# Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation

arXiv: https://arxiv.org/abs/2509.22093 · HTML: https://mlsanity.com/paper/2509.22093/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 25 of 25)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control](https://mlsanity.com/paper/2502.05855/) (2025)
- [NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks](https://mlsanity.com/paper/2504.19854/) (2025)
- [DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution](https://mlsanity.com/paper/2411.02359/) (2024)
- [EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2506.10100/) (2025)
- [VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching](https://mlsanity.com/paper/2502.02175/) (2025)
- [MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation](https://mlsanity.com/paper/2503.20384/) (2025)
- [SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration](https://mlsanity.com/paper/2506.12723/) (2025)
- [Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models](https://mlsanity.com/paper/2505.21200/) (2025)
- [Cross-Self KV Cache Pruning for Efficient Vision-Language Inference](https://mlsanity.com/paper/2412.04652/) (2024)

## Built on by (most cited first, 30 of 34)

- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey](https://mlsanity.com/paper/2510.17111/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [GeoSem-WAM: Geometry- and Semantic-Aware World Action Models](https://mlsanity.com/paper/2606.03188/) (2026)
- [Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance](https://mlsanity.com/paper/2603.25661/) (2026)
- [Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2512.09927/) (2025)
- [TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration](https://mlsanity.com/paper/2512.15773/) (2025)
- [See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model](https://mlsanity.com/paper/2605.11817/) (2026)
- [StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models](https://mlsanity.com/paper/2608.11671/) (2026)
- [AttenA+: Rectifying Action Inequality in Robotic Foundation Models](https://mlsanity.com/paper/2605.13548/) (2026)
- [SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation](https://mlsanity.com/paper/2605.29662/) (2026)
- [TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models](https://mlsanity.com/paper/2603.24584/) (2026)
- [Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation](https://mlsanity.com/paper/2605.02757/) (2026)
- [ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2605.29438/) (2026)
- [Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation](https://mlsanity.com/paper/2606.31382/) (2026)
- [DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference](https://mlsanity.com/paper/2603.10469/) (2026)
- [Training-Free Interaction-Aligned Visual Token Pruning for Efficient Embodied Manipulation](https://mlsanity.com/paper/2603.22991/) (2026)
- [Move-Then-Operate: Behavioral Phasing for Human-Like Robotic Manipulation](https://mlsanity.com/paper/2604.23620/) (2026)
- [Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think](https://mlsanity.com/paper/2606.20246/) (2026)
- [Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete](https://mlsanity.com/paper/2605.12160/) (2026)
- [Differentiable Efficient Operator Search](https://mlsanity.com/paper/2606.05232/) (2026)
- [Role-Conditioned Sub-Token Routing for Efficient Vision-Language-Action Policies](https://mlsanity.com/paper/2608.18410/) (2026)
- [Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models](https://mlsanity.com/paper/2608.21247/) (2026)
- [ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics](https://mlsanity.com/paper/2609.07838/) (2026)
- [Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs](https://mlsanity.com/paper/2609.21022/) (2026)
- [SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference](https://mlsanity.com/paper/2609.28064/) (2026)
- [The Decision Value of Perception Compute](https://mlsanity.com/paper/2609.35910/) (2026)
- [Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference](https://mlsanity.com/paper/2609.36967/) (2026)
- [Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control](https://mlsanity.com/paper/2609.37772/) (2026)
- [Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination](https://mlsanity.com/paper/2609.38984/) (2026)

## Abstract (arXiv)

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by reducing visual redundancy within VLA models, but they overlook the varying redundancy across robotic manipulation stages. We observe that the visual token redundancy is higher in coarse manipulation phase than in fine-grained operations, and is strongly correlated with the action dynamic. Motivated by this observation, we propose Action-aware Dynamic Pruning (ADP), a multi-modal pruning framework that integrates text-driven token selection with action-aware trajectory gating. Our method introduces a gating mechanism that conditions the pruning signal on recent action trajectories, using past motion windows to adaptively adjust token retention ratios in accordance with dynamics, thereby balancing computational efficiency and perceptual precision across different manipulation stages. Extensive experiments on the LIBERO suites and diverse real-world scenarios demonstrate that our method significantly reduces FLOPs and action inference latency (textite.g. 1.35 × speed up on OpenVLA-OFT) while maintaining competitive success rates (textite.g. 25.8% improvements with OpenVLA) compared to baselines, thereby providing a simple plug-in path to efficient robot policies that advances the efficiency and performance frontier of robotic manipulation. Our project website is: hrefhttps://vla-adp.github.io/ADP.com.