11 datasets

The '11 datasets' benchmark contains a variety of datasets used to evaluate the effectiveness of Multimodal Prompt Learning methods, specifically in assessing their performance in robust generalization and cross-modal alignment.

Papers using 11 datasets (4)

CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment2026TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs2026From Points to Clouds: Learning Robust Semantic Distributions for Multi-modal Prompts2025Learning Domain Invariant Prompt for Vision-Language Models2022 · 4 cites