Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning

• URL: http://arxiv.org/abs/2601.12894v1
• Date: Mon, 19 Jan 2026 09:50:36 GMT
• Title: Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
• Authors: Kangye Ji, Yuan Meng, Zhou Jianbo, Ye Li, Hanyun Cui, Zhi Wang,
• Abstract summary: Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions.<n>We propose $underlinetextbfS$parse $underlinetextbfA$ction$underlinetextbfG$en for extremely sparse action generation.
• Score: 9.92274274871221
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions, but its multi-step denoising processes make it impractical for real-time visuomotor control. Existing caching-based acceleration methods typically rely on $\textit{static}$ schedules that fail to adapt to the $\textit{dynamics}$ of robot-environment interactions, thereby leading to suboptimal performance. In this paper, we propose $\underline{\textbf{S}}$parse $\underline{\textbf{A}}$ction$\underline{\textbf{G}}$en ($\textbf{SAG}$) for extremely sparse action generation. To accommodate the iterative interactions, SAG customizes a rollout-adaptive prune-then-reuse mechanism that first identifies prunable computations globally and then reuses cached activations to substitute them during action diffusion. To capture the rollout dynamics, SAG parameterizes an observation-conditioned diffusion pruner for environment-aware adaptation and instantiates it with a highly parameter- and inference-efficient design for real-time prediction. Furthermore, SAG introduces a one-for-all reusing strategy that reuses activations across both timesteps and blocks in a zig-zag manner, minimizing the global redundancy. Extensive experiments on multiple robotic benchmarks demonstrate that SAG achieves up to 4$\times$ generation speedup without sacrificing performance. Project Page: https://sparse-actiongen.github.io/.

Related papers

• Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy [52.106797722292896]
  We present DCDP, a Dynamic Closed-Loop Diffusion Policy framework that integrates chunk-based action generation with real-time correction.<n>In dynamic PushT simulations, DCDP improves adaptability by 19% without retraining while requiring only 5% additional computation.
  arXiv  Detail & Related papers  (2026-03-02T15:04:18Z)
• SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation [8.00733338569737]
  Retrieval-Augmented Generation grounds large language model outputs in external evidence.<n>Recent works scale RAG at inference time along two complementary dimensions.<n>We propose a multi-agent framework that coordinates sequential and parallel inference-time scaling.
  arXiv  Detail & Related papers  (2026-01-22T20:18:55Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• On Geometric Structures for Policy Parameterization in Continuous Control [7.056222499095849]
  We propose a novel, computationally efficient action generation paradigm that preserves the structural benefits of operating on a unit manifold.<n>Our method decomposes the action into a deterministic directional vector and a learnable concentration, enabling efficient between the target direction and uniform noise.<n> Empirically, our method matches or exceeds state-of-the-art methods on standard continuous control benchmarks.
  arXiv  Detail & Related papers  (2025-11-11T13:32:38Z)
• 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)
• OmniSAT: Compact Action Token, Faster Auto Regression [70.70037017501357]
  We introduce an Omni Swift Action Tokenizer, which learns a compact, transferable action representation.<n>The resulting discrete tokenization shortens the training sequence by 6.8$times$, and lowers the target entropy.
  arXiv  Detail & Related papers  (2025-10-08T03:55:24Z)
• Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation [27.007611140797852]
  Existing methods optimize inference speed by reducing visual redundancy within VLA models.<n>We propose textbfAction-aware textbfDynamic textbfPruning (textbfADP), a multi-modal pruning framework that integrates text-driven token selection with action-aware trajectory gating.
  arXiv  Detail & Related papers  (2025-09-26T09:13:02Z)
• Self-Guided Action Diffusion [53.38661283705301]
  Self-guided action diffusion is a more efficient variant of bidirectional decoding tailored for diffusion-based policies.<n>Our method achieves up to 70% higher success rates than existing counterparts on challenging dynamic tasks.
  arXiv  Detail & Related papers  (2025-08-17T00:39:15Z)
• Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation [49.45822979879046]
  Generative recommendation (GR) typically encodes behavioral or semantic aspects of item information into discrete tokens.<n>We present Chunk AutoRegressive Modeling (CAR), a new generation paradigm following the decision pattern that users usually think semantic aspects of items.
  arXiv  Detail & Related papers  (2025-06-30T09:13:54Z)
• Real-Time Execution of Action Chunking Flow Policies [49.1574468325115]
  This paper presents a novel inference-time algorithm that enables asynchronous execution of action interacting systems.<n>It is applicable to any diffusion- or VLA-based systems executing out of the box with no re-training.<n>Results show that RTC is fast, performant, and uniquely robust to inference manipulation.
  arXiv  Detail & Related papers  (2025-06-09T01:01:59Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning [33.790048240113165]
  In this work, we consider the low-data regime, with limited or no access to expert behavior.<n>We propose $textbfCode as Generative Affordances$ $(textbf$textttCoGA$)$.<n>By greatly reducing the number of actions that an agent must consider, we demonstrate on a wide range of tasks in the MiniWob++ benchmark.
  arXiv  Detail & Related papers  (2025-04-24T06:20:08Z)

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.