# Generative Trajectory Stitching through Diffusion Composition

arXiv: https://arxiv.org/abs/2503.05153 · HTML: https://mlsanity.com/paper/2503.05153/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 81 of its 91 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 81)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC](https://mlsanity.com/paper/2302.11552/) (2023)
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://mlsanity.com/paper/2112.10751/) (2021)
- [Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models](https://mlsanity.com/paper/2308.01557/) (2023)
- [AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners](https://mlsanity.com/paper/2302.01877/) (2023)
- [HIQL: Offline Goal-Conditioned RL with Latent States as Actions](https://mlsanity.com/paper/2307.11949/) (2023)
- [Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning](https://mlsanity.com/paper/2410.14157/) (2024)
- [Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning](https://mlsanity.com/paper/2304.01203/) (2023)
- [Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2305.18459/) (2023)
- [Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL](https://mlsanity.com/paper/2209.03993/) (2022)
- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)
- [Synthetic Experience Replay](https://mlsanity.com/paper/2303.06614/) (2023)
- [Compositional Foundation Models for Hierarchical Planning](https://mlsanity.com/paper/2309.08587/) (2023)
- [Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task](https://mlsanity.com/paper/2310.09336/) (2023)

## Built on by (most cited first, 30 of 41)

- [Reinforcement Learning for Flow-Matching Policies](https://mlsanity.com/paper/2507.15073/) (2025)
- [State-Covering Trajectory Stitching for Diffusion Planners](https://mlsanity.com/paper/2506.00895/) (2025)
- [Multi-Modal Manipulation via Multi-Modal Policy Consensus](https://mlsanity.com/paper/2509.23468/) (2025)
- [Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning](https://mlsanity.com/paper/2506.10137/) (2025)
- [CREPE: Controlling Diffusion with Replica Exchange](https://mlsanity.com/paper/2509.23265/) (2025)
- [Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning](https://mlsanity.com/paper/2506.00867/) (2025)
- [Test-Time Graph Search for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2510.07257/) (2025)
- [Hybrid Diffusion for Simultaneous Symbolic and Continuous Planning](https://mlsanity.com/paper/2509.21983/) (2025)
- [Compositional Planning with Jumpy World Models](https://mlsanity.com/paper/2602.19634/) (2026)
- [Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL](https://mlsanity.com/paper/2602.03389/) (2026)
- [Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction](https://mlsanity.com/paper/2607.19919/) (2026)
- [BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning](https://mlsanity.com/paper/2506.05762/) (2025)
- [Generative View Stitching](https://mlsanity.com/paper/2510.24718/) (2025)
- [Temporal Backtracking Search for Test-time Generative Video Reasoning](https://mlsanity.com/paper/2606.13861/) (2026)
- [Extremum Flow Matching for Offline Goal Conditioned Reinforcement Learning](https://mlsanity.com/paper/2505.19717/) (2025)
- [Factorizing Diffusion Policies for Observation Modality Prioritization](https://mlsanity.com/paper/2509.16830/) (2025)
- [Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making](https://mlsanity.com/paper/2512.08280/) (2025)
- [Compositional Monte Carlo Tree Diffusion for Extendable Planning](https://mlsanity.com/paper/2510.21361/) (2025)
- [Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigation](https://mlsanity.com/paper/2601.22965/) (2026)
- [Compositional Visual Planning via Inference-Time Diffusion Scaling](https://mlsanity.com/paper/2603.02646/) (2026)
- [Refining Compositional Diffusion for Reliable Long-Horizon Planning](https://mlsanity.com/paper/2605.03075/) (2026)
- [NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL](https://mlsanity.com/paper/2607.07855/) (2026)
- [Flexible Locomotion Learning with Diffusion Model Predictive Control](https://mlsanity.com/paper/2510.04234/) (2025)
- [ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts](https://mlsanity.com/paper/2511.23442/) (2025)
- [Action-Sufficient Goal Representations](https://mlsanity.com/paper/2601.22496/) (2026)
- [Analogical Trajectory Transfer](https://mlsanity.com/paper/2605.14393/) (2026)
- [Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2605.20609/) (2026)
- [Improving Trajectory Stitching with Flow Models](https://mlsanity.com/paper/2505.07802/) (2025)
- [What Do You Need for Compositional Generalization in Diffusion Planning?](https://mlsanity.com/paper/2505.18083/) (2025)
- [Muninn: Your Trajectory Diffusion Model But Faster](https://mlsanity.com/paper/2605.09999/) (2026)

## Abstract (arXiv)

Effective trajectory stitching for long-horizon planning is a significant challenge in robotic decision-making. While diffusion models have shown promise in planning, they are limited to solving tasks similar to those seen in their training data. We propose CompDiffuser, a novel generative approach that can solve new tasks by learning to compositionally stitch together shorter trajectory chunks from previously seen tasks. Our key insight is modeling the trajectory distribution by subdividing it into overlapping chunks and learning their conditional relationships through a single bidirectional diffusion model. This allows information to propagate between segments during generation, ensuring physically consistent connections. We conduct experiments on benchmark tasks of various difficulties, covering different environment sizes, agent state dimension, trajectory types, training data quality, and show that CompDiffuser significantly outperforms existing methods.