Dinesha, Ujwal

2 publications

ICLR 2025 DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback Guojun Xiong, Ujwal Dinesha, Debajoy Mukherjee, Jian Li, Srinivas Shakkottai

NeurIPS 2024 Risk-Averse Fine-Tuning of Large Language Models Sapana Chaudhary, Ujwal Dinesha, Dileep Kalathil, Srinivas Shakkottai