Anant Gupta

About Me

Hi! I’m Anant Gupta, a first-year M.S. student in Computer Science at Georgia Tech, where I also earned my B.S. in Computer Science and Mathematics. I’m interested in continual learning, meta-learning, and information retrieval — and more broadly, in how we can build systems that learn, adapt, and teach like humans. I’m fascinated by how models might one day learn efficiently from limited data and generalize across domains, much like people do.

Before starting my M.S., I worked on chaotic dynamical systems and large-scale dataset generation. I’m also passionate about teaching and have been a TA for Automata and Complexity (CS 4510) for four semesters — an experience that’s shaped how I think about learning itself, in both humans and machines.

Research Interests

I’m broadly interested in how humans learn, retain, and reason — and how these principles can inspire more adaptive machine learning systems. We learn continuously, connect ideas across contexts, and refine our understanding through explanation and teaching. My research aims to bring these traits to AI: systems that can recall, relate, and reinterpret knowledge over time, rather than just store it.

Currently, my work spans three directions:

• Information Retrieval : Humans efficiently recall knowledge and retrieve relevant information from external sources while learning. Can we design models that do the same — retrieving, integrating, and reinterpreting information to enhance their reasoning and understanding?

• Continual Learning : Humans learn continuously without catastrophic forgetting. Can we train models that similarly retain past knowledge and adapt to new tasks without revisiting old data?

• LLMs as Teachers : Humans often learn best by teaching — explaining concepts refines understanding and exposes gaps in reasoning. Can large language models emulate this process, teaching advanced theory topics in ways that help them learn and reason more effectively themselves?