AI RESEARCH
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
arXiv CS.CV
•
ArXi:2604.06912v1 Announce Type: new MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism with visually redundant tokens, severely bottlenecking inference throughput while ignoring spatial sparsity and query intent. To overcome this, we propose Q-Zoom, a query-aware adaptive high-resolution perception framework that operates in an efficient coarse-to-fine manner.