Abhijeet Sinha

I am a PhD student at the National University of Singapore working on Reinforcement Learning and Large Language Models. My topic of interest include Deep Reinforcement Learning, Large Language Models, and their applications in various domains.

Recently I have been working on solution to the mode collapse problem in Deep Reinforcement Learning and Large Language Models. Where during finetuning some outputs become more probable than others and the model fails to generate diverse outputs. I am trying to find a solution to this problem.

I have done my undergraduate studies from IIT Madras.

I like reading about Science, History, and Philosophy and Philosophy of Science.