Tokenizer Generator Coupling in Medical Image Generation

• URL: http://arxiv.org/abs/2608.07713v1
• Date: Fri, 07 Aug 2026 18:57:09 GMT
• Title: Tokenizer Generator Coupling in Medical Image Generation
• Abstract summary: Latent medical image generators usually treat the tokenizer as fixed preprocessing.<n>We test whether this separation is valid in a controlled ChestMNIST study at 64x64.<n> rankings depend jointly on the tokenizer, generator, and sampler.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent medical image generators usually treat the tokenizer as fixed preprocessing. We test whether this separation is valid in a controlled ChestMNIST study at 64x64, crossing discrete tokenizers, generator families, and sampler settings under a shared latent grid, with continuous-latent reference cells. In this controlled setting, rankings depend jointly on the tokenizer, generator, and sampler: the best quantizer changes with the generator, and validation-based sampler selection changes the apparent generator ranking. We retrain the vocabulary-1024 interaction block at three seeds and the interaction survives (6 of 9 pairwise quantizer comparisons exceed three seed standard deviations), and we scope the wider single-seed grid accordingly. Reconstruction PSNR alone is not a reliable selection criterion; we instead introduce a generator-free statistic, neighbour-conditional predictive gain, that separates the quantizer families by downstream generation quality (rank-AUC 1.00) where reconstruction PSNR and marginal token entropy do not. On LFQ-1024, retuning D3PM and SE-D3PM (selected on a held-out validation split) moves them from default FID-192 0.44/0.41 to 0.09/0.10 at lower NFE, replicated across seeds; the continuous references were not given an equivalent sampler sweep. We report FID-192 as an internal ranking metric; it ranks consistently with standard FID-2048 (Spearman 0.80) and with a label-free classifier two-sample test (0.78). We interpret these results through a rate-distortion-modelability framing, where modelability is conditional on the generator, sampler, and inference budget. All experiments are at 64x64 on low-resolution medical-style images, unconditional, and evaluated with non-clinical FID-based metrics, and we scope every claim to that setting. Code: https://github.com/liamchalcroft/medtokenizers and https://github.com/liamchalcroft/medlatents.

Related papers

• Frequency-Decorrelated Temporal Ensembles for EEG--fNIRS Imagined-Handwriting Decoding [5.096813697804564]
  The Multimodal Brain-Computer Interface Grand Challenge provides synchronized EEG and fNIRS for four-class subject-independent handwriting-trajectory classification.<n>We propose FRED, a task-adapted system that trains a compact multi-scale temporal network on three complementary EEG frequency views.<n>A modality audit finds fNIRS-only decoding at chance (0.2511 overall), while adding fNIRS to EEG changes accuracy by only +0.0025.
  arXiv  Detail & Related papers  (2026-08-04T06:08:11Z)
• GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification [17.505968172455784]
  GenSyn10 is a CIFAR-10-aligned synthetic image dataset of 60,000 images (10 classes, 32$times$32, 50k/10k split) generated using three state-of-the-art models.<n>We evaluate 17 image classification models under a four-stage protocol: real-data baseline, zero-shot transfer, fine-tuning, and retention.<n>Despite a measurable domain gap, CIFAR-10-trained models achieve up to 96.86% zero-shot accuracy on GenSyn10, increasing to 99.88% after fine-tuning.
  arXiv  Detail & Related papers  (2026-07-10T09:47:16Z)
• Representation Distribution Matching for One-Step Visual Generation [107.84208192304455]
  We elucidate the design space of Representation Distribution Matching (RDM)<n>We identify two design axes, how the distributions are compared and the representations they are compared in, and controlled studies along them yield three findings.<n>The same recipe post-trains the four-step FLUX.2 [klein] into a one-step generator, surpassing the four-step version on GenEval, 0.826 to 0.794, and on PickScore, 22.76 to 22.58, in 90 H200 GPU-hours.
  arXiv  Detail & Related papers  (2026-07-02T16:15:38Z)
• Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations [59.34593956287438]
  Aionoscope is a diagnostic tool for inspecting latent-state accessibility in frozen time-series representations.<n>Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels.
  arXiv  Detail & Related papers  (2026-07-01T13:54:20Z)
• The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation [55.62875959637507]
  We treat FID as a random variable on a two-axis panel of training and generation seeds.<n>We measure its variance directly on several hundred SiT networks trained on class-conditional ImageNet 256x256.
  arXiv  Detail & Related papers  (2026-06-18T17:49:32Z)
• How Fragile Are Training-Free AI-Generated Image Detectors? A Controlled Audit of Score Direction, Preprocessing, and Compression [6.3999417080764225]
  We audit two representative training-free scores -- an autoencoder-reconstruction score (AEROBLADE-style) and a noise-perturbation feature-similarity score (RIGID-style)<n>The audit yields three cautionary findings.
  arXiv  Detail & Related papers  (2026-06-18T17:05:51Z)
• A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI [0.0]
  We present a benchmark that isolates the contribution of a quantum generator to brain-MRI augmentation.<n>No augmentation variant significantly outperforms real-data-only training.<n>We release the protocol as a testbed for rigorous evaluation of quantum generative augmentation in medical imaging.
  arXiv  Detail & Related papers  (2026-06-17T11:54:17Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval [0.0]
  Legal teams increasingly use machine learning to triage large volumes of contractual evidence.<n>Many models are opaque, non-deterministic, and difficult to align with frameworks such as HIPAA or NERC-CIP.<n>We study a simple, reproducible alternative based on deterministic dual encoders and transparent fuzzy triage bands.
  arXiv  Detail & Related papers  (2026-03-08T00:31:34Z)
• S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
  In this paper we address the problem of classification in the presence of label noise. In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space. Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
  arXiv  Detail & Related papers  (2021-11-22T15:49:20Z)
• Sampling-Decomposable Generative Adversarial Recommender [84.05894139540048]
  We propose a Sampling-Decomposable Generative Adversarial Recommender (SD-GAR) In the framework, the divergence between some generator and the optimum is compensated by self-normalized importance sampling. We extensively evaluate the proposed algorithm with five real-world recommendation datasets.
  arXiv  Detail & Related papers  (2020-11-02T13:19:10Z)

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.