Date of Award

2026

Degree Name

Computer Science

College

College of Engineering and Computer Sciences

Type of Degree

M.S.

Document Type

Thesis

First Advisor

Dr. Husnu Narman

Second Advisor

Dr. Pingping Zhu

Third Advisor

Dr. Haroon Malik

Abstract

Human gesture inference has broad applications ranging from sign language interpretation to device control. Traditional methods often rely on extensive manually labeled hand datasets for deep learning. Furthermore, they are typically limited to a discrete set of gestures existing in these datasets. Large Language Models (LLMs) created by enterprise companies such as OpenAI have demonstrated positive results in many artificial intelligence tasks, with a notable strength being their adaptability. Existing literature has shown that LLM based systems can not only perform gesture inference but can propose user intent provided with a context and list of possible actions. We propose an ablative study of an LLM based gesture inference system applied to the context of guiding an autonomous agent through a maze. Measuring distance from the goal, inference time, and token expenditure. We intend to iteratively measure several techniques to determine the optimal LLM architecture for gesture based guidance.

Subject(s)

Computer science.

Artificial intelligence.

Machine learning.

Natural language processing (Computer science)

User interfaces (Computer systems)

Human-computer interaction.

Share

COinS