ADAPT

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

04:00

2026-08-19

arxiv.org

artificial-intelligence

Learning What Not to Learn: Adversarial Disentangled Prompt Tuning for Robust Vision-Language Models

Researchers propose ADAPT (Adversarial Disentangled Prompt Tuning), a robust prompt tuning framework that mitigates robust generalization overfitting in vision-language models by disentangling robust …

04:55

2026-07-01

machinebrief.com

large-language-models

Taming AI Hallucinations: A New Approach with ADAPT

Researchers introduced ADAPT, a framework that reduces hallucinations in multimodal large language models by up to 60% through refining text-to-image cross-attention dynamics. The approach uses a cros…

// co-occurs with top 3 entities

arXiv 1 MLLMs 1 DPO 1

// topics top 5 topics

ai research 2 ai safety 2 artificial intelligence 1 machine learning 1 large language models 1