Fangyu Liu
Source-listed: Staff Research Scientist · Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Gemini: A Family of Highly Capable Multimodal ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextSaved credit: Contributor · 2024Explore people connected to this work →
- PaliGemma: A versatile 3B VLM for transferSaved credit: Contributor · 2024Explore people connected to this work →
- DePlot: One-shot visual language reasoning by plot-to-table translationSaved credit: First author · 2023Explore people connected to this work →
- MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart DerenderingSaved credit: First author · 2023Explore people connected to this work →