Erkan Turan

Far from merely clustering tokens, full Transformers act as pattern-forming dynamical systems that natively amplify traveling and rotating waves—an inductive bias that can be engineered at initialization to accelerate training.

Generative drifting's empirical success is no longer a mystery: it's secretly score matching, but with frequency-dependent convergence bottlenecks that explain the preference for Laplacian kernels.

Ditching ReLU can provably prevent oversmoothing in deep GNNs by inducing bifurcations that create stable, heterogeneous node representations.