Junnan Li
Source-listed: Research Director; Director, AI Research Singapore · Salesforce
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationSaved credit: First author · 2022Explore people connected to this work →
- Align before Fuse: Vision and Language Representation Learning with Momentum DistillationSaved credit: First author · 2021Explore people connected to this work →
- Align and Prompt: Video-and-Language Pre-training with Entity PromptsSaved credit: Contributor · 2021Explore people connected to this work →
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsSaved credit: First author · 2023Explore people connected to this work →
- LAVIS: A Library for Language-Vision IntelligenceSaved credit: Contributor · 2022Explore people connected to this work →