Sotabase

Career

· Senior Research Scientist, Google DeepMind2024–
· Research Scientist, Google2021–2024
· Postdoctoral Researcher, Berkeley Artificial Intelligence Research2020–2021
· Research Intern, Facebook AI2019–2019
· Master of Science - MS, Computer Science, 4.0/4.0, University of California, Berkeley2018–2020
· Research Intern, NVIDIA2017–2017
· Graduate Student Researcher, University of California, Berkeley2017–2020
· Doctor of Philosophy (Ph.D.), Computer Science / Mechanical Engineering, University of California, Berkeley2013–2020
· Graduate Student Researcher, University of California, Berkeley2013–2020

Publications (43)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
European Conference on Computer Vision · 2022
702
cited
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Computer Vision and Pattern Recognition · 2018
664
cited
Variational Adversarial Active Learning
IEEE International Conference on Computer Vision · 2019
641
cited
Contrastive Test-Time Adaptation
Computer Vision and Pattern Recognition · 2022
342
cited
Adversarial Continual Learning
European Conference on Computer Vision · 2020
224
cited
Uncertainty-guided Continual Learning with Bayesian Neural Networks
International Conference on Learning Representations · 2019
209
cited
Predicting with Confidence on Unseen Distributions
IEEE International Conference on Computer Vision · 2021
138
cited
Self-Supervised Pretraining Improves Self-Supervised Pretraining
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2021
129
cited
Compositional GAN: Learning Image-Conditional Binary Composition
International Journal of Computer Vision · 2018
98
cited
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
International Conference on Learning Representations · 2020
52
cited
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Conference on Empirical Methods in Natural Language Processing · 2023
50
cited
Gradient-free Policy Architecture Search and Adaptation
Conference on Robot Learning · 2017
30
cited
Peridynamics analysis of the nanoscale friction and wear properties of amorphous carbon thin films
2015
29
cited
Minimax Active Learning
arXiv.org · 2020
28
cited
Compositional GAN: Learning Conditional Image Composition
arXiv.org · 2018
26
cited
Reverse Thinking Makes LLMs Stronger Reasoners
North American Chapter of the Association for Computational Linguistics · 2024
23
cited
Generalized Zero-Shot Learning via Aligned Variational Autoencoders
CVPR Workshops · 2019
20
cited
Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment
2024
20
cited
On-target Adaptation
arXiv.org · 2021
20
cited
Sotabase
Sayna Ebrahimi | Researcher Profile | Sotabase | Sotabase