TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration

• URL: http://arxiv.org/abs/2512.15773v1
• Date: Sat, 13 Dec 2025 07:53:14 GMT
• Title: TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
• Authors: Ye Li, Jiahe Feng, Yuan Meng, Kangye Ji, Chen Tang, Xinwan Wen, Shutao Xia, Zhi Wang, Wenwu Zhu,
• Abstract summary: Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
• Score: 64.32072516882947
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. The temporal complexity of embodied tasks demands a dynamic and adaptable computation mode. Static and lossy acceleration methods, such as quantization, fail to handle such dynamic embodied tasks, while speculative decoding offers a lossless and adaptive yet underexplored alternative for DP. However, it is non-trivial to address the following challenges: how to match the base model's denoising quality at lower cost under time-varying task difficulty in embodied settings, and how to dynamically and interactively adjust computation based on task difficulty in such environments. In this paper, we propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP), the first framework that enables speculative decoding for DP with temporal adaptivity. First, to handle dynamic environments where task difficulty varies over time, we distill a Transformer-based drafter to imitate the base model and replace its costly denoising calls. Second, an RL-based scheduler further adapts to time-varying task difficulty by adjusting speculative parameters to maintain accuracy while improving efficiency. Extensive experiments across diverse embodied environments demonstrate that TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz and enabling real-time diffusion-based control without performance degradation.

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)
• Hierarchical Online-Scheduling for Energy-Efficient Split Inference with Progressive Transmission [23.81409473238433]
  Device-edge collaborative inference with Deep Neural Networks (DNNs) faces fundamental trade-offs among accuracy, latency and energy consumption.<n>This paper proposes a novel ENergy-ACcuracy Hierarchical optimization framework for split Inference, named ENACHI.<n> Experiments on ImageNet dataset demonstrate that ENACHI outperforms state-of-the-art benchmarks under varying deadlines and bandwidths.
  arXiv  Detail & Related papers  (2026-01-13T01:56:46Z)
• Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy [40.173458986694584]
  We introduce Difficulty-Aware Interpolant Policy (DA-SIP), a framework that enables robotic controllers to adaptively adjust their integration horizon in real time based on task difficulty.<n>DA-SIP achieves 2.6-4.4x reduction in total time while maintaining task success rates comparable to fixed maximum-computation baselines.
  arXiv  Detail & Related papers  (2025-11-25T22:46:42Z)
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching [51.98089287914147]
  textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.<n>Inspired by the two-stage decision-making process in humans, we propose a textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.
  arXiv  Detail & Related papers  (2025-10-23T03:52:39Z)
• DeCo-SGD: Joint Optimization of Delay Staleness and Gradient Compression Ratio for Distributed SGD [5.618337879898599]
  Distributed machine learning in high-end-to-end latency and low, varying bandwidth networks undergoes severe throughput degradation.<n>Existing approaches typically employ gradient compression and delayed aggregation to alleviate low bandwidth and high latency.<n>We propose DeCoSGD, which dynamically adjusts the compression ratio and staleness based on the real-time network condition.
  arXiv  Detail & Related papers  (2025-07-23T09:22:51Z)
• Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models [66.57755931421285]
  Large-scale artificial intelligence (LAI) models pose significant challenges for real-time communication scenarios.<n>This paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models.<n>We propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference.
  arXiv  Detail & Related papers  (2025-06-16T08:42:16Z)
• Adaptive Inference-Time Scaling via Cyclic Diffusion Search [61.42700671176343]
  We introduce the challenge of adaptive inference-time scaling-dynamically adjusting computational effort during inference.<n>We propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework.<n>ABCD refines outputs through bi-directional diffusion cycles while adaptively controlling exploration depth and termination.
  arXiv  Detail & Related papers  (2025-05-20T07:31:38Z)
• CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationarity [0.0]
  We introduce a novel architecture, ChoronoAdaptive Network (CANet), inspired by style-transfer techniques.<n>The core of CANet is the Non-stationary Adaptive Normalization module, seamlessly integrating the Style Blending Gate and Adaptive Instance Normalization (AdaIN)<n> experiments on real-world datasets validate CANet's superiority over state-of-the-art methods, achieving a 42% reduction in MSE and a 22% reduction in MAE.
  arXiv  Detail & Related papers  (2025-04-24T20:05:33Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)

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.