Sotabase

Career

· Staff Research Scientist, Google DeepMind2024–
· Research Scientist, Google AI2019–2024
· Research Intern, Apple2016–2016
· Research Intern, Google2015–2015
· PhD student, Computer vision and machine learning, GPA=3.95, University of California, Berkeley2014–2019
· Summer Business Analyst, McKinsey & Company2012–2012

Publications (31)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
International Conference on Learning Representations · 2021
1,168
cited
PaLI: A Jointly-Scaled Multilingual Language-Image Model
International Conference on Learning Representations · 2022
921
cited
Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning
Proceedings of the National Academy of Sciences of the United States of America · 2019
226
cited
DeepBox: Learning Objectness with Convolutional Networks
IEEE International Conference on Computer Vision · 2015
184
cited
F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models
arXiv.org · 2022
173
cited
Learning Open-World Object Proposals without Learning to Classify
IEEE Robotics and Automation Letters · 2021
155
cited
From Lifestyle Vlogs to Everyday Interactions
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
126
cited
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
IEEE International Conference on Computer Vision · 2019
125
cited
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Computer Vision and Pattern Recognition · 2023
113
cited
Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection
International Conference on Medical Image Computing and Computer-Assisted Intervention · 2018
104
cited
Zero-Shot Detection via Vision and Language Knowledge Distillation
arXiv.org · 2021
89
cited
Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
European Conference on Computer Vision · 2020
76
cited
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Computer Vision and Pattern Recognition · 2022
69
cited
Open-Vocabulary Object Detection upon Frozen Vision and Language Models
International Conference on Learning Representations · 2023
55
cited
Contrastive Feature Masking Open-Vocabulary Vision Transformer
IEEE International Conference on Computer Vision · 2023
39
cited
DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model
Neural Information Processing Systems · 2023
37
cited
Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image
IEEE International Conference on Computer Vision · 2021
37
cited
MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
Trans. Mach. Learn. Res. · 2023
31
cited
Video Question Answering with Iterative Video-Text Co-Tokenization
European Conference on Computer Vision · 2022
21
cited
Sotabase
Weicheng Kuo | Researcher Profile | Sotabase | Sotabase