← authors · overview

• LAION-5B: An open large-scale dataset for training next generation image-text models
  2022 · 1040 citations
• Objaverse-XL: A Universe of 10M+ 3D Objects
  2023 · 40 citations
• Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
  2022 · 27 citations
• Patching open-vocabulary models by interpolating weights
  2022 · 27 citations
• Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
  2023 · 17 citations
• CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
  2022 · 10 citations
• Does progress on ImageNet transfer to real-world datasets?
  2023 · 7 citations
• Robust fine-tuning of zero-shot models
  2021 · 5 citations
• Why are Visually-Grounded Language Models Bad at Image Classification?
  2024 · 3 citations
• Objaverse: A Universe of Annotated 3D Objects
  2022 · 2 citations
• Multilingual Diversity Improves Vision-Language Representations
  2024 · 2 citations
• Data or Language Supervision: What Makes CLIP Better than DINO?
  2025
• A Sober Look at the Robustness of CLIPs to Spurious Features
  2024