3 papers
cs.AI2026
Training Alignment Auditors via Reinforcement Learning
Paul Rosu, Rowan Wang
Alignment auditing of frontier models increasingly relies on LLM auditors to surface undesirable behaviors at scale, but current automated auditors can struggle with coherent inves…
cs.LG2025
A PDE-Informed Latent Diffusion Model for 2-m Temperature Downscaling
Paul Rosu, Muchang Bahng, Erick Jiang +2
This work presents a physics-conditioned latent diffusion model tailored for dynamical downscaling of atmospheric data, with a focus on reconstructing high-resolution 2-m temperatu…
cs.CL2025
LITERA: An LLM Based Approach to Latin-to-English Translation
Paul Rosu
This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for…