← authors · overview

• Mobileclip: Fast Image-text Models Through Multi-modal Reinforced Training
  2023 · 36 citations
• VSE++: Improving Visual-semantic Embeddings With Hard Negatives
  2017
• Focallens: Instruction Tuning Enables Zero-shot Conditional Image Representations
  2025
• Fastfill: Efficient Compatible Model Update
  2023