Paper Detail

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang

huggingface Score 5.4

Published 2026-04-29 · First seen 2026-05-05

General AI

Abstract

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{xu2026combostoc,
  title = {ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models},
  author = {Rui Xu and Jiepeng Wang and Hao Pan and Yang Liu and Xin Tong and Shiqing Xin and Changhe Tu and Taku Komura and Wenping Wang},
  year = {2026},
  abstract = {In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance},
  url = {https://huggingface.co/papers/2405.13729},
  keywords = {diffusion generative models, combinatorial complexity, stochastic processes, ComboStoc, asynchronous time steps, structured generation tasks, high-dimensional data, code available, huggingface daily},
  eprint = {2405.13729},
  archiveprefix = {arXiv},
}

Metadata

{}