collaborators

8 papers

cs.LG2026

Multi-Way Representation Alignment

Akshit Achara, Tatiana Gaintseva, Mateo Mahaut +5

The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces. However, current strategies for mapping t…

cs.LG2026

Adversarial Attacks Leverage Interference Between Features in Superposition

Edward Stevinson, Lucas Prieto, Melih Barsbey +1

Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decisio…

cs.LG2026

From Data Statistics to Feature Geometry: How Correlations Shape Superposition

Lucas Prieto, Edward Stevinson, Melih Barsbey +2

A central idea in mechanistic interpretability is that neural networks represent more features than they have dimensions, arranging them in superposition to form an over-complete b…

cs.LG2025

On the Interaction of Compressibility and Adversarial Robustness

Melih Barsbey, Antônio H. Ribeiro, Umut Şimşekli +1

Modern neural networks are expected to simultaneously satisfy a host of desirable properties: accurate fitting to training data, generalization to unseen inputs, parameter and comp…

cs.LG2025

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility

Melih Barsbey, Lucas Prieto, Stefanos Zafeiriou +1

Robustness and resource-efficiency are two highly desirable properties for modern machine learning models. However, achieving them jointly remains a challenge. In this paper, we id…

cs.LG2025

Grokking at the Edge of Numerical Stability

Lucas Prieto, Melih Barsbey, Pedro A. M. Mediano +1

Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progres…