# Prompt Tuning

3 related articles

Subscribe to updates

aclanthology.org Oct 21, 2026
Medical vision-language models get a calibration stress test: 1,638 controlled runs expose where confidence breaks
Evaluation of medical vision-language models has centered on accuracy, leaving whether their confidence is trustworthy largely untested. MVC-Bench splits calibration into three axes, robustness, effectiveness of calibration and prompt-tuning methods, and stability under prompt templates and random seeds, spanning fundus, histopathology and chest X-ray modalities, eight backbones and six prompt-tuning methods across 1,638 controlled experiments. In-domain calibration rankings barely survive domain shift, with a mean Kendall correlation of -0.0598 over 30 rank-transfer tests and none significantly positive; the proposed Multi-Class Margin regularizer reaches the lowest ECE in 10 of 12 in-domain settings but only 4 under domain shift.
Evaluation of medical vision-language models has centered on accuracy, leaving whether their confidence is trustworthy largely untested. MVC-Bench splits calibration into three axes, robustness, effectiveness of calibration and prompt-tuning methods, and stability under prompt templates and random seeds, spanning fundus, histopathology and chest X-ray modalities, eight backbones and six prompt-tuning methods across 1,638 controlled experiments. In-domain calibration rankings barely survive domain shift, with a mean Kendall correlation of -0.0598 over 30 rank-transfer tests and none significantly positive; the proposed Multi-Class Margin regularizer reaches the lowest ECE in 10 of 12 in-domain settings but only 4 under domain shift.
MVC-Bench Multi-Class Margin Regularization (MCM)Classifier Calibration Medical Vision-Language Models Prompt Tuning
arXiv Sep 25, 2026
PromptGate lifts query purity in open-set federated active learning from about 60% to above 95% using federated learnable prompts
PromptGate introduces a client-adaptive vision-language gating module for open-set federated active learning (OS-FAL): it learns class-specific context (CSC) prompts on a frozen BiomedCLIP backbone, splitting them into global tokens aggregated via FedAvg and client-local tokens, uses VLM pseudo-labels to filter the unlabeled pool into a high-purity ID candidate pool before querying, and then hands that pool to any downstream active learning strategy; on the FedISIC and FedEMBED federated medical imaging benchmarks, static VLM prompting degrades to roughly 50% ID purity, whereas PromptGate maintains above 95% purity with 98% OOD recall.
PromptGate introduces a client-adaptive vision-language gating module for open-set federated active learning (OS-FAL): it learns class-specific context (CSC) prompts on a frozen BiomedCLIP backbone, splitting them into global tokens aggregated via FedAvg and client-local tokens, uses VLM pseudo-labels to filter the unlabeled pool into a high-purity ID candidate pool before querying, and then hands that pool to any downstream active learning strategy; on the FedISIC and FedEMBED federated medical imaging benchmarks, static VLM prompting degrades to roughly 50% ID purity, whereas PromptGate maintains above 95% purity with 98% OOD recall.
University Hospital Bonn University of Bonn
Adea Nesturi（First author）Shadi Albarqouni（Corresponding author）
PromptGate Open-Set Federated Active Learning Prompt Tuning Vision-Language Models Federated Learning
International Journal of Computer Vision Sep 25, 2026
Tsinghua survey on parameter-efficient fine-tuning: LoRA trains only 4.7M parameters on GPT-3, saving over 99.97% and slightly improving on full fine-tuning
This survey by Tsinghua University's Knowledge Engineering Group systematically reviews parameter-efficient fine-tuning (PEFT) for foundation models (FMs), organizing methods into five categories—selective, additive, prompt, reparameterization, and hybrid—and reviewing their applications across five model structures (LLMs, vision foundation models, vision-language models, visual content generation models, and multimodal foundation models), while deriving three trend observations from Semantic Scholar citation counts (PEFT growing broadly; LLMs and VFMs dominating; MFMs relatively underexplored) and identifying reliability, interpretability, and unified benchmarks as future directions.
This survey by Tsinghua University's Knowledge Engineering Group systematically reviews parameter-efficient fine-tuning (PEFT) for foundation models (FMs), organizing methods into five categories—selective, additive, prompt, reparameterization, and hybrid—and reviewing their applications across five model structures (LLMs, vision foundation models, vision-language models, visual content generation models, and multimodal foundation models), while deriving three trend observations from Semantic Scholar citation counts (PEFT growing broadly; LLMs and VFMs dominating; MFMs relatively underexplored) and identifying reliability, interpretability, and unified benchmarks as future directions.
Tsinghua University
Dan Zhang（First author）Jie Tang（Corresponding author）
Parameter-Efficient Fine-Tuning Foundation Models LoRA Prompt Tuning Low-Rank Adaptation

You’re all caught up

Medical vision-language models get a calibration stress test: 1,638 controlled runs expose where confidence breaks

PromptGate lifts query purity in open-set federated active learning from about 60% to above 95% using federated learnable prompts

Tsinghua survey on parameter-efficient fine-tuning: LoRA trains only 4.7M parameters on GPT-3, saving over 99.97% and slightly improving on full fine-tuning