cs.LGNov 18, 2026

Variable Length Diffuse Everything: Arbitrary Length Generative Modeling on Arbitrary State Spaces

Authors: Kevin Rojas, Felix X. -F. Ye, Molei Tao

Organizations: Georgia Institute of Technology · University at Albany, SUNY

Abstract

Diffusion and flow-based generative models have achieved remarkable results across diverse applications, but most assume data of fixed-dimension/length. Meanwhile, real-world problems such as layout generation often involve variable-length, multimodal data, such as continuous bounding box coordinates paired with discrete types. Existing methods typically address variable length by padding data to a fixed size or by introducing specialized objectives to model lengths explicitly, adding complexity and limiting generality. We propose Variable Length Diffuse Everything (VL-DE), a simple and general framework for variable-length multimodal generation on arbitrary state spaces. Instead of padding, VL-DE handles variable length through an insertion-based mechanism grounded in a principled theoretical framework, yielding a tractable training objective. In addition, by utilizing the fact that VL-DE is based on a generator with an additive form, we develop a higher-order sampler by appropriately handling the time dependence. Extensive experiments on layout and molecule generation demonstrate the effectiveness of our approach.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Variable-Length Generative Protein Design via Generalized Poisson Flow

    Jul 10, 2026Chaoran Cheng, Zhanghan Ni, Yanru Qu +4Generative ModelingFlow-Based Generative Modeling

  2. Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers

    Jun 18, 2026Dong Hoon Lee, Seunghoon HongToken MergingDiffusion-Based Image Generation