AI RESEARCH
QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining
arXiv CS.LG
•
ArXi:2505.23004v2 Announce Type: replace Multimodal Large Language Models (MLLMs) encode images into visual tokens, aligning visual and textual signals within a shared latent space to facilitate crossmodal representation learning. The CLIP model is a widely adopted foundational vision language model whose vision encoder has played a critical role in the development of MLLMs such as LLaVA. However, the CLIP vision encoder suffers from notable limitations including being constrained to only handling fixed input resolutions and a failure to produce separated embeddings for dissimilar images.