I am a PhD student at New York University working on Mechanistic Interpretability. My previous research in the PhD was on scaling laws and phase transitions of diffusion models and neural networks with Eric Vanden-Eijnden and Arthur Jacot. I obtained my B.S. in Mathematics at Stanford University, where I worked on interacting particle systems with Amir Dembo

Tied Crosscoders: new architecture for model-diffing to understand how chat model behavior arises from the base model and to measure how novel chat features are when compared to base features.

Optimizing Noise Schedules of Generative Models in High Dimensions
S. Aranguri, G. Biroli, M. Mezard, E. Vanden-Eijnden
Under review

Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models
S. Aranguri, F. Insulla
ICLR 2025 Deep Generative Model in Machine Learning Workshop and Frontiers in Probabilistic Inference Workshop

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
Z. Tu, S. Aranguri, A. Jacot
NeurIPS 2024

Untangling planar graphs and curves by staying positive
S. Aranguri, H. Chang, D. Fridman
ACM-SIAM Symposium on Discrete Algorithms 2022