Efficient VLA Inference

VLA: Vision-Language-Action Model

Overview

This topic studies how to run vision-language-action models fast enough for responsive, reliable robot control, including on edge devices. Common approaches prune or cache visual tokens, quantize or distill models, reduce action-generation steps, and overlap inference with observation and execution. Methods are tested on manipulation benchmarks such as LIBERO and RoboTwin, as well as real robots, using measures like latency, control frequency, memory, energy, and task success. The main tension is that faster inference can undermine closed-loop reliability or motion quality, so gains must be assessed in full task execution rather than by model speed alone.

Latest papers

CardsList

221 papers36 papers in the last four weeks, down 35% on the four weeks before. 0.3% of all new papers.

  1. Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA

    Apr 3, 2026Zihua Wang, Zhitao Lin, Ruibo Li +4Closed-Loop Control of VLAsVision-Language-Action Models

  2. MobiGuide: Vocabulary-Guided Online Recovery for Mobile Manipulation

    Apr 2, 2026Jia Syuen Lim, Zhizhen Zhang, Peter Bohm +3Mobile ManipulationDiffusion Policy

  3. Training-Free Interaction-Aligned Visual Token Pruning for Efficient Embodied Manipulation

    Mar 24, 2026Jintao Cheng, Weibin Li, Haozhe Wang +7Visual Token PruningEfficient VLA Inference

  4. Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring

    Mar 24, 2026Teng Yan, Zhengyang Pei, Chengyu Shi +8Affordance-Based Robotic ManipulationRobotic Manipulation

  5. DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models

    Mar 23, 2026Zhide Zhong, Junfeng Li, Junjie He +10VLMs for RoboticsReasoning for VLAs

  6. RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models

    Mar 21, 2026Zihao Zheng, Hangyu Cao, Jiayu Chen +6Edge-Cloud Collaborative InferenceEfficient VLA Inference

  7. FASTER: Rethinking Real-Time Flow VLAs

    Mar 19, 2026Yuxiang Lu, Zhe Liu, Xianzhe Fan +5Efficient VLA InferenceRobotics

  8. From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models

    Mar 19, 2026Zhuofan Li, Hongkun Yang, Zhenyang Chen +4Efficient VLAsVision-Language-Action Models

  9. ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models

    Mar 18, 2026Zhou Fang, Jiaqi Wang, Wenzhuo Li +2Efficient VLA InferenceVision-Language-Action Models

  10. HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness

    Mar 18, 2026Zihao Zheng, Zhihao Mao, Sicheng Tian +8Efficient VLA InferenceSpeculative Decoding

  11. Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies

    Mar 16, 2026Utkarsh Grover, Ravi Ranjan, Mingyang Mao +9Robot Foundation ModelsEdge Computing

  12. AnolisVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile Manipulation

    Mar 16, 2026Yusuke Takagi, Motonari Kambara, Daichi Yashima +3Language-Conditioned Robot ManipulationVision-Language-Action Models

  13. AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving

    Mar 16, 2026Wenhui Huang, Songyan Zhang, Qihang Huang +6Mixture-of-TransformersEnd-to-End Autonomous Driving

  14. OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism

    Mar 15, 2026Xiangyu Li, Huaizhi Tang, Xin Ding +3Efficient VLA InferenceKV-Cache Management

  15. DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

    Mar 11, 2026Shuyao Shang, Bing Zhan, Yunfei Yan +9Autonomous DrivingVision-Language-Action Models

  16. DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference

    Mar 11, 2026Yuquan Li, Lianjie Ma, Han Ding +1Efficient VLA InferenceVisual Token Compression

  17. ActECC: Action Chunk Temporal Harnessing for Edge-Cloud Collaborative VLA Inference System

    Mar 9, 2026Zihao Zheng, Zhihao Mao, Hui Huang +9Temporal Modeling for VLAsEdge-Cloud Collaborative Inference

  18. DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

    Mar 9, 2026Zihao Zheng, Hangyu Cao, Chibang Tao +9VLM QuantizationEfficient VLA Inference

  19. Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation

    Mar 5, 2026Pengfei Yi, Yingjie Ma, Wenjiang Xu +4Long-Horizon Robotic ManipulationVLMs for Robotics

  20. LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics

    Mar 3, 2026Justin Williams, Kishor Datta Gupta, Roy George +1Efficient VLA InferenceOn-Device Inference

  21. KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models

    Mar 2, 2026Zihao Zheng, Zhihao Mao, Maoliang Li +6Robot KinematicsEfficient VLA Inference

  22. ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models

    Mar 2, 2026Cheng Yang, Jianhao Jiao, Lingyi Huang +8Vision-Language-Action ModelsReasoning for VLAs

  23. Unifying Language-Action Understanding and Generation for Autonomous Driving

    Mar 2, 2026Xinyang Wang, Qian Liu, Wenjie Ding +7Vision-Language-Action ModelsEnd-to-End Autonomous Driving

  24. Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures

    Mar 1, 2026Manoj Vishwanathan, Suvinay Subramanian, Anand RaghunathanVision-Language-Action ModelsEfficient VLA Inference

  25. DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation

    Feb 26, 2026Zebin Yang, Yijiahao Qi, Tong Xie +3Layer Skipping in Language Model DecodingEfficient VLA Inference

  26. Recursive Belief Vision Language Action Models

    Feb 24, 2026Vaidehi Bagaria, Bijo Sebastian, Nirav Kumar PatelVision-Language-Action ModelsLong-Horizon Robotic Manipulation