NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Multi-perspective TinyLM with TTT and POE achieves 21.7% accuracy on the ARC-AGI-2 evaluation benchmark.
citing papers explorer
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
-
Multi-Perspective Transformers in ARC-AGI-2 Challenge
Multi-perspective TinyLM with TTT and POE achieves 21.7% accuracy on the ARC-AGI-2 evaluation benchmark.