NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
Najoung Kim and Tal Linzen
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A transformer trained on random meaningless MicroPy programs generalizes to execute diverse human-written programs, providing empirical evidence it can act as a universal computer.
R-EMID metric with upper bound shows user shifts pose highest risk to role-playing model generalization, with co-evolving RL as most effective mitigation.
Observational causal-inspired analysis finds prompt optimization failures arise from systematic interactions between edit families and task characteristics rather than random artifacts.
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.
LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.
DiRL extracts a reasoning-memorization direction from model representations inside GRPO to weight gradients and shape rewards so that exploration favors reasoning trajectories over memorization ones.
citing papers explorer
-
Training Transformers as a Universal Computer
A transformer trained on random meaningless MicroPy programs generalizes to execute diverse human-written programs, providing empirical evidence it can act as a universal computer.