2 papers
cs.CV2024
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Xin Xiao, Bohong Wu, Jiacong Wang +3
Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method…
cs.CV2024
World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
Jiacong Wang, Bohong Wu, Haiyong Jiang +4
Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The…