Zhiding Yu

Zhiding Yu is a principal research scientist and research lead at NVIDIA Research. Before joining NVIDIA, he received his Ph.D. in ECE from Carnegie Mellon University in 2017. His research interests include Transformers, foundation models, and multimodal LLMs, with their applications to building the next-generation general intelligence. He is a recipient of multiple best paper awards and challenge winners. At NVIDIA, he led numerous efforts to develop state-of-the-art models, data engines and autonomous driving systems.
Avatar photo

Posts by Zhiding Yu

GIF of several autonomous driving views.
Generative AI Jun 17, 2024

End-to-End Driving at Scale with Hydra-MDP

Building an autonomous system to navigate the complex physical world is extremely challenging. The system must perceive its environment and make quick, sensible... 6 MIN READ
High quality instance segmentation done fast and efficiently with DiscoBox.
Computer Vision / Video Analytics Mar 24, 2022

Segment Objects without Masks and Reduce Annotation Effort Using the DiscoBox DL Framework

Instance segmentation is a core visual recognition problem for detecting and segmenting objects. In the past several years, this area has been one of the holy... 5 MIN READ
Data Science Nov 17, 2020

Building a Benchmark for Human-Level Concept Learning and Reasoning

Humans have an inherent ability to learn novel concepts from only a few samples and generalize these concepts to different situations. Even though today’s... 10 MIN READ