Csordás, Róbert
- A Modern Self-Referential Weight Matrix That Learns to Modify Itself
2022/02/11 by Kazuki Irie, Irie, Kazuki, Imanol Schlag +5 · 2 voices · 10 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Machine Learning and ELM #Neural Networks and Applications #cs.LG
- Mindstorms in Natural Language-Based Societies of Mind
2023/05/26 by Mingchen Zhuge, Zhuge, Mingchen, Haozhe Liu +49 · 5 voices · 9 citations
Computer Science · Social Sciences · #Language and cultural evolution #Multimodal Machine Learning Applications #Topic Modeling #cs.AI #cs.CL #cs.CV #cs.LG #cs.MA
- A Generalist Neural Algorithmic Learner
2022/09/22 by Borja Ibarz, Ibarz, Borja, Vitaly Kurin +27 · 2 voices · 4 citations
Computer Science · #Machine Learning and Algorithms #Advanced Graph Neural Networks #Advanced Neural Network Applications
- Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
2021/06/11 by Kazuki Irie, Irie, Kazuki, Imanol Schlag +5 · 8 citations
Computer Science · #Artificial Intelligence in Games #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics
- MoEUT: Mixture-of-Experts Universal Transformers
2024/05/25 by Róbert Csordás, Csordás, Róbert, Kazuki Irie +7 · 13 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Semantic Web and Ontologies
- Randomized Positional Encodings Boost Length Generalization of Transformers
2023/05/26 by Anian Ruoss, Ruoss, Anian, Grégoire Delétang +13 · 9 citations
Computer Science · #Multimodal Machine Learning Applications #Topic Modeling #Natural Language Processing Techniques
- Are Neural Nets Modular? Inspecting Functional Modularity Through\n Differentiable Weight Masks
2020/10/05 by Róbert Csordás, Csordás, Róbert, Sjoerd van Steenkiste +3 · 6 citations
Computer Science · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Topic Modeling
- Do Language Models Use Their Depth Efficiently?
2025/05/20 by Róbert Csordás, Csordás, Róbert, Christopher D. Manning +3 · 13 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Topic Modeling
- Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space
2025/09/30 by Houjun Liu, Shikhar Murty, Liu, Houjun +5 · 2 voices · 2 citations
Computer Science · Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Educational Games and Gamification #Educational Tools and Methods #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
- SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
2023/12/13 by Róbert Csordás, Csordás, Róbert, Piotr Piękos +5 · 5 citations
Engineering · Computer Science · #Ferroelectric and Negative Capacitance Devices #Parallel Computing and Optimization Techniques #Topic Modeling
- The Devil is in the Detail: Simple Tricks Improve Systematic\n Generalization of Transformers
2021/08/26 by Róbert Csordás, Kazuki Irie, Csordás, Róbert +3 · 4 citations
Computer Science · Physics and Astronomy · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Topic Modeling
- Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
2024/08/20 by Róbert Csordás, Csordás, Róbert, Christopher Potts +5 · 7 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction #Machine Learning (cs.LG) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)
- MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
2024/10/28 by Kallini, Julie, Murty, Shikhar, Manning, Christopher D. +2 · 6 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization
2021/10/14 by Csordás, Róbert, Irie, Kazuki, Schmidhuber, Jürgen · 2 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
- Metalearning Continual Learning Algorithms
2023/12/01 by Kazuki Irie, Irie, Kazuki, Róbert Csordás +3 · 1 voice
#cs.LG
- Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions
2023/10/24 by Kazuki Irie, Irie, Kazuki, Róbert Csordás +3 · 2 citations
Computer Science · Engineering · #Advanced Neural Network Applications #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning (cs.LG) #Neural Networks and Applications
- Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing
2025/05/01 by Piotr Piękos, Piękos, Piotr, Róbert Csordás +3 · 4 citations
Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Topic Modeling
- Approximating Two-Layer Feedforward Networks for Efficient Transformers
2023/10/16 by Csordás, Róbert, Irie, Kazuki, Schmidhuber, Jürgen · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
- Measuring In-Context Computation Complexity via Hidden State Prediction
2025/03/17 by Vincent Herrmann, Herrmann, Vincent, Róbert Csordás +3 · 2 voices · 2 citations
#cs.LG