AI RESEARCH
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
arXiv CS.AI
•
ArXi:2605.30126v1 Announce Type: cross Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression addresses this by