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. EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints

    Aug 16, 2026Ao Zhou, Bo Dai, Le Yu +5Efficient VLA InferenceEdge Inference

  2. BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control

    Aug 14, 2026Ming Shang, Yuchen Huang, Jiaoyang Chen +8Vision-Language-Action ModelsEfficient VLA Inference

  3. FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving

    Aug 13, 2026Zekai Li, Yihao Liang, Hongfei Zhang +3Efficient VLA InferenceAutonomous Driving

  4. Keep the Future, Drop the Rollout: RIFT for World Action Models

    Aug 12, 2026Chushan Zhang, Jinguang Tong, Xuesong Li +2Efficient VLA InferenceEfficient Inference for World Action Models

  5. Neural Introspection Gating for Adaptive KV-Cache Reuse in Vision-Language-Action Models

    Aug 11, 2026Zhijie Wu, Kento Kawaharazuka, Kei OkadaAdaptive InferenceKV Caching

  6. World Tokens: Enhancing Embodied Policies with Training-Time World Modeling

    Aug 10, 2026Qu Tang, Benhui Zhuang, Bo Yuan +3Efficient VLA InferenceEfficient VLAs

  7. Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Experts

    Aug 10, 2026Farida Mohsen, Thowayba Elkaffash, Mohammad Reza Chalak Qazani +3Vision-Language-Action ModelsEfficient VLA Inference

  8. Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model

    Aug 7, 2026Harisankar Babu, Benjamin Coors, Christopher Lang +3VLMs for Autonomous DrivingEfficient VLA Inference

  9. Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection

    Aug 6, 2026Yuewei Sun, Lang Qin, Zechuan Tian +11Efficient VLA InferenceVLMs for Robotics

  10. Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference

    Aug 5, 2026Zheng Liu, Zeyu Guo, Zihan Liu +9AI Accelerator InferenceEfficient VLA Inference

  11. Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

    Aug 5, 2026Weiheng Zhao, Haoyi Jiang, Xin Shi +5Action-Conditioned World ModelsEfficient VLA Inference

  12. PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud

    Aug 4, 2026Chenghua Wang, Daliang Xu, Dongqi Cai +21Efficient VLA InferenceOn-Device Inference

  13. Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution

    Aug 4, 2026Weichen Xu, Zhenhua Liu, Lin Luo +8Efficient VLA InferenceRobotic Manipulation

  14. WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA

    Aug 2, 2026Zhihao Zhu, Hanlin Shang, Mingwang Xu +6End-to-End Autonomous DrivingDiffusion Model Distillation

  15. The Gate, Not the Cache: Gate Provenance Bounds the Closed-Loop Reliability of Training-Free VLA Token Skipping

    Aug 1, 2026Qi Luo, Shuaijun Liu, Hao Zhao +5Efficient VLA InferenceVision-Language-Action Models

  16. Action Chunk Scheduling for Batched Robot Policy Serving

    Jul 31, 2026Rohan Bansal, David He, Nadun Ranawaka Arachchige +4Multi-Robot SystemsRobot Foundation Models

  17. FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling

    Jul 31, 2026Li Lin, Wujun Xu, Weiwei Meng +3Temporal Modeling for VLAsEfficient VLA Inference

  18. TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

    Jul 29, 2026Hengyi Xie, Chenfei Yao, Xianjin Wu +4Efficient VLA InferenceEfficient VLAs

  19. Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control

    Jul 29, 2026Weili Zeng, Yitong Xing, Fulong Liu +10World ModelsEfficient VLA Inference

  20. CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

    Jul 28, 2026Minhyeok Lee, Chiyoung Kim, Chanhoe Gu +5Reasoning for VLAsEfficient VLA Inference

  21. A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference

    Jul 27, 2026Zhuoran Song, Haozhe Jiang, Chunyu Qi +4AI Accelerator InferenceEfficient VLA Inference

  22. JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models

    Jul 17, 2026Haoran Sun, Wentao Zhang, Junyang Hua +18Efficient VLA InferenceVLA Post-Training

  23. Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving

    Jul 17, 2026Yun Li, Jiachen Gong, Simon Thompson +7Efficient VLA InferenceVision-Language-Action Models

  24. Reflex: Real-Time VLA Control through Streaming Inference

    Jul 16, 2026Yuanchun Guo, Bingyan LiuFlow MatchingKV Caching

  25. EagleVLA: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference

    Jul 14, 2026Zebin Yang, Qi Wang, Yunhe Wang +6Efficient VLA InferenceVision-Language-Action Models

  26. Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference

    Jul 14, 2026Yuzhou Wu, Yuxin Zheng, Muchun Niu +6Efficient VLA InferenceEfficient VLAs

  27. Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

    Jul 2, 2026Ling Xu, Chuyu Han, Borui Li +6Efficient Neural Network InferenceEfficient VLA Inference