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

arXiv: https://arxiv.org/abs/2512.15773 · HTML: https://mlsanity.com/paper/2512.15773/

## Key facts

- Cited by 6 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 43 of its 52 references that are in the map.
- First posted on arXiv 13 Dec 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 30 of 43)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Q-Diffusion: Quantizing Diffusion Models](https://mlsanity.com/paper/2302.04304/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Post-training Quantization on Diffusion Models](https://mlsanity.com/paper/2211.15736/) (2022)
- [PTQD: Accurate Post-Training Quantization for Diffusion Models](https://mlsanity.com/paper/2305.10657/) (2023)
- [Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation](https://mlsanity.com/paper/2405.07503/) (2024)
- [Speculative Decoding with Big Little Decoder](https://mlsanity.com/paper/2302.07863/) (2023)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers](https://mlsanity.com/paper/2406.17343/) (2024)
- [EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2506.10100/) (2025)
- [One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation](https://mlsanity.com/paper/2410.21257/) (2024)
- [SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration](https://mlsanity.com/paper/2506.12723/) (2025)
- [LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models](https://mlsanity.com/paper/2404.11098/) (2024)
- [Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation](https://mlsanity.com/paper/2509.22093/) (2025)
- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [Accelerated Diffusion Models via Speculative Sampling](https://mlsanity.com/paper/2501.05370/) (2025)
- [SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching](https://mlsanity.com/paper/2509.11628/) (2025)
- [Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey](https://mlsanity.com/paper/2510.17111/) (2025)

## Built on by (most cited first, 6 of 6)

- [RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics](https://mlsanity.com/paper/2603.12939/) (2026)
- [Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning](https://mlsanity.com/paper/2601.12894/) (2026)
- [ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2605.29438/) (2026)
- [Accelerating Speculative Diffusions via Block Verification](https://mlsanity.com/paper/2606.13426/) (2026)
- [Test-time Sparsity for Extreme Fast Action Diffusion](https://mlsanity.com/paper/2605.13316/) (2026)
- [rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference](https://mlsanity.com/paper/2609.19104/) (2026)

## Abstract (arXiv)

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.