cs.AINov 11, 2026

Marginal-Preserving Coupled Diffusion Composition for Long-Horizon Planning

Authors: Hengrui Zhang, Qiyu Wang, Yuhu Cheng, Brooks Paige, Xuesong Wang

Organizations: School of Information and Control Engineering, China University of Mining and Technology · Center for Artificial Intelligence, University College London, London

Abstract

Compositional diffusion planners extend short-horizon trajectory models to long-horizon goal-conditioned planning by generating and stitching multiple local trajectory chunks. However, in multimodal environments, local plausibility is not sufficient for global consistency: independently initialized chunks may denoise toward incompatible overlap modes, producing plans that are individually feasible but incoherent after stitching. Existing remedies typically add search, guidance, pruning, or graph-based structure at inference time, increasing computational cost or relying on task-specific machinery. We instead investigate graph-structured dependence among chunk-wise initial diffusion noises as a lightweight coordination mechanism for compositional trajectory planning. We propose Marginal-Preserving Coupled Diffusion Composition (MCDC), a training-free inference method for pretrained compositional diffusion planners. Instead of sampling chunk noises independently, MCDC constructs coupled Gaussian initializations whose per-chunk marginals remain exactly standard Gaussian, as required by the pretrained denoiser, while neighboring chunks receive positively correlated noise components. This preserves the standard-Gaussian initialization marginal of each chunk while biasing adjacent chunks toward compatible overlap-mode choices. We prove exact marginal preservation and show, under a simple multimodal overlap model, that positive coupling increases the probability of compatible mode selection. On OGBench long-horizon stitch tasks, MCDC consistently improves over independent compositional diffusion sampling while retaining nearly the same inference time, and achieves a favorable success--cost trade-off compared with search-based composition methods.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Refining Compositional Diffusion for Reliable Long-Horizon Planning

    May 4, 2026Kyowoon Lee, Yunhao Luo, Anh Tong +1Trajectory GenerationDiffusion-Based Planning

  2. Compositional Diffusion Planning with Chunk Selection and Reachability Measure

    Oct 28, 2026Chanyoung Park, Youngjoong Kim, Jaesik ParkDiffusion-Based PlanningReachability Analysis