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. StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models

    Oct 6, 2026Shangyuan Yuan, Xinda Qi, Yujiang Pu +2Efficient VLA InferenceVision-Language-Action Models

  2. ESP: Energy-Score Policy for One-Step Multimodal Action Generation

    Oct 6, 2026Lilika Makabe, Heecheol Kim, Yasuyuki MatsushitaEfficient VLA InferenceVision-Language-Action Models

  3. When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

    Oct 5, 2026Seonghoon Yu, Dongwon Kim, HyungRok Jung +4Efficient VLA InferenceRobotic Manipulation

  4. FastOPD: On-Policy Distillation for Lightweight VLA Deployment

    Oct 2, 2026Yoojin Oh, Jeongsol Kim, Yeonwoo Seo +7Efficient VLA InferenceVision-Language-Action Models

  5. CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation

    Oct 2, 2026Jin Hyun, Jung Gyu Min, Gyuhyun Jung +1Post-Training QuantizationVLM Quantization

  6. Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination

    Oct 2, 2026Shenglan Li, Zhendong Mi, Hengyi Zhu +6VLMs for RoboticsReasoning for VLAs

  7. World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models

    Oct 1, 2026Jie He, Wei Li, Junwen Tong +3World Models for VLAsFlow-Based VLAs

  8. Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models

    Oct 1, 2026Jiawei Fan, Sifeng Wang, Yuqing Hou +1Flow MatchingRobot Foundation Models

  9. Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation

    Sep 30, 2026Di Wu, Rongtian Shen, Ping Liu +8Robotic ControlReal-Time Robot Control

  10. Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts

    Sep 30, 2026Jingbo Wang, Wenxuan Song, Wenhao Yu +6Flow MatchingEfficient VLA Inference

  11. WayFinder: Hierarchical Visual-Language-Action for Zero-Shot Waypoint Generation and Low-Level Kinematic Control

    Sep 29, 2026Timothy K Johnsen, Marco LevoratoRobotic ControlLarge Language Model-Based Robot Planning

  12. Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference

    Sep 29, 2026Jiayu Chen, Shuyong Gao, Jingkai Jia +6Efficient VLA InferenceVLMs for Robotics

  13. Reactive Real-Time Flow Policies via Asynchronous Distribution Alignment

    Sep 29, 2026Moritz Zoellner, Reece O'Mahoney, Ioannis Havoutis +1Robot Policy LearningEfficient VLA Inference

  14. Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks

    Sep 29, 2026Guoheng Sun, Chen Chen, Jin Wang +2Long-Horizon Robotic ManipulationAction-Conditioned World Models

  15. EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model

    Sep 28, 2026Rithvik Jonna, Man Namgung, Aakash Gurram +1Visual NavigationVLM Quantization

  16. What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

    Sep 28, 2026Renping Zhou, Zanlin Ni, Zihao Fan +8Action-Conditioned World ModelsEfficient VLA Inference

  17. Don't Throw Away the Tail: Action Upcycling for Policy Acceleration

    Sep 28, 2026Taesung Kwon, Jangho Park, Sunwoo Park +5Robot Policy LearningEfficient VLA Inference

  18. D2^2-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation

    Sep 28, 2026Zijian Ye, Chengqi Wei, Wei Huang +9Memory-Augmented VLMsLong-Horizon Robotic Manipulation

  19. Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning

    Sep 28, 2026Shengchao Hu, Peng Wang, Qiyang Zhou +5VLA AdaptationEfficient VLA Inference

  20. Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference

    Sep 28, 2026Qianer Li, Chengjie Zhang, Jingwen Chen +3Efficient VLA InferenceVision-Language-Action Models

  21. RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models

    Sep 28, 2026Yuhan Chen, Ke Yu, Pengfei Liu +3Efficient VLA InferenceVision-Language-Action Models

  22. Quantile Head for Vision-Language-Action Models

    Sep 28, 2026Xuan Wang, Yinan Wu, Haoran Duan +1Quantile RegressionEfficient VLA Inference