Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks. However, these benchmarks keep a static nature and overlap with the pre-training da...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-11
Hauptverfasser:	Yang, Yue, Zhang, Shuibai, Shao, Wenqi, Zhang, Kaipeng, Yi, Bin, Wang, Yu, Luo, Ping
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmarks Contamination Modules Performance evaluation Task complexity Vision Visual perception Visual tasks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!