Primary-Fine Decoupling for Action Generation in Robotic Imitation

• URL: http://arxiv.org/abs/2602.21684v1
• Date: Wed, 25 Feb 2026 08:36:45 GMT
• Title: Primary-Fine Decoupling for Action Generation in Robotic Imitation
• Abstract summary: Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning.<n>We propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations.<n>PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks.
• Score: 91.2899765310853
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning. To this end, existing approaches often model the action space as either a discrete set of tokens or a continuous, latent-variable distribution. However, both approaches present trade-offs: some methods discretize actions into tokens and therefore lose fine-grained action variations, while others generate continuous actions in a single stage tend to produce unstable mode transitions. To address these limitations, we propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations. First, we compress action chunks into a small set of discrete modes, enabling a lightweight policy to select consistent coarse modes and avoid mode bouncing. Second, a mode conditioned MeanFlow policy is learned to generate high-fidelity continuous actions. Theoretically, we prove PF-DAG's two-stage design achieves a strictly lower MSE bound than single-stage generative policies. Empirically, PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks. It further generalizes to real-world tactile dexterous manipulation tasks. Our work demonstrates that explicit mode-level decoupling enables both robust multi-modal modeling and reactive closed-loop control for robotic manipulation.

Related papers

• Beyond Noise Steering: Dual-Latent Space Reinforcement Learning for Generative Robot Policy [13.530890681678619]
  Pretrained generative robot policies learn expressive action prior to demonstrations.<n>Existing reinforcement learning methods only steer the noisy space but fail to modulate intermediate action representations during the generation process.<n>We propose a novel Dual-Latent Space Reinforcement Learning framework, which complements initial-noise steering with representation-level control inside the frozen generator.
  arXiv  Detail & Related papers  (2026-09-10T09:04:04Z)
• Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring [77.17706435067372]
  Large Policy (LDiP) is a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates.<n>Rather than perturbing actions, LDiP improves expressivity through iterative scoring.<n>Across end-to-end planning, closed-loop driving, robotic manipulation, and vision-language-action settings, LDiP consistently outperforms strong discrete and continuous baselines.
  arXiv  Detail & Related papers  (2026-09-07T05:12:52Z)
• High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching [3.5570904967011505]
  Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions.<n>Existing one-step acceleration methods compress the whole generation process into a single large update, leading to spatial deviation, frequency distortion, and mode averaging.<n>This paper proposes a high-fidelity one-step generative visuomotor policy framework that addresses these issues with three complementary mechanisms.
  arXiv  Detail & Related papers  (2026-07-04T13:12:38Z)
• World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry [82.93104394404781]
  General-purpose world models promise scalable policy evaluation, optimization, and planning.<n>We propose World Action Verifier (WAV), a framework that enables world models to identify their own prediction errors and self-improve.
  arXiv  Detail & Related papers  (2026-04-02T12:48:36Z)
• From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation [18.70033095161235]
  We propose a framework that distills a Conditional Flow Matching expert into a fast single-step student via Implicit Likelihood Estimation (IMLE)<n>A bi-directional Chamfer distance provides a set-level objective that promotes both mode coverage and fidelity.<n>A unified perception encoder further integrates multi-view RGB, depth, point clouds, and proprioception into a geometry-aware representation.
  arXiv  Detail & Related papers  (2026-03-10T09:30:05Z)
• BiKC+: Bimanual Hierarchical Imitation with Keypose-Conditioned Coordination-Aware Consistency Policies [25.25845809170421]
  We propose a novel keypose-conditioned coordination-aware consistency policy tailored for bimanual manipulation.<n>Our framework instantiates hierarchical imitation learning with a high-level keypose predictor and a low-level trajectory generator.<n>In particular, we devise an innovative approach for identifying bimanual keyposes, considering both robot-centric action features and task-centric operation styles.
  arXiv  Detail & Related papers  (2026-01-17T17:33:18Z)
• Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion [60.186310080523135]
  Bifurcation of generative modeling into autoregressive approaches for discrete data (text) and diffusion approaches for continuous data (images) hinders development of truly unified multimodal systems.<n>We propose textbfCoM-DAD, a novel probabilistic framework that reformulates multimodal generation as a hierarchical dual-process.<n>Our method demonstrates superior stability over standard masked modeling, establishing a new paradigm for scalable, unified text-image generation.
  arXiv  Detail & Related papers  (2026-01-07T16:21:19Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking [29.920087317401396]
  Generative Behavior Cloning is a simple yet effective framework for robot learning.<n>We propose two novel techniques to enhance the consistency and reactivity of diffusion policies.<n>Our approach substantially improves GBC performance across a wide range of simulated and real-world robotic manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-14T11:16:34Z)
• DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation [23.382067451764396]
  Flow-based generative models have emerged as a promising solution to learning distributions of actions.<n>Existing flow-based policies suffer from representation collapse, the inability to distinguish similar visual representations, leading to failures in precise manipulation tasks.<n>We propose DM1, a novel flow matching framework that integrates dispersive regularization into MeanFlow to prevent collapse while maintaining one-step efficiency.
  arXiv  Detail & Related papers  (2025-10-09T07:12:20Z)
• Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance [63.33213516925946]
  We introduce textbfAlign-Then-stEer (textttATE), a novel, data-efficient, and plug-and-play adaptation framework.<n>Our work presents a general and lightweight solution that greatly enhances the practicality of deploying VLA models to new robotic platforms and tasks.
  arXiv  Detail & Related papers  (2025-09-02T07:51:59Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [73.75271615101754]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model [54.64088247291416]
  A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
  arXiv  Detail & Related papers  (2025-03-13T17:59:52Z)
• CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction [28.761494362934087]
  Coarse-to-Fine AutoRegressive Policy (CARP) is a novel paradigm for visuomotor policy learning.<n>It redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach.<n>CARP achieves competitive success rates, with up to a 10% improvement, and delivers 10x faster inference compared to state-of-the-art policies.
  arXiv  Detail & Related papers  (2024-12-09T18:59:18Z)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)
• BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulation [48.08416841005715]
  We introduce a novel keypose-conditioned consistency policy tailored for bimanual manipulation. It is a hierarchical imitation learning framework that consists of a high-level keypose predictor and a low-level trajectory generator. Simulated and real-world experimental results demonstrate that the proposed approach surpasses baseline methods in terms of success rate and operational efficiency.
  arXiv  Detail & Related papers  (2024-06-14T14:49:12Z)

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.