Pith. sign in

REVIEW 3 cited by

A Geometric Perspective on Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.19947 v3 pith:4BCGX2BR submitted 2023-05-31 cs.CV cs.LGstat.ML

classification cs.CVcs.LGstat.ML
keywords samplingtrajectorydiffusionmodelsdatadenoisingdifferentialdistribution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochastic differential equations (SDEs) and their marginal-preserving ordinary differential equations (ODEs) to describe data perturbation and generative modeling in a unified framework. In this paper, we carefully inspect the ODE-based sampling of a popular variance-exploding SDE and reveal several intriguing structures of its sampling dynamics. We discover that the data distribution and the noise distribution are smoothly connected with a quasi-linear sampling trajectory and another implicit denoising trajectory that even converges faster. Meanwhile, the denoising trajectory governs the curvature of the corresponding sampling trajectory and its finite differences yield various second-order samplers used in practice. Furthermore, we establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm, with which we can characterize the asymptotic behavior of diffusion models and identify the empirical score deviation. Code is available at \url{https://github.com/zju-pi/diff-sampler}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Affine probability paths make the clean endpoint algebraically recoverable from any intermediate state and velocity, so early-exit decoding yields training-free 20–70% NFE savings at near-matched quality.

  2. x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Truncated Jump Sampling stops the ODE early and outputs the algebraically decoded x0 estimate, reducing NFEs by 20-70% across six model families with no retraining.

  3. x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A pretrained diffusion or flow-matching model's endpoint estimate E[x0|xt], decoded from an intermediate state and velocity, is already good enough that truncating the ODE early saves 20-70% of NFEs with near-matched quality.

Pith tools