Scholar
Yin Cui
Google Scholar ID: iP5m52IAAAAJ
Research Scientist, NVIDIA
Citations & Impact
Citations
15,733
H-index
30
i10-index
43
Publications
20
Co-authors
176
list available
Publications
Resume (English only)
Academic Achievements
- PAMI Mark Everingham Prize (2023) - COCO dataset
- VideoGLUE: Video General Understanding Evaluation of Foundation Models (TMLR 2024)
- Why Fine-grained Labels in Pretraining Benefit Generalization? (TMLR 2024)
- Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation (CVPR 2024)
- Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception (NeurIPS 2023)
- DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model (NeurIPS 2023)
- A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models (ICML 2023)
- F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models (ICLR 2023)
- Scaling Open-Vocabulary Image Segmentation with Image-Level Labels (ECCV 2022)
- Open-vocabulary Object Detection via Vision and Language Knowledge Distillation (ICLR 2022)
- Surrogate Gap Minimization Improves Sharpness-Aware Training (ICLR 2022)
Education
- Ph.D. in Computer Science from Cornell University and Cornell Tech in 2019, advised by Professor Serge Belongie.
Background
- Currently a research scientist at NVIDIA. Previously, a research scientist at Google. Main research interests are Generative AI and Multimodal.
Miscellany
- No other information provided
