Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
Naman Saxena, Mudit Gaur, Vaneet Aggarwal
Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hiera…
cs.LG2026
Oracle-Robust Online Alignment for Large Language Models
Zimeng Li, Mudit Gaur, Vaneet Aggarwal
We study online alignment of large language models under misspecified preference feedback, where the observed preference oracle deviates from an ideal but unknown ground-truth orac…
cs.LG2026
Order-Optimal Sample Complexity of Rectified Flows
Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal
Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport traject…