2 papers
cs.CV2025
Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding
Zhanpeng Chen, Mingxiao Li, Ziyang Chen +3
Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibitin…
cs.AI2024
MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training
Zhanpeng Chen, Chengjin Xu, Yiyan Qi +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in processing and generating content across multiple data modalities. However, a significant draw…