Projects & Publications

A showcase of my technical projects and academic publications.

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

Zeng, et al.

Arxiv '25 • February 2025

Used synthetic data to improve PRMs and scale test-time compute on new domains.

Read Paper

Multi-Bin Batching for Increasing LLM Inference Throughput

Guldogan, et al.

Arxiv '24 • November 2024

Outlines a new approach based on queuing theory to increase throughput of LLM systems.

Read Paper

Computers are learning to do math, but can they learn to think along the way?

Jackson Kunde

Journal of Undergraduate Science & Technology • March 2023

Opinion article which details computer-assisted proofs from early computers to current language models.

Read Paper
RLHF Project Image

Reinforcement Learning from Human Feedback Implementation

November 2024

Here, I implement RLHF using my own transformer implementation and a simple policy gradient algorithm.

View Project
Language Transformer Image

Language Transformer Implementation

November 2024

Here, I implement a decoder-only language model using Pytorch, and I build a trainer to train the model on a shakespeare dataset.

View Project
PPO Project Image

Proximal Policy Optimization Implementation

February 2024

Here, I implement PPO and show it working for breakout and cartpole.

View Project
AI Risks Demo Image

Demonstrated Risks of AI Agents on Emergency Services

2025

Led a team that demonstrated how AI models could be exploited to automate coordinated phone calls, either to falsely report emergencies or to advocate for specific policies to congressional offices.

View Project