Scholar
Zhaowei Cai
Google Scholar ID: uRrSKVIAAAAJ
Amazon Artificial General Intelligence
Citations & Impact
Citations
13,804
H-index
17
i10-index
20
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- - Papers published:
- - Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge, NeurIPS 2025
- - Enhancing Numerical Prediction of MLLMs with Soft Labeling, ICCV 2025
- - The Amazon Nova Family of Models: Technical Report and Model Card, Tech Report, 2024
- - Amazon Nova Premier: Technical report and model card, Tech Report, 2025
- - Scaling up Image Segmentation across Data and Tasks, CVPR 2025
- - Mixed-Query Transformer: A Unified Image Segmentation Architecture, arXiv, 2024
- - Open-World Dynamic Prompt and Continual Visual Representation Learning, ECCV 2024
- - PolyFormer: Referring Image Segmentation as Sequential Polygon Generation, CVPR 2023
- - Masked Vision and Language Modeling for Multi-modal Representation Learning, ICLR 2023
- - Semi-supervised Vision Transformers at Scale, NeurIPS 2022
- - X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks, ECCV 2022
- - Area Chair for CVPR 2023 and ICCV 2023
Research Experience
- - Senior Applied Scientist with Amazon AGI multimodal team
- - Research intern at Facebook AI Research (FAIR), Micsoft Research Redmond (MSR), IBM T. J. Watson Research, and Institute of Automation, Chinese Academy of Sciences (CASIA)
Education
- - Ph.D. and M.S. degrees from UC San Diego, advised by Nuno Vasconcelos
Background
- - Research Interests: Computer vision and machine learning, especially vision and language understanding, object detection, semi- and self-supervised learning, low-precision neural networks, etc.