Diffusion models can extract reusable density-mode concepts from their time-indexed scores to enable compositional generation at test time on held-out benchmarks from ColorMNIST and CelebA.
Lake, Tomer D
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CB-RNNs with a cerebellar feedforward module learn temporal tasks faster than matched RNNs, with the module driving efficiency even after freezing the recurrent core as a fixed reservoir.
citing papers explorer
-
Test-Time Compositional Generalization in Diffusion Models via Concept Discovery
Diffusion models can extract reusable density-mode concepts from their time-indexed scores to enable compositional generation at test time on held-out benchmarks from ColorMNIST and CelebA.
-
Cortico-cerebellar modularity as an architectural inductive bias for efficient temporal learning
CB-RNNs with a cerebellar feedforward module learn temporal tasks faster than matched RNNs, with the module driving efficiency even after freezing the recurrent core as a fixed reservoir.