Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition

• URL: http://arxiv.org/abs/2503.12466v1
• Date: Sun, 16 Mar 2025 11:40:10 GMT
• Title: Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
• Authors: Jiahang Cao, Qiang Zhang, Hanzhong Guo, Jiaxu Wang, Hao Cheng, Renjing Xu,
• Abstract summary: Diffusion Policy (DP) has attracted significant attention as an effective method for policy representation.<n>We propose a novel policy composition method: by leveraging multiple pre-trained DPs based on individual visual modalities.<n>We demonstrate the potential of MCDP to improve both adaptability and performance.
• Score: 10.777232453153568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Policy (DP) has attracted significant attention as an effective method for policy representation due to its capacity to model multi-distribution dynamics. However, current DPs are often based on a single visual modality (e.g., RGB or point cloud), limiting their accuracy and generalization potential. Although training a generalized DP capable of handling heterogeneous multimodal data would enhance performance, it entails substantial computational and data-related costs. To address these challenges, we propose a novel policy composition method: by leveraging multiple pre-trained DPs based on individual visual modalities, we can combine their distributional scores to form a more expressive Modality-Composable Diffusion Policy (MCDP), without the need for additional training. Through extensive empirical experiments on the RoboTwin dataset, we demonstrate the potential of MCDP to improve both adaptability and performance. This exploration aims to provide valuable insights into the flexible composition of existing DPs, facilitating the development of generalizable cross-modality, cross-domain, and even cross-embodiment policies. Our code is open-sourced at https://github.com/AndyCao1125/MCDP.

Related papers

• Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations [19.77729438305312]
  Contractive Diffusion Policies (CDPs) induce contractive behavior in the diffusion sampling dynamics.<n>CDPs often outperform baseline policies, with pronounced benefits under data scarcity.
  arXiv  Detail & Related papers  (2026-01-02T23:33:59Z)
• Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP [57.28979643999352]
  We propose a framework that enables unified solvers to perceive the shared-component nature across VRP variants.<n>We introduce a State-Decomposable MDP (SDMDP) that reformulates VRPs by expressing the state space as the Cartesian product of basis state spaces.<n>A Latent Space-based SDMDP extension is developed by incorporating both the optimal basis policies and a learnable mixture function.
  arXiv  Detail & Related papers  (2025-10-24T13:31:31Z)
• Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process [55.91649771370862]
  Dirichlet process (DP) mixture model is a powerful non-parametric method that can amplify the most prominent features.<n>We propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment.
  arXiv  Detail & Related papers  (2025-10-23T16:53:24Z)
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition [52.232968183793986]
  General Policy Composition (GPC) is a training-free method that enhances performance by combining the distributional scores of multiple pre-trained policies.<n>GPC consistently improves performance and adaptability across a diverse set of tasks.
  arXiv  Detail & Related papers  (2025-10-01T16:05:53Z)
• Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning [0.0]
  We propose a generative policy trained with an augmented flow-matching objective to predict direct completion vectors from intermediate flow samples.<n>Our method scales effectively to offline, offline-to-online, and online RL settings, offering substantial gains in speed and adaptability.<n>We extend SSCP to goal-conditioned RL, enabling flat policies to exploit subgoal structures without explicit hierarchical inference.
  arXiv  Detail & Related papers  (2025-06-26T16:09:53Z)
• IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation [3.7584322469996896]
  IMLE Policy is a novel behaviour cloning approach based on Implicit Maximum Likelihood Estimation (IMLE)<n>It excels in low-data regimes, effectively learning from minimal demonstrations and requiring 38% less data on average to match the performance of baseline methods in learning complex multi-modal behaviours.<n>We validate our approach across diverse manipulation tasks in simulated and real-world environments, showcasing its ability to capture complex behaviours under data constraints.
  arXiv  Detail & Related papers  (2025-02-17T23:22:49Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient [26.675822002049372]
  Deep Diffusion Policy Gradient (DDiffPG) is a novel actor-critic algorithm that learns from scratch multimodal policies. DDiffPG forms a multimodal training batch and utilizes mode-specific Q-learning to mitigate the inherent greediness of the RL objective. Our approach further allows the policy to be conditioned on mode-specific embeddings to explicitly control the learned modes.
  arXiv  Detail & Related papers  (2024-06-02T09:32:28Z)
• MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild [81.32127423981426]
  Multimodal emotion recognition based on audio and video data is important for real-world applications. Recent methods have focused on exploiting advances of self-supervised learning (SSL) for pre-training of strong multimodal encoders. We propose a different perspective on the problem and investigate the advancement of multimodal DFER performance by adapting SSL-pre-trained disjoint unimodal encoders.
  arXiv  Detail & Related papers  (2024-04-13T13:39:26Z)
• Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks [92.32670915472099]
  We propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs) We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
  arXiv  Detail & Related papers  (2023-10-03T17:37:52Z)
• Policy Representation via Diffusion Probability Model for Reinforcement Learning [67.56363353547775]
  We build a theoretical foundation of policy representation via the diffusion probability model. We present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. We propose the DIPO which is an implementation for model-free online RL with DIffusion POlicy.
  arXiv  Detail & Related papers  (2023-05-22T15:23:41Z)
• Deep Multimodal Fusion for Generalizable Person Re-identification [15.250738959921872]
  DMF is a Deep Multimodal Fusion network for the general scenarios on person re-identification task. Rich semantic knowledge is introduced to assist in feature representation learning during the pre-training stage. A realistic dataset is adopted to fine-tine the pre-trained model for distribution alignment with real-world.
  arXiv  Detail & Related papers  (2022-11-02T07:42:48Z)
• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [70.20191211010847]
  Offline reinforcement learning (RL) aims to learn an optimal policy using a previously collected static dataset. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. We show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.
  arXiv  Detail & Related papers  (2022-08-12T09:54:11Z)
• Latent-Variable Advantage-Weighted Policy Optimization for Offline RL [70.01851346635637]
  offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios. We propose to leverage latent-variable policies that can represent a broader class of policy distributions. Our method improves the average performance of the next best-performing offline reinforcement learning methods by 49% on heterogeneous datasets.
  arXiv  Detail & Related papers  (2022-03-16T21:17:03Z)
• DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs [33.07594285100664]
  We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience.<n>Our main contribution is to introduce the Deep Averagers with Costs MDP (DAC-MDP) and to investigate its solutions for offline RL.
  arXiv  Detail & Related papers  (2020-10-18T00:11:45Z)

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.