HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding

20 December 2024

Papers citing "HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding"

1 / 1 papers shown

Title
Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training Yiran Chen Hao Peng Tong Zhang Heng Ji VLM 28 0 0 13 May 2025