42 citations · 94 across the 13 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
Gerasimos Chatzoudis, Zhuowei Li, Gemma E. Moran +2
Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. W…
stat.ML2025
Towards Interpretable Deep Generative Models via Causal Representation Learning
Gemma E. Moran, Bryon Aragam
Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art perform…