surpasses FLUX-Schnell 12B (20$times$ more parameters) in one step quality.<n>With LoRA tuning on Qwen-Image 20B, APEX reaches a GenEval score of 0.89 at NFE=1 in 6 hours, surpassing the original 50-step teacher (0.87) and providing a 15.33$times$ inference speedup.
  arXiv  Detail & Related papers  (2026-04-14T05:54:33Z)
• CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning [15.930478833291827]
  Fine-tuning large language models (LLMs) with backpropagation achieves high performance but incurs substantial memory overhead.<n>We propose CurvZO, which tracks curvature signals online from scalar ZO feedback.<n>We show that CurvZO consistently improves fine-tuning performance and reduces training time over ZO baselines.
  arXiv  Detail & Related papers  (2026-03-23T09:13:45Z)
• Learnable Chernoff Baselines for Inference-Time Alignment [64.81256817158851]
  We introduce Learnable Chernoff Baselines as a method for efficiently and approximately sampling from exponentially tilted kernels.<n>We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling.
  arXiv  Detail & Related papers  (2026-02-08T00:09:40Z)
• Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance [5.814544128372275]
  We propose Guided Path Sampling (GPS) as a new paradigm for iterative refinement.<n>GPS replaces unstable extrapolation with a principled, manifold-constrained, ensuring the sampling path remains on the data manifold.<n>GPS outperforms existing methods in both perceptual quality and complex prompt adherence.
  arXiv  Detail & Related papers  (2025-12-28T11:12:56Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• Automated classification of pre-defined movement patterns: A comparison between GNSS and UWB technology [55.41644538483948]
  Real-time location systems (RTLS) allow for collecting data from human movement patterns. The current study aims to design and evaluate an automated framework to classify human movement patterns in small areas.
  arXiv  Detail & Related papers  (2023-03-10T14:46:42Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)

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.