news

Sep 23, 2025 I’m proud to announce that our preprint Evaluation-Aware Reinforcement Learning has been published on arXiv!
Sep 19, 2025 I’m pleased to have served as a reviewer for the Reliable ML from Unreliable Data workshop at NeurIPS 2025.
Sep 08, 2025 I’ve joined Amazon as an Applied Scientist Intern, working on agentic evaluation frameworks for language model agents.
May 09, 2025 I’m pleased to announce that our paper Reinforcement Learning from Human Feedback with High-Confidence Safety Guarantees has been accepted for publication at RLC 2025!
Apr 04, 2025 I’m pleased to have served as a Senior Reviewer for RLC 2025! (Last year, I served as a Technical Reviewer for RLC 2024.)
Mar 16, 2025 I’m proud to announce that our preprint Are Deep Speech Denoising Models Robust to Adversarial Noise? has been published on arXiv!
Feb 25, 2025 I’m proud to announce that our preprint Supervised Reward Inference has been published on arXiv!