llm-kb
← Back to research
Paper

TCLA: Training-Free Few-Shot Adaptation for Medical VLMs

Researchers propose TCLA, a training-free method to adapt medical Vision-Language Models (VLMs) to out-of-distribution data using only a few examples. It corrects inference logits without additional trainable components, improving stability in low-data regimes like 1-shot. The method is model-agnostic and fast, addressing domain shifts and class bias in medical imaging.

0 engagement·1 source·Fri, Jul 10, 2026, 04:06 PM
The paper introduces TCLA (Training-Free Class-wise Logit Adaptation), a purely training-free few-shot adaptation method for Medical VLMs. Unlike existing approaches that require fine-tuning or additional trainable components, TCLA corrects inference logits based on a small set of labeled examples. This makes it stable even in extremely low-data regimes (e.g., 1-shot) and robust across different medical data types. The method is model-agnostic and computationally efficient, offering a practical solution for adapting pretrained VLMs to specific medical domains without retraining.

Entities

TCLA(tool)Medical Vision-Language Models(concept)

Related

PaperFri, Jul 10, 2026, 02:19 PM

Robustifying Vision-Language Models via Test-Time Prompt Adaptation

A new arxiv paper proposes a test-time prompt adaptation method to improve robustness of Vision-Language Models like CLIP against adversarial perturbations. The approach leverages distributional structure rather than sample-level heuristics to distinguish adversarial mispredictions from true semantic consistency.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 02:57 PM

BTHA: A Backbone-Transferable Adapter for Text-Guided Medical Segmentation

Researchers propose BTHA, a hierarchical adapter framework that decouples language guidance from vision and text backbones in text-guided medical image segmentation. BTHA uses a stable feature-level interface to enable reuse of language modules across heterogeneous encoder pairs without network redesign. This addresses a key limitation of existing tightly coupled architectures.

0 engagement·1 source·arxiv
arXiv
PaperThu, Jul 9, 2026, 10:34 PM

CLAP paper proposes direct VLM-to-VLA adaptation to isolate semantic transfer

A new arXiv paper introduces CLAP, a method that converts pretrained vision-language models (VLMs) into vision-language-action models (VLAs) with minimal architectural changes, avoiding the distribution mismatch caused by predicting actions as bare numeric tokens. The approach aims to clarify how VLM capabilities transfer across model scales for robot control.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 03:35 PM

ALICE: Multi-stage distillation unifies eight pathology foundation models into one backbone

Researchers introduce ALICE, a unified pathology foundation model trained via multi-stage agglomerative distillation from eight teacher models spanning vision-only, vision-language, and slide-level expertise. Pretrained on 24,985,184 tile-level and 155,604 high-resolution images, ALICE consolidates fragmented capabilities into a single backbone and is evaluated across 21 task scenarios.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 05:39 AM

New paper proposes LLM-GCN hybrid for semi-supervised image classification

A new arXiv paper introduces a method that integrates Large Language Models with Graph Convolutional Networks to improve semi-supervised image classification. The approach addresses the challenge of graph construction for visual data by leveraging LLMs to generate better graph representations, potentially reducing the need for labeled datasets.

0 engagement·1 source·arxiv
arXiv