# Extendable Planning via Multiscale Diffusion

arXiv: https://arxiv.org/abs/2503.20102 · HTML: https://mlsanity.com/paper/2503.20102/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [The pitfalls of next-token prediction](https://mlsanity.com/paper/2403.06963/) (2024)
- [AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners](https://mlsanity.com/paper/2302.01877/) (2023)
- [Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2305.18459/) (2023)
- [Deep Hierarchical Planning from Pixels](https://mlsanity.com/paper/2206.04114/) (2022)
- [Diffusion Models for Reinforcement Learning: A Survey](https://mlsanity.com/paper/2311.01223/) (2023)
- [On the role of planning in model-based deep reinforcement learning](https://mlsanity.com/paper/2011.04021/) (2020)
- [Offline Reinforcement Learning with Reverse Model-based Imagination](https://mlsanity.com/paper/2110.00188/) (2021)
- [Investigating Compounding Prediction Errors in Learned Dynamics Models](https://mlsanity.com/paper/2203.09637/) (2022)
- [DiffuserLite: Towards Real-time Diffusion Planning](https://mlsanity.com/paper/2401.15443/) (2024)
- [DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching](https://mlsanity.com/paper/2402.02439/) (2024)
- [World Models via Policy-Guided Trajectory Diffusion](https://mlsanity.com/paper/2312.08533/) (2023)
- [Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination](https://mlsanity.com/paper/2206.07989/) (2022)
- [Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning](https://mlsanity.com/paper/2310.19308/) (2023)

## Built on by (most cited first, 2 of 2)

- [Spooky Action at a Distance: Normalization Layers Enable Side-Channel Spatial Communication](https://mlsanity.com/paper/2507.04709/) (2025)
- [NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches](https://mlsanity.com/paper/2610.02339/) (2026)

## Abstract (arXiv)

Long-horizon planning is crucial in complex environments, but diffusion-based planners like Diffuser are limited by the trajectory lengths observed during training. This creates a dilemma: long trajectories are needed for effective planning, yet they degrade model performance. In this paper, we introduce this extendable long-horizon planning challenge and propose a two-phase solution. First, Progressive Trajectory Extension incrementally constructs longer trajectories through multi-round compositional stitching. Second, the Hierarchical Multiscale Diffuser enables efficient training and inference over long horizons by reasoning across temporal scales. To avoid the need for multiple separate models, we propose Adaptive Plan Pondering and the Recursive HM-Diffuser, which unify hierarchical planning within a single model. Experiments show our approach yields strong performance gains, advancing scalable and efficient decision-making over long-horizons.