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. Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs

    Sep 24, 2026Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro +3Efficient VLA InferenceVision-Language-Action Models

  2. CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action Execution

    Sep 23, 2026Shuai Zeng, Yuxuan Liang, Hangmiao Hu +4Efficient VLA InferenceVision-Language-Action Models

  3. VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models

    Sep 21, 2026Jiuyi Xu, Qing Jin, Meida Chen +3Mixed-Precision QuantizationClosed-Loop Control of VLAs

  4. FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding

    Sep 21, 2026Hung T. Ho, Khanh D. Nguyen, Quang D. Nguyen +5VLM QuantizationEfficient VLA Inference

  5. vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation

    Sep 21, 2026Khanh D. Nguyen, Hoang M. Truong, An T. LeLanguage-Conditioned Robot ManipulationEfficient VLA Inference

  6. StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies

    Sep 19, 2026Wenzhuo Li, Qiongfeng Shi, Yi ZhouMemory-Augmented VLMsVision-Language-Action Models

  7. React When You Need To: Event-Triggered Asynchronous Inference for VLA Policies

    Sep 18, 2026Yansong Wu, Huaqing Li, Tianding Hou +2Vision-Language-Action ModelsVLMs for Robotics

  8. Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies

    Sep 18, 2026Zhipeng Tang, Xinda Chen, Weining Rao +5Flow-Based VLAsEfficient VLA Inference

  9. SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation

    Sep 17, 2026Kaivalya Agrawal, Md Ashiqur Rahman, Raymond A. Yeh +1Long-Horizon Robotic ManipulationEfficient VLA Inference

  10. FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models

    Sep 16, 2026Yuchen Han, Jianhan Wu, Xiaoyang Qu +3Diffusion SamplingEfficient VLA Inference

  11. rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference

    Sep 16, 2026Kaijun Zhou, Zhiyang Li, Le Chen +1Efficient VLA InferenceVision-Language-Action Models

  12. KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Models

    Sep 16, 2026Anna Li, Christina Giannoula, Nandita VijaykumarEfficient VLA InferenceVision-Language-Action Models

  13. VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge

    Sep 16, 2026Deyu Cao, Ryuji Oi, Kosuke Matsushima +4Efficient VLA InferenceVision-Language-Action Models

  14. Technical Report: One-Step Drifting Action Heads for GR00T N1.7

    Sep 16, 2026Xihe ShaoEfficient VLA InferenceVision-Language-Action Models

  15. Efficient Vision-Language-Action Management and Serving for Robot Factories

    Sep 10, 2026Dionysios Adamopoulos, Nattapol Chanpaisit, Basel Fakhri +1Edge ComputingEfficient VLA Inference

  16. IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

    Sep 10, 2026Kian Hosseinkhani, Qinhe Peng, George Shramko +6Efficient VLA InferenceVision-Language-Action Models

  17. ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics

    Sep 7, 2026Boliang Liu, Wint Yi Poe, Jingyun Di +2Efficient VLA InferenceEfficient VLAs

  18. GloVLA: Let Geometry Move and Local VLA Interact for Robust Object-Centric Manipulation in Unstructured Environments

    Sep 5, 2026Truong Thanh Nguyen, Huy Hoang Nguyen, Ha Anh Nguyen +5Hierarchical Robot ControlRobotic Manipulation

  19. Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies

    Sep 4, 2026Andrew Ting Yan Li, Zhuo Li, Zhelin Yang +3Reasoning for VLAsVision-Language-Action Models

  20. Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving

    Sep 3, 2026Ruoyu Yao, Yusen Xie, Qingzhao Liu +5Latent Action LearningEnd-to-End Autonomous Driving

  21. SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

    Sep 2, 2026Cheng Yin, Wang Xu, Junpeng Yang +8Vision-Language-Action ModelsMemory-Augmented VLMs

  22. Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving

    Aug 31, 2026Tongfei Guo, Lili SuVLMs for Autonomous DrivingEfficient VLA Inference

  23. DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting

    Aug 30, 2026Yuxuan Gao, Shiqi Zhang, Yedong Shen +6Efficient VLA InferenceVisuomotor Policy Learning

  24. SMILE: Smooth Motion for Improved Long-Horizon VLA Execution

    Aug 29, 2026Jongwoo Park, E-Ro Nguyen, Kanchana Ranasinghe +3B-Spline Trajectory RepresentationVision-Language-Action Models

  25. Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation

    Aug 24, 2026Xiwen Chen, Zelin Li, Zhiruo Zhou +3Spatial Grounding for VLAsVision-Language-Action Models

  26. Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification

    Aug 16, 2026Chunyu Qi, Zhuoran Song, Jian Weng +6Efficient VLA InferenceRobotic Manipulation