4 papers
The Importance of Phase in Neural Representations: An Internal Oppenheim-Lim Test of Image Classifiers
Alper Yıldırım
Oppenheim and Lim (1981) showed that natural images stay recognizable when reconstructed from their Fourier phase alone, while the magnitude carries little of their identity. We as…
HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting
Alper Yıldırım
Simple linear and frequency-domain models remain surprisingly competitive in long-horizon time-series forecasting, and recent mechanistic evidence suggests that standard forecastin…
Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
Alper Yıldırım
Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in NLP actually engage on time s…
The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
Alper Yıldırım
Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypotheses a priori by modifying archit…