Róbert Csordás

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 30

Top Topics

Natural Language

Training Patterns

Top Venues

Publications

Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber, Christopher Potts, Christopher D. Manning
MoEUT: Mixture-of-Experts Universal Transformers. CoRR (2024)
Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber
Topological Neural Discrete Representation Learning à la Kohonen. CoRR (2023)
Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness
Randomized Positional Encodings Boost Length Generalization of Transformers. CoRR (2023)
Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber
Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions. EMNLP (2023)
Róbert Csordás, Piotr Piekos, Kazuki Irie, Jürgen Schmidhuber
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention. CoRR (2023)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
Approximating Two-Layer Feedforward Networks for Efficient Transformers. CoRR (2023)
Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber
Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions. CoRR (2023)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
Approximating Two-Layer Feedforward Networks for Efficient Transformers. EMNLP (Findings) (2023)
Mingchen Zhuge, Haozhe Liu, Francesco Faccio, Dylan R. Ashley, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, Kazuki Irie, Louis Kirsch, Bing Li, Guohao Li, Shuming Liu, Jinjie Mai, Piotr Piekos, Aditya Ramesh, Imanol Schlag, Weimin Shi, Aleksandar Stanic, Wenyi Wang, Yuhui Wang, Mengmeng Xu, Deng-Ping Fan, Bernard Ghanem, Jürgen Schmidhuber
Mindstorms in Natural Language-Based Societies of Mind. CoRR (2023)
Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber
Automating Continual Learning. CoRR (2023)
Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness
Randomized Positional Encodings Boost Length Generalization of Transformers. ACL (2) (2023)
Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention. CoRR (2022)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations. EMNLP (2022)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations. CoRR (2022)
Borja Ibarz, Vitaly Kurin, George Papamakarios, Kyriacos Nikiforou, Mehdi Bennani, Róbert Csordás, Andrew Joseph Dudzik, Matko Bosnjak, Alex Vitvitskyi, Yulia Rubanova, Andreea Deac, Beatrice Bevilacqua, Yaroslav Ganin, Charles Blundell, Petar Velickovic
A Generalist Neural Algorithmic Learner. LoG (2022)
Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention. ICML (2022)
Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. ICML (2022)
Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. CoRR (2022)
Borja Ibarz, Vitaly Kurin, George Papamakarios, Kyriacos Nikiforou, Mehdi Bennani, Róbert Csordás, Andrew Dudzik, Matko Bosnjak, Alex Vitvitskyi, Yulia Rubanova, Andreea Deac, Beatrice Bevilacqua, Yaroslav Ganin, Charles Blundell, Petar Velickovic
A Generalist Neural Algorithmic Learner. CoRR (2022)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization. ICLR (2022)
Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks. ICLR (2021)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization. CoRR (2021)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers. EMNLP (1) (2021)
Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber
Improving Baselines in the Wild. CoRR (2021)
Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. CoRR (2021)
Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. NeurIPS (2021)
Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers. CoRR (2021)
Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks. CoRR (2020)
Róbert Csordás, Jürgen Schmidhuber
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control. CoRR (2019)
Róbert Csordás, Jürgen Schmidhuber
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control. ICLR (Poster) (2019)
Róbert Csordás, László Havasi, Tamás Szirányi
Detecting Objects Thrown over Fence in Outdoor Scenes. VISAPP (3) (2015)