Assur modules improve limited-data learning of planar mechanisms
Assur-derived features give a geometric-mean 1.8× sample-efficiency gain over flattened adjacency and position inputs.
Stories per day · 30 days
Relatedbenchmarks1generalization1interpretability1mechanism-design1mechanistic-interpretability1planar-mechanisms1planning1representation-learning1sae1sample-efficiency1sparse-autoencoders1steering1world-models1
3 stories, newest first · one card per story
Stories tagged #compositionality
AnyGoal tests whether world models generalize past expert rollouts
The benchmark recombines in-support states and actions that expert trajectories rarely pair, and current models fail those cases.
Behavioral Compositionality of Sparse Autoencoder Representations
SAE features are more compositional than random bases, but faithful explanations still need pairwise interactions.