Shashank Gupta

I completed my PhD at the Information Retrieval Lab at the University of Amsterdam, supervised by Prof. Maarten de Rijke and Prof. Harrie Oosterhuis, where I focused on off-policy evaluation and learning for ranking and recommendation systems—developing methods to improve models using logged user interactions.

During my PhD, I got a chance to intern at Meta AI working on applications of these ideas. I developed reinforcement learning methods for fine-tuning text-to-image diffusion models and worked on off-policy learning for large-scale recommendation systems and mixture-of-experts architecture for candidate generator.

My research interests include machine learning, information retrieval, contextual bandits, off-policy methods, and reinforcement learning for post-training of foundation models.

Before my PhD, I was a data scientist at Flipkart in India, where I worked on search ranking and query understanding. I hold a research master’s degree from IIIT Hyderabad.

For more information about my publications, my personal website is: https://shashank-gupta.com/.