Sayna Ebrahimi
Sayna Ebrahimi joined Google Cloud AI Research as a research scientist in November 2021. Her research focuses on tackling real-world large-scale multimodal data distributions while maximizing adaptation and generalization. She also develops label-efficient algorithms which reduce human effort while facilitate transfer of information through unsupervised and semi-supervised models. She received her PhD from UC Berkeley advised by Trevor Darrell. At Berkeley, her research was at the intersection of computer vision and machine learning with specialization in continual learning and domain adaptation.
Research Areas
Authored Publications
Sort By
Google
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
Somesh Jha
Transactions on Machine Learning Research (TMLR) (2024)
Model Swarms: Collaborative Search of Adapted LLM Experts via Swarm Intelligence
Shangbin Feng
Yike Wang
Nathalie Rauschmayr
Yejin Choi
Yulia Tsvetkov
2024
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Somesh Jha
Findings of the Association for Computational Linguistics: EMNLP (2023)
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Han Zhang
Xiaoqi Ren
Jennifer Dy
ECCV 2022
