AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment

Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 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 utilization loss L_u (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 46.71 -> 47.81Improved
add semantic integrity loss L_s (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 45.84 -> 47.81Improved
add label prediction loss L_p (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 11.44 -> 47.81Improved
use Gaussian locality prior instead of Laplacian prior (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 47.72 -> 47.81No clear effect
use locality-aware fusion instead of global fusion (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 44.64 -> 47.81Improved
use locality-aware fusion instead of convolution-based fusion (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 46.95 -> 47.81Improved
add data augmentation (ablation)PromptHub N=16 · Pascal-5i segmentationmean mIoU: 47.07 -> 47.81Improved
add data augmentation (ablation)PromptHub N=1 · Pascal VOC2012 detectionmIoU: 43.52 -> 44.51Improved
increase prompts from N=1 to N=16PromptHub · Pascal-5i segmentationmean mIoU: 45.17 -> 47.81Improved
replace Condenser with PromptHub fusion under N=16multi-prompt VICL · Pascal-5i segmentation (trained on COCO-5i)mean mIoU: 40.52 -> 42.17Improved
replace hyperparameter sigma with query-adaptive sigma (ablation)PromptHub N=1 · Pascal-5i segmentationmean mIoU: 45.17 -> 45.86No clear effect
replace Condenser with PromptHub under flipped-query misalignmentfusion module N=16 · Spatial misalignmentperformance drop: -1.39 -> -0.66Improved

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