1
Text-Only Data Synthesis for Vision Language Model Training
无需图片标注，纯文本就能合成高质量训练数据，大幅降低视觉语言模型的数据门槛。
arXiv:2503.22655v2 Announce Type: replace Abstract: Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pai…