3 papers
cs.LG2025
Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data
Ege Erdogan, Ana Lucic
Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity. In particular, their activations entangle many concepts…
cs.LG2025
Geometric Flow Models over Neural Network Weights
Ege Erdogan
Deep generative models such as flow and diffusion models have proven to be effective in modeling high-dimensional and complex data types such as videos or proteins, and this has mo…
cs.LG2023
Poisoning Evasion: Symbiotic Adversarial Robustness for Graph Neural Networks
Ege Erdogan, Simon Geisler, Stephan Günnemann
It is well-known that deep learning models are vulnerable to small input perturbations. Such perturbed instances are called adversarial examples. Adversarial examples are commonly…