Santiago Aranguri

According to our database, Santiago Aranguri authored at least 6 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2026

Inference-Time Toxicity Mitigation in Protein Language Models.

Manuel Fernández Burda, Santiago Aranguri, Iván Arcuschin Moreno, Enzo Ferrante

CoRR, March, 2026

In-the-Wild Model Organisms: Mitigating Undesirable Emergent Behaviors in Production LLM Post-Training via Data Attribution.

Frank Xiao, Santiago Aranguri

CoRR, February, 2026

2025

Optimizing Noise Schedules of Generative Models in High Dimensionss.

Santiago Aranguri, Giulio Biroli, Marc Mézard, Eric Vanden-Eijnden

CoRR, January, 2025

2024

Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models.

Santiago Aranguri, Francesco Insulla

CoRR, 2024

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes.

Zhenfeng Tu, Santiago Aranguri, Arthur Jacot

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2022

Untangling Planar Graphs and Curves by Staying Positive.

Santiago Aranguri, Hsien-Chih Chang, Dylan Fridman

Proceedings of the 2022 ACM-SIAM Symposium on Discrete Algorithms, 2022