Long-range dependency in integer multiplication is a mirage from 1D representation; a 2D grid reduces it to local 3x3 operations, letting a 321-parameter neural cellular automaton generalize perfectly to inputs 683 times longer than training while Transformers fail.
Growing Neural Cellular Automata , volume =
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Sheaf-ADMM trains multi-agent systems by unrolling ADMM with sheaf-specified constraints, yielding improved MNIST robustness to shifts and higher Sudoku solve rates than MPNN baselines.
A 2D neural cellular automaton spontaneously self-organizes into a Proto-CKY representation that exhibits syntactic processing capabilities for context-free grammars when trained on membership problems.
Hybrid coarse-grid NCA plus implicit decoder produces arbitrary-resolution real-time outputs for morphogenesis and texture synthesis on grids and meshes while preserving self-organization.
Joint training of NCA rules and SIREN pre-patterns improves robustness, encoding capacity, and symmetry breaking compared to purely self-organizing models by offloading information to initial conditions.
A neural cellular automaton learns compositional rules from data alone to achieve structural generalization on the SLOG semantic parsing benchmark, reaching 67.3% accuracy and fully succeeding on 11 of 17 categories.
Deriving a neural cellular automaton from locality, symmetry, and stability postulates produces 100% accurate addition generalization from 16-digit to 1-million-digit inputs.
A review of Neural Cellular Automata that unifies existing approaches with a modular framework, notation, and reference code in NCAtorch.
citing papers explorer
-
On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication
Long-range dependency in integer multiplication is a mirage from 1D representation; a 2D grid reduces it to local 3x3 operations, letting a 321-parameter neural cellular automaton generalize perfectly to inputs 683 times longer than training while Transformers fail.
-
Learning Multi-Agent Coordination via Sheaf-ADMM
Sheaf-ADMM trains multi-agent systems by unrolling ADMM with sheaf-specified constraints, yielding improved MNIST robustness to shifts and higher Sudoku solve rates than MPNN baselines.
-
On the Emergence of Syntax by Means of Local Interaction
A 2D neural cellular automaton spontaneously self-organizes into a Proto-CKY representation that exhibits syntactic processing capabilities for context-free grammars when trained on membership problems.
-
Neural Cellular Automata: From Cells to Pixels
Hybrid coarse-grid NCA plus implicit decoder produces arbitrary-resolution real-time outputs for morphogenesis and texture synthesis on grids and meshes while preserving self-organization.
-
Learning Developmental Scaffoldings to Guide Self-Organisation
Joint training of NCA rules and SIREN pre-patterns improves robustness, encoding capacity, and symmetry breaking compared to purely self-organizing models by offloading information to initial conditions.
-
Structural Generalization on SLOG without Hand-Written Rules
A neural cellular automaton learns compositional rules from data alone to achieve structural generalization on the SLOG semantic parsing benchmark, reaching 67.3% accuracy and fully succeeding on 11 of 17 categories.
-
On the Spatiotemporal Dynamics of Generalization in Neural Networks
Deriving a neural cellular automaton from locality, symmetry, and stability postulates produces 100% accurate addition generalization from 16-digit to 1-million-digit inputs.
-
A New Kind of Network? Review and Reference Implementation of Neural Cellular Automata
A review of Neural Cellular Automata that unifies existing approaches with a modular framework, notation, and reference code in NCAtorch.