Cite
Notes
Only stored in your browser.
Attribution
Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding
arXiv 2025
MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training
arXiv 2024
from 2 papers
Chengjin Xu
Jian Guo
Mingxiao Li
Nan Du
Xiaolong Li
Yiyan Qi
Yuexian Zou
Ziyang Chen