mlsanityData to 7 Oct 2026

TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models

arXiv 2607.09562 ↗First posted 10 Jul 2026cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA, a purely training-free few-shot adaptation method for Medical VLMs, which is fast and model-agnostic. TCLA corrects inference logits based on a small set of support samples, boosting pretrained VLMs performance by improving inter-class deconfusion and reducing domain shift. Extensive experiments on nine datasets across multiple medical imaging modalities including X-ray, Ultrasound, MRI, CT, Histopathology, demonstrate that TCLA consistently improves OOD performance of Medical VLMs and, in most of cases, outperforms existing training-based adaptation methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 34 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

25 of 34 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature13 Jan
  2. 2024BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models21 Nov
  3. 2024Few-shot Adaptation of Medical Vision-Language Models5 Sep
  4. 2024DeViDe: Faceted medical knowledge for improved medical vision-language pre-training4 Apr

Other references · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  4. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  5. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  6. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  7. 2014How transferable are features in deep neural networks?cited by 1,216
  8. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  9. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
  10. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  11. 2023Visual-Language Prompt Tuning with Knowledge-guided Context Optimizationcited by 307
  12. 2020COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Imagescited by 264
9 more
  1. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  2. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 192
  3. 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
  4. 2023MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiologycited by 149
  5. 2023Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinementcited by 84
  6. 2017Gaussian Prototypical Networks for Few-Shot Learning on Omniglotcited by 20
  7. 2025ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Modelscited by 15
  8. 2025Logits DeConfusion with CLIP for Few-Shot Learningcited by 11
  9. 2025Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Settingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation
  2. 2026Semi-Supervised Few-Shot Adaptation of Vision-Language Models
  3. 2025Full Conformal Adaptation of Medical Vision-Language Models
  4. 2025Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift
  5. 2025Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review
  6. 2025Scaling Down to Scale Up: Towards Operationally-Efficient and Deployable Clinical Models via Cross-Modal Low-Rank Adaptation for Medical Vision-Language Models
  7. 2025How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study
  8. 2026CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift