← Search

Junqi Ge

2 accepted papers

2025

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

ICCV 2025poster

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly tasks involving videos, high-resolution images, or lengthy image-text documents. In our work, we first conduct an empirical analysis of VLMs…

2024

Parameter-Inverted Image Pyramid Networks

NeurIPS 2024spotlight

Image pyramids are commonly used in modern computer vision tasks to obtain multi-scale features for precise understanding of images. However, image pyramids process multiple resolutions of images using the same large-scale model, which requires significant computational cost. To overcome this issue,…