ARC-NCA shows that per-task test-time training of Neural Cellular Automata can solve about 13 percent of a 262-task ARC-AGI subset, but the claimed parity with ChatGPT 4.5 relies on results from different benchmark splits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
ARC-NCA shows that per-task test-time training of Neural Cellular Automata can solve about 13 percent of a 262-task ARC-AGI subset, but the claimed parity with ChatGPT 4.5 relies on results from different benchmark splits.