A factorized modular diffusion policy improves fitting of multimodal robot actions and enables flexible task adaptation without catastrophic forgetting.
Hierarchical text-conditional image generation with clip latents, 2022
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Diffusion models via DDPM work for anomaly detection but are slow; the proposed DTE method estimates diffusion time distribution analytically and with a neural net to deliver faster inference while outperforming DDPM on ADBench for unsupervised and semi-supervised settings.
Semantic embeddings extract behavior atoms from microtubule swarm simulations that match expected patterns from DNA control parameters.
citing papers explorer
-
Flexible Multitask Learning with Factorized Diffusion Policy
A factorized modular diffusion policy improves fitting of multimodal robot actions and enables flexible task adaptation without catastrophic forgetting.
-
On Diffusion Modeling for Anomaly Detection
Diffusion models via DDPM work for anomaly detection but are slow; the proposed DTE method estimates diffusion time distribution analytically and with a neural net to deliver faster inference while outperforming DDPM on ADBench for unsupervised and semi-supervised settings.
-
Semantic analysis of behavior in a DNA-functionalized molecular swarm
Semantic embeddings extract behavior atoms from microtubule swarm simulations that match expected patterns from DNA control parameters.