activity
20242026
collaborators

7 papers

cs.AI2026

Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance

Allison Zhuang, Santiago Aranguri

Steering interventions targeting eval-awareness, a model's recognition that it is being tested, are increasingly used in safety evaluation pipelines, where evaluation-awareness is…

cs.LG2026

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

Leon Bergen, Usha Bhalla, Sidharth Baskaran +14

Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. Th…

cs.LG2026

Inference-Time Toxicity Mitigation in Protein Language Models

Manuel Fernández Burda, Santiago Aranguri, Iván Arcuschin Moreno +1

Protein language models (PLMs) are becoming practical tools for de novo protein design, yet their dual-use potential raises safety concerns. We show that domain adaptation to speci…

cs.LG2026

Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training

Frank Xiao, Santiago Aranguri

We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By computing activation-differe…

cs.LG2025

Optimizing Noise Schedules of Generative Models in High Dimensionss

Santiago Aranguri, Giulio Biroli, Marc Mezard +1

Recent works have shown that diffusion models can undergo phase transitions, the resolution of which is needed for accurately generating samples. This has motivated the use of diff…

cs.LG2024

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

Santiago Aranguri, Francesco Insulla

We analyze the training of a two-layer autoencoder used to parameterize a flow-based generative model for sampling from a high-dimensional Gaussian mixture. Previous work shows tha…