ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted schedules are standard choices, but they rely on fixed prescriptions and can therefore be suboptimal. To address this limitation, we propose Adaptive Reparameterized Time (ART), a continuous-time control formulation that learns a time change by treating the speed of the sampling clock as the control, so that a uniform grid on the learned clock induces adaptive timesteps in the original diffusion time. Based on a leading-order Euler err
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%Understand diffusion in 20 minutes →
- PossiblePossibly related (embedding) · 45%rllm-org/rllm →
- LinkedLinked via arxiv author · 85%Yilie Huang →
“ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning”
- LinkedLinked via arxiv author · 85%Wenpin Tang →
“ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning”
- LinkedLinked via arxiv author · 85%Xun Yu Zhou →
“ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning”