Urvashi Khandelwal
Source-listed: 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 →
- Few-Shot Recalibration of Language ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Pix2Struct: Screenshot Parsing as Pretraining for Visual Language UnderstandingSaved credit: Contributor · 2023Explore people connected to this work →
- From Pixels to UI Actions: Learning to Follow Instructions via Graphical User InterfacesSaved credit: Contributor · 2023Explore people connected to this work →
- Nearest Neighbor Machine TranslationSaved credit: First author · 2021Explore people connected to this work →