publications

2026

1. Are Latent Reasoning Models Easily Interpretable?

   Connor Dilgren and Sarah Wiegreffe

   2026

   PDF Code

2025

1. SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories

   Chihao Shen, Connor Dilgren, Purva Chiniya, and 3 more authors

   2025

   PDF Code Website