Efficient VLAs

VLA: Vision-Language-Action Model

Overview

Efficient VLA research studies how robots and other embodied agents can connect visual observations and language instructions to actions under limited compute, memory, and latency budgets. Common approaches include compact backbones and action heads, visual-token pruning, quantization and cache reuse, and faster action generation through chunking, parallel decoding, or fewer diffusion steps. Other methods adapt computation to the task or reuse compressed memory so models can respond quickly while retaining context for long-horizon manipulation, navigation, and driving. Results on benchmarks such as LIBERO, RoboCasa, and driving and real-robot evaluations show that many methods can improve speed or reduce resource use, but efficiency must also be judged by task success, robustness, motion quality, and end-to-end execution cost.

Latest papers

CardsList

110 papers9 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.

  1. NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation

    Jul 7, 2026Ziye Wang, Modi Shi, Chaojun Ni +5Memory-Augmented VLMsLong-Horizon Robotic Manipulation

  2. XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning

    Jul 5, 2026Iok Tong Lei, Ying Jie Yap, Wei Huang +5Robot Policy LearningLanguage-Conditioned Robot Manipulation

  3. Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

    Jul 2, 2026Junhao Shi, Siyin Wang, Xiaopeng Yu +3Self-Supervised Pre-TrainingEfficient VLAs

  4. Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

    Jun 26, 2026Guoheng Sun, Kaixi Feng, Shwai He +8Model CompressionEfficient VLAs

  5. UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models

    Jun 22, 2026Lin Sun, Zhiwei Guan, Conglin Wang +7Efficient VLM InferenceEfficient VLA Inference

  6. PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

    Jun 21, 2026Xianghui Wang, Feng Chen, Wenbo Zhang +4Efficient VLAsVision-Language-Action Models

  7. UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling

    Jun 19, 2026Tao Xu, Runhao Zhang, Zhijian Huang +7World Models for RoboticsMulti-View Learning

  8. FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

    Jun 18, 2026Duc Minh Nguyen, Nghiem Tuong Diep, Binh Gia Nguyen +20VLM AdaptationEfficient VLAs

  9. Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

    Jun 18, 2026Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18Model CompressionVLM Compression

  10. PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space

    Jun 16, 2026Bochen Yang, Lianlei ShanEfficient VLAsLatent Visual Reasoning

  11. vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

    Jun 6, 2026Khanh D. Nguyen, Hung T. Ho, Chinh T. Nguyen +5AI Accelerator InferenceEfficient VLM Inference

  12. TBD-VLA: Temporal Block Diffusion Vision Language Action Model

    Jun 5, 2026Sung-Wook Lee, Xuhui Kang, Yen-Ling KuoEfficient VLA InferenceEfficient VLAs

  13. VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

    May 28, 2026Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9Efficient VLM InferenceEfficient VLA Inference

  14. ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models

    May 28, 2026Ye Li, Huanan Liu, Kangye Ji +7Efficient VLM InferenceEfficient VLA Inference

  15. Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling

    May 27, 2026Xinyu Wang, Mingze Li, Sicheng Lyu +6Post-Training QuantizationEfficient VLA Inference

  16. DriveMA: Rethinking Language Interfaces in Driving VLAs with One-Step Meta-Actions

    May 20, 2026Weicheng Zheng, Yixin Huang, Qiao Sun +2VLMs for Autonomous DrivingEfficient VLAs

  17. ActQuant: Sub-4-bit Action-Guided Backbone Weight-Only Quantization for Vision-Language-Action Models

    May 19, 2026Arash Akbari, Arman Akbari, Masih Eskandar +11Neural Network QuantizationVLM Quantization

  18. Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

    May 15, 2026Jin Shi, Brady Zhang, Yishun LuVLM DistillationEfficient VLA Inference

  19. Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

    May 14, 2026Tao Lin, Yuxin Du, Jiting Liu +14Language-Conditioned Robot ManipulationEfficient VLAs

  20. LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models

    May 11, 2026Boyang Shen, Kaixiang Yang, Hao Wang +4Efficient VLM InferenceEfficient VLA Inference

  21. One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy

    May 8, 2026Zuojin Tang, Shengchao Yuan, Xiaoxin Bai +4Visual Token CompressionEfficient VLAs

  22. ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations

    May 8, 2026Yuhao Zhou, Yunpeng Zhu, Yang Zhou +7Vision-Language ModelsEfficient VLAs

  23. MolmoAct2: Action Reasoning Models for Real-world Deployment

    May 4, 2026Haoquan Fang, Jiafei Duan, Donovan Clay +26Embodied ReasoningEfficient VLAs

  24. Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference

    May 4, 2026Yudong Liu, Yuan Li, Zijia Tang +12Efficient VLM InferenceEfficient VLA Inference

  25. Being-H0.7: A Latent World-Action Model from Egocentric Videos

    Apr 30, 2026Hao Luo, Wanpeng Zhang, Yicheng Feng +6Visuomotor Policy LearningEfficient VLAs