default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDRóbert Csordás
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c16]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
Self-organising Neural Discrete Representation Learning à la Kohonen. ICANN (1) 2024: 343-362- [c15]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber, Christopher Potts, Christopher D. Manning:
MoEUT: Mixture-of-Experts Universal Transformers. NeurIPS 2024 - [c14]Róbert Csordás, Piotr Piekos, Kazuki Irie, Jürgen Schmidhuber:
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention. NeurIPS 2024 - [i20]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber, Christopher Potts, Christopher D. Manning:
MoEUT: Mixture-of-Experts Universal Transformers. CoRR abs/2405.16039 (2024) - [i19]Róbert Csordás, Christopher Potts, Christopher D. Manning, Atticus Geiger:
Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations. CoRR abs/2408.10920 (2024) - [i18]Julie Kallini, Shikhar Murty, Christopher D. Manning, Christopher Potts, Róbert Csordás:
MrT5: Dynamic Token Merging for Efficient Byte-level Language Models. CoRR abs/2410.20771 (2024) - 2023
- [c13]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: 1889-1903 - [c12]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
Approximating Two-Layer Feedforward Networks for Efficient Transformers. EMNLP (Findings) 2023: 674-692 - [c11]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions. EMNLP 2023: 9455-9465 - [i17]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
Topological Neural Discrete Representation Learning à la Kohonen. CoRR abs/2302.07950 (2023) - [i16]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 abs/2305.16843 (2023) - [i15]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 A. 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 abs/2305.17066 (2023) - [i14]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
Approximating Two-Layer Feedforward Networks for Efficient Transformers. CoRR abs/2310.10837 (2023) - [i13]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions. CoRR abs/2310.16076 (2023) - [i12]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
Automating Continual Learning. CoRR abs/2312.00276 (2023) - [i11]Róbert Csordás, Piotr Piekos, Kazuki Irie, Jürgen Schmidhuber:
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention. CoRR abs/2312.07987 (2023) - 2022
- [c10]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations. EMNLP 2022: 9758-9767 - [c9]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization. ICLR 2022 - [c8]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: 9639-9659 - [c7]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. ICML 2022: 9660-9677 - [c6]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: 2 - [i10]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. CoRR abs/2202.05780 (2022) - [i9]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 abs/2202.05798 (2022) - [i8]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 abs/2209.11142 (2022) - [i7]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations. CoRR abs/2210.06350 (2022) - 2021
- [c5]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers. EMNLP (1) 2021: 619-634 - [c4]Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks. ICLR 2021 - [c3]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. NeurIPS 2021: 7703-7717 - [i6]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. CoRR abs/2106.06295 (2021) - [i5]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers. CoRR abs/2108.12284 (2021) - [i4]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization. CoRR abs/2110.07732 (2021) - [i3]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
Improving Baselines in the Wild. CoRR abs/2112.15550 (2021) - 2020
- [i2]Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks. CoRR abs/2010.02066 (2020)
2010 – 2019
- 2019
- [c2]Róbert Csordás, Jürgen Schmidhuber:
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control. ICLR (Poster) 2019 - [i1]Róbert Csordás, Jürgen Schmidhuber:
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control. CoRR abs/1904.10278 (2019) - 2015
- [c1]Róbert Csordás, László Havasi, Tamás Szirányi
:
Detecting Objects Thrown over Fence in Outdoor Scenes. VISAPP (3) 2015: 593-599
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-02-15 01:22 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
