PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding 文章

ArXiv CS.CV2026-05-29NEWSen作者: Selim Kuzucu, Alessio Tonioni, Vasile Lup, Bernt Schiele, Federico Tombari, Muhammad Ferjad Naeem
查看原文 →
关系图谱

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding · 相关技术

相关技术

PARCELnested query resamplingnested poolingElastic visual-token compressionLarge vision-language model