NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
Lake, and Todd M
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Humans exhibit abstraction learning consistent with prospective compression of future tasks in non-stationary domains, unlike retrospective compression algorithms or LLM-based approaches.
ARC-AGI-2 adds a larger, more complex set of tasks to the original ARC-AGI benchmark to give finer-grained measurement of fluid intelligence in AI.
citing papers explorer
-
Prospective Compression in Human Abstraction Learning
Humans exhibit abstraction learning consistent with prospective compression of future tasks in non-stationary domains, unlike retrospective compression algorithms or LLM-based approaches.
-
ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
ARC-AGI-2 adds a larger, more complex set of tasks to the original ARC-AGI benchmark to give finer-grained measurement of fluid intelligence in AI.