Wassim (Wes) Bouaziz

Publications

Take a look at my Google Scholar for updated publications and citations. * denotes equal contributions.

Byzantine Machine Learning: MultiKrum and an optimal notion of robustness teaser
Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset teaser
On Monotonicity in AI Alignment teaser
Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning teaser
Clustering Head: A Visual Case Study of the Training Dynamics in Transformers teaser
Easing Optimization Paths: a Circuit Perspective teaser
Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification teaser
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning teaser
Iteration Head: A Mechanistic Study of Chain-of-Thought teaser
The Llama 3 Herd of Models teaser
Inverting Gradient Attacks Makes Powerful Data Poisoning teaser
On the Parameterized Complexity of Counting Small-Sized Minimum $\boldsymbol{(S, T)}$-Cuts teaser
$\texttt{pyannote.audio}$: neural building blocks for speaker diarization teaser