Zhenzhen Li

Title: Innovations of Zhenzhen Li in Vision-Language Models

Introduction

Zhenzhen Li is an accomplished inventor based in Gibsonia, PA (US). She has made significant contributions to the field of artificial intelligence, particularly in the area of vision-language models. Her innovative work has led to the development of a unique patent that enhances the capabilities of these models.

Latest Patents

Zhenzhen Li holds a patent titled "Scalable prompt learning for large vision-language models." This patent describes a method for generating text-driven prompts and class prediction probabilities using a vision-language model (VLM). The process involves receiving candidate class names associated with various candidate classes for images. It also includes generating class text tokens based on text descriptions of the candidate class names. Furthermore, the method generates context prompt vectors that define context information related to an image classification task. By appending respective class text tokens to the context prompt vectors, the VLM can generate and output class prediction probabilities for sample images.

Career Highlights

Zhenzhen Li is currently employed at Robert Bosch, where she applies her expertise in artificial intelligence and machine learning. Her work at the company has allowed her to collaborate with other talented professionals in the field.

Collaborations

Some of her notable coworkers include Chen Qiu and Xingyu Li, who contribute to the innovative environment at Robert Bosch.

Conclusion

Zhenzhen Li's contributions to the field of vision-language models exemplify her innovative spirit and dedication to advancing technology. Her patent reflects her ability to merge language and visual data, paving the way for future advancements in artificial intelligence.