activity
20202025
most citedGoing Beyond Linear Transformers with Recurrent Fast Weight Programmers

13 citations · 13 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2025

Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing

Piotr Piękos, Róbert Csordás, Jürgen Schmidhuber

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still…

cs.LG2025

Measuring In-Context Computation Complexity via Hidden State Prediction

Vincent Herrmann, Róbert Csordás, Jürgen Schmidhuber

Detecting when a neural sequence model does "interesting" computation is an open problem. The next token prediction loss is a poor indicator: Low loss can stem from trivially predi…

cs.LG2024

MoEUT: Mixture-of-Experts Universal Transformers

Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber +2

Previous work on Universal Transformers (UTs) has demonstrated the importance of parameter sharing across layers. By allowing recurrence in depth, UTs have advantages over standard…

cs.LG2023

Approximating Two-Layer Feedforward Networks for Efficient Transformers

Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-ef…

cs.LG2022

CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations

Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

Well-designed diagnostic tasks have played a key role in studying the failure of neural nets (NNs) to generalize systematically. Famous examples include SCAN and Compositional Tabl…

cs.LG202113 cited

Going Beyond Linear Transformers with Recurrent Fast Weight Programmers

Kazuki Irie, Imanol Schlag, Róbert Csordás +1

Transformers with linearised attention (''linear Transformers'') have demonstrated the practical scalability and effectiveness of outer product-based Fast Weight Programmers (FWPs)…