Owen Oertell — Publications

Scaling Offline RL via Efficient and Expressive Shortcut Models

Efficient Controllable Diffusion via Optimal Classifier Guidance

Improved Bounds for Delay Dependent Bandits

Convergence Of Consistency Model With Multistep Sampling Under General Data Assumptions

TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models

REBEL: Reinforcement Learning via Regressing Relative Rewards

RL for Consistency Models: Reward Guided Text-to-Image Generation with Fast Inference

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning

Dataset Reset Policy Optimization for RLHF

A Kernel Method Approach to Orbital Debris Blast Point Determination

Overdetermined Eigenvector Approach to Passive Angles-Only Relative Orbit Determination