Nathan Kallus
- $Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
- Efficient Adaptive Experimentation with Noncompliance
- GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
- Simulation-Based Inference for Adaptive Experiments
- Value-Guided Search for Efficient Chain-of-Thought Reasoning