Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning

• URL: http://arxiv.org/abs/2606.00837v1
• Date: Sat, 30 May 2026 18:26:53 GMT
• Title: Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
• Abstract summary: Existing methods improve global coherence by repeatedly propagating local consistency signals.<n>We propose Coarse-to-Fine Compositional Diffusion (CoFi), an inference-time sampler that separates global structure formation from local detail refinement.<n>CoFi not only improves both global coherence and local sample quality over prior compositional baselines, but also requires 2-8x fewer denoiser evaluations.
• Score: 37.38989133673186
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models provide strong priors for generating structured data, but many tasks require outputs beyond the scale on which these models are typically trained. Compositional generation addresses this by composing overlapping local plans from a pretrained short-horizon prior into a long-horizon output. However, standard composition primarily enforces agreement between neighboring local plans, yielding local consistency without directly specifying the global structure of the full composition. As a result, locally compatible plans may still form an implausible route, task sequence, or temporal evolution. Existing methods improve global coherence by repeatedly propagating local consistency signals or by adding inference-time optimization, but these procedures become expensive as the number or dimensionality of local plans increases. We propose Coarse-to-Fine Compositional Diffusion (CoFi), an inference-time sampler that separates global structure formation from local detail refinement. CoFi first aligns local denoised estimates around a shared coarse structure, producing a global scaffold that captures the long-range task-level arrangement. It then diffuses this scaffold to an intermediate noise level and denoises it with the same pretrained local prior, restoring local fine structure while preserving the scaffold-induced global coherence. Across long-horizon robotic planning, panoramic image generation, and long video generation, CoFi not only improves both global coherence and local sample quality over prior compositional baselines, but also requires 2-8x fewer denoiser evaluations.

Related papers

• Refining Compositional Diffusion for Reliable Long-Horizon Planning [31.40044829548484]
  We propose a training-free guidance method that steers compositional sampling toward high-density, globally coherent plans.<n> Experiments on challenging long-horizon tasks from OGBench, including locomotion, object manipulation, and pixel-based observations, demonstrate that RCD consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2026-05-04T18:44:19Z)
• TowerDataset: A Heterogeneous Benchmark for Transmission Corridor Segmentation with a Global-Local Fusion Framework [46.45117150541737]
  We introduce TowerDataset, a heterogeneous benchmark for transmission-corridor segmentation.<n>It preserves long corridor extents, defines a fine-grained 22-class taxonomy, and provides standardized splits and evaluation protocols.<n>In addition, we present a global-local fusion framework which preserves and fuses whole-scene and local-detail information.
  arXiv  Detail & Related papers  (2026-04-18T05:40:57Z)
• Efficiency Follows Global-Local Decoupling [62.05489838893081]
  We introduce ConvNeur, a two-branch architecture in which a lightweight neural memory branch aggregates global context on a compact set of tokens.<n>A learned gate lets global cues modulate local features without entangling their objectives.<n>On standard classification, detection, and segmentation benchmarks, ConvNeur matches or surpasses comparable alternatives at similar or lower compute.
  arXiv  Detail & Related papers  (2026-03-20T02:20:16Z)
• Compositional Visual Planning via Inference-Time Diffusion Scaling [41.86377754505579]
  Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data.<n>We propose that the key to stable compositional generation lies in enforcing boundary agreement on the estimated clean data.<n>Our method formulates long-horizon planning as inference over a chain-structured factor graph of overlapping video chunks, where pretrained short-horizon video diffusion models provide local priors.
  arXiv  Detail & Related papers  (2026-03-03T06:24:06Z)
• Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation [96.88162755522342]
  Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI.<n>We introduce DACo, a planning-grounding decoupled architecture that disentangles global deliberation from local grounding.<n>By disentangling global reasoning from local action, DACo alleviates cognitive overload and improves long-horizon stability.
  arXiv  Detail & Related papers  (2026-02-21T19:19:55Z)
• Compositional Diffusion with Guided Search for Long-Horizon Planning [25.850015543620128]
  We propose Compositional Diffusion with Guided Search (CDGS) for compositional generative models.<n>Our method explores diverse combinations of local modes through population-based sampling, prunes infeasible candidates using likelihood-based filtering, and enforces global consistency through iterative resampling.<n>The approach generalizes across domains, enabling coherent text-guided panoramic images and long videos through effective local-to-global message passing.
  arXiv  Detail & Related papers  (2025-12-31T22:03:19Z)
• FedAgg: Adaptive Federated Learning with Aggregated Gradients [1.5653612447564105]
  We propose an adaptive FEDerated learning algorithm called FedAgg to alleviate the divergence between the local and average model parameters and obtain a fast model convergence rate. We show that our framework is superior to existing state-of-the-art FL strategies for enhancing model performance and accelerating convergence rate under IID and Non-IID datasets.
  arXiv  Detail & Related papers  (2023-03-28T08:07:28Z)
• Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation [53.04781510348416]
  Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness. We propose to structurally decouple the modeling of long-term and short-term correlations in an end-to-end framework, Global-to-Local Transformer (GLoT) Our GLoT surpasses previous state-of-the-art methods with the lowest model parameters on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M.
  arXiv  Detail & Related papers  (2023-03-26T14:57:49Z)
• Global Aggregation then Local Distribution for Scene Parsing [99.1095068574454]
  We show that our approach can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks. Our approach allows us to build new state of the art on major semantic segmentation benchmarks including Cityscapes, ADE20K, Pascal Context, Camvid and COCO-stuff.
  arXiv  Detail & Related papers  (2021-07-28T03:46:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.