← authors · overview

• Write and Paint: Generative Vision-Language Models are Unified Modal Learners
  2022 · 5 citations
• X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
  2022 · 5 citations
• VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models
  2022 · 4 citations
• Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training
  2025
• EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
  2022