← authors · overview

• VL-BERT: Pre-training of Generic Visual-Linguistic Representations
  2019 · 785 citations
• VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
  2021 · 288 citations
• Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
  2022 · 151 citations
• LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
  2020 · 59 citations
• VL-BEiT: Generative Vision-Language Pretraining
  2022 · 22 citations
• CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
  2022 · 2 citations
• Distilled Dual-Encoder Model for Vision-Language Understanding
  2021 · 1 citations
• VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning
  2022 · 1 citations
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
  2025
• mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data
  2025
• Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
  2025
• Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
  2020
• Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation
  2024