About Me
I am a PhD candidate in Psychology at Stanford University, working in the Stanford Autonomous Agents Lab with Nick Haber. My research focuses on LLM post-training, reinforcement learning, and reward modeling, with roots in computational cognitive science.
I study how to train language models to reason more effectively, how to provide useful feedback during learning, and how to evaluate what models learn. My recent work spans dense rewards for exploratory RL, adaptive reasoning budgets, reward-model biases, and human-preference evaluation. I also work on theory of mind in multi-agent systems and benchmarks connecting human and machine learning.
Previously, I earned an M.S. in Computer Science and undergraduate degrees in Informatics and Mathematics at Indiana University.
CV (PDF) · Google Scholar · GitHub · Email
Selected research
ExpRL: Exploratory RL for LLM Mid-Training
COLM 2026
RL-based mid-training with dense outcome- and process-level rewards from a reference-guided LLM judge. On held-out AIME 2026 with Qwen3-4B, ExpRL improved pass@1 over the strongest baseline at each stage by 3.6 points after priming and 4.7 points after identical sparse-GRPO post-training.
One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
ICML 2026
Identified persistent length, uncertainty, position, sycophancy, and model-style biases in language reward models. Null-space probe projections reduced three of these biases without retraining or loss on RewardBench-2.
LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing
EACL 2026 · Long Paper
A creative-writing evaluation benchmark with 43k training pairs and a 2.5k-pair debiased, human-labeled test set. Trained reward models improved human-preference agreement by 5 points over the strongest zero-shot judge.
Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
NeurIPS 2025 Efficient Reasoning Workshop · Spotlight
A GRPO-compatible adaptive length penalty reduced DeepScaleR-1.5B generation length by more than 50% at matched accuracy across MATH-500, AIME, and OlympiadBench, while allocating 5.35× more tokens to hard prompts than easy ones.
Industry research
Radical Numerics
Member of Technical Staff Intern
October 2025 - January 2026
Built an end-to-end post-training and evaluation stack for DPO-tuning genomic foundation models, including preference-data processing, training orchestration, and evaluation for biomedical DNA-sequence design.
Toyota Research Institute
Research Scientist Intern, Human-AI Interactive Learning
June - September 2025
Developed a teacher-training objective for corrective feedback, scoring teacher outputs by how much they improved a frozen student's likelihood of the reference solution. Established a final-answer reward signal and studied why it did not transfer to long reasoning traces.