4 papers
Adapting Linear-Time Architectures for Tabular In-Context Learning
David Schnurr, Felix Sarnthein, Thomas Hofmann +1
Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large datasets. Existing linear-time…
Revisiting Knowledge Distillation: The Hidden Role of Dataset Size
Giulia Lanzillotta, Felix Sarnthein, Gil Kur +2
The concept of knowledge distillation (KD) describes the training of a student model from a teacher model and is a widely adopted technique in deep learning. However, it is still n…
Fixed-Point RNNs: Interpolating from Diagonal to Dense
Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone +1
Linear recurrent neural networks (RNNs) and state-space models (SSMs) such as Mamba have become promising alternatives to softmax-attention as sequence mixing layers in Transformer…
Random Teachers are Good Teachers
Felix Sarnthein, Gregor Bachmann, Sotiris Anagnostidis +1
In this work, we investigate the implicit regularization induced by teacher-student learning dynamics in self-distillation. To isolate its effect, we describe a simple experiment w…