Róbert Csordás
16 papers · 2019–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (35) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(10)
🧬
Topic Evolution
🌈
Renaissance Researcher
(5)
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(75)
Venues
Top co-authors
Research topics
Machine Learning
(13)
Deep Learning
(11)
Architectures
(10)
Artificial Intelligence
(7)
Core AI
(7)
Core Methods
(7)
Optimization & Theory · Machine Learning
(7)
Natural Language Processing
(3)
Reinforcement Learning
(2)
Application Areas
(2)
Applications
(2)
Learning Paradigms
(2)
Learning Types
(2)
Optimization & Theory · Deep Learning
(2)
Interdisciplinary
(1)
Keywords
attention mechanism
(4)
recurrent neural network
(3)
neural network
(3)
mixture of expert
(3)
systematic generalization
(3)
language modeling
(2)
universal transformer
(2)
linear transformer
(2)
language model
(2)
few-shot learning
(1)
question answering
(1)
continual learning
(1)
model architecture
(1)
natural language understanding
(1)
transformer architecture
(1)
in-context learning
(1)
parameter sharing
(1)
knowledge distillation
(1)
reinforcement learning
(1)
gradient descent
(1)
Papers
Measuring In-Context Computation Complexity via Hidden State Prediction
ICML 2025
MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
ICLR 2025
MoEUT: Mixture-of-Experts Universal Transformers
NeurIPS 2024
Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
EMNLP 2024
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
NeurIPS 2024
Approximating Two-Layer Feedforward Networks for Efficient Transformers
EMNLP 2023
Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions
EMNLP 2023
Randomized Positional Encodings Boost Length Generalization of Transformers
ACL 2023
A Modern Self-Referential Weight Matrix That Learns to Modify Itself
ICML 2022
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations
EMNLP 2022
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention
ICML 2022
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization
ICLR 2022
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
ICLR 2021
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
NeurIPS 2021
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers
EMNLP 2021
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
ICLR 2019