Shwetha Somasundaram

Title: Shwetha Somasundaram: Innovator in Large Language Models

Introduction

Shwetha Somasundaram is a prominent inventor based in Chennai, India. She has made significant contributions to the field of artificial intelligence, particularly in the area of large language models. Her innovative work has led to the development of a unique patent that enhances the capabilities of these models.

Latest Patents

Shwetha holds a patent titled "Generating draft sequence rankings for speculative decoding using large language model hidden states." This patent relates to systems, non-transitory computer-readable media, and methods for utilizing hidden states of a large language model to generate responses to queries through speculative decoding. The disclosed systems determine a prompt that includes a query and an input guide text related to the query. They also generate draft predictions by comparing tokens associated with candidate draft predictions to a hidden state of a previous token. This innovative approach allows for more accurate and efficient responses generated by large language models.

Career Highlights

Shwetha is currently employed at Adobe, Inc., where she continues to push the boundaries of technology and innovation. Her work at Adobe has allowed her to collaborate with other talented professionals in the field, contributing to the advancement of artificial intelligence applications.

Collaborations

Some of her notable coworkers include Apoorv Umang Saxena and Anirudh Phukan. Together, they work on various projects that aim to enhance the functionality and performance of large language models.

Conclusion

Shwetha Somasundaram is a trailblazer in the field of artificial intelligence, with her patent showcasing her innovative spirit and technical expertise. Her contributions to large language models are paving the way for future advancements in the industry.