2025: First paper as supervisor, “Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization,” accepted to ICLR-2025; two additional papers accepted to AISTATS-2025
2024: Paper “Demonstration-Regularized RL” accepted to ICLR-2024; paper “Generative Flow Networks as Entropy-Regularized RL” received an oral presentation at AISTATS-2024
2023: Paper “Model-free Posterior Sampling via Learning Rate Randomization” accepted to NeurIPS-2023
2023: Paper “Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold” presented at COLT-2023
2023: Paper “Fast Rates for Maximum Entropy Exploration” accepted to ICML-2023
February 2025: Released internship results titled “On teacher Hacking in Language Model Distillation”