Nolan Smyth

Co-supervisor

Sujets de recherche

Apprentissage automatique appliqué

Astrophysique

Sécurité de l'IA

Publications

Efficient Safety Alignment of Language Models via Latent Personality Traits

Mohamed Amine Merzouk

Damiano Fornasiere

Linh Le

David Williams-King

Adam Oberman

Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternat… (voir plus)ives. Latent Adversarial Training (LAT) is among the most effective defenses, but can degrade utility and requires training on large datasets of harmful prompts. We introduce Latent Personality Alignment (LPA), which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature. We hypothesize that personality-anchored representations share latent structure with harm avoidance, so adversarially stabilizing them implicitly constrains the subspace exploited by jailbreak attacks. LPA achieves near-zero attack success rates on HarmBench across direct requests and five jailbreak methods, despite never seeing harmful content during training and no loss of performance on standard benchmarks. Moreover, the training process is lightweight; the entire procedure completes in minutes on a single GPU and uses 75x fewer examples than standard LAT. Extensive ablations demonstrate the robustness, efficiency, and generalization of our method.

2026-07-07

Conference on Language Modeling (accepté)

doi.org

openreview.net

Microlensing Detection and Inference via Learned Bayes Factors

We present a unified framework for gravitational microlensing event detection and parameter inference. Traditional pipelines use determinist… (voir plus)ic hard cuts on photometric statistics, systematically missing low-magnification events in the finite-source regime. We instead frame detection as Bayesian model comparison using Evidence Networks, which learn calibrated Bayes factors from binary-labeled simulations, and combine this with Neural Posterior Estimation (NPE) for amortized parameter inference. Both share a transformer encoder that handles irregularly-sampled time series without imputation. On simulated Roman Space Telescope data, our Evidence Network achieves

2026-05-29

AI4Physics @ International Conference on Machine Learning (publié)

openreview.net

Transformer Embeddings for Fast Microlensing Inference

2025-12-11

ArXiv (prépublication)

arxiv.org

Neural Deprojection of Galaxy Stellar Mass Profiles

M. J. Yantovski-Barth

Hengyue Zhang

Connor Stone

Martin Bureau