SOURCE-LINKED INTELLIGENCE

Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Diffusion models generate a sample by traversing a denoising trajectory, a sequence of stochastic noise-reduction steps that transforms pure noise into a draw from a target distribution. At deployment time, additional computation can improve sample quality without retraining: at each step, the sampler draws several candidate noise samples, scores the resulting predictions with a quality criterion called the verifier, and retains the best candidate at the cost of one network evaluation per candidate. This raises a resource allocation question: given a fixed budget of function evaluations, how s

Read original source ↗ Open in workspace

recordType

paper

region

Global