Soravit Changpinyo
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextSaved credit: Contributor · 2024Explore people connected to this work →
- PaLI-X: On Scaling up a Multilingual Vision and Language ModelSaved credit: Contributor · 2024Explore people connected to this work →
- PaLI: A Jointly-Scaled Multilingual Language-Image ModelSaved credit: Contributor · 2023Explore people connected to this work →
- MaXM: Towards Multilingual Visual Question AnsweringSaved credit: Contributor · 2023Explore people connected to this work →
- Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsSaved credit: Contributor · 2021Explore people connected to this work →