AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Knowledge-Enhanced Explainable Prompting for Vision-Language Models

Yequan Bie, Andong Tan, Zhixuan Chen, Zhiyuan Cai, Luyang Luo, Hao Chen

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add logit_IPA attention logit to KEEP (ablation)KEEP · Medical averageaccuracy (%): 85.98 -> 87.09Improved
add logit_IPA attention logit to KEEP (ablation)KEEP · Natural averageaccuracy (%): 80.16 -> 80.88Improved
add image-prompt matching contrastive loss L_IPM (ablation)KEEP · Medical averageaccuracy (%): 84.69 -> 87.09Improved
add image-prompt matching contrastive loss L_IPM (ablation)KEEP · Natural averageaccuracy (%): 79.61 -> 80.88Improved
add cross-entropy fusion loss L_CLS (ablation)KEEP · Medical averageaccuracy (%): 80.50 -> 87.09Improved
add cross-entropy fusion loss L_CLS (ablation)KEEP · Natural averageaccuracy (%): 70.25 -> 80.88Improved
use fine-grained domain-specific knowledge prompts instead of no, random, general or intervened knowledge (ablation)KEEP · all eight datasetsaccuracyImproved
adapt CLIP with KEEP prompt learningCLIP · Medical averageaccuracy (%): 43.59 -> 87.09Improved
replace LASP with KEEP at 10% training dataCCBTM · CCBTM (10% data)accuracy (%): 82.69 -> 92.89Improved
reduce CCBTM training data from 50% to 10% for KEEPKEEP · CCBTMaccuracy (%): 94.73 -> 92.89No clear effect
use KEEP instead of BiomedCoOp (BiomedCLIP-based)medical datasets · Medical averageaccuracy (%): 79.62 -> 87.09Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy