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. Allocentric Memory, Egocentric Acting: A Dual-Frame VLA for Urban Aerial Navigation

    Nov 18, 2026Haotian Xu, Yue Hu, Zhengqiu Zhu +3Aerial VLNSpatial Grounding for VLAs

  2. CoBoVLA: Decoupling Language from Action with Discrete Codes for Robust and Interpretable Robot Manipulation

    Nov 17, 2026Mehul Arora, Dhruv Agarwal, Ambuj AgrawalVision-Language-Action ModelsInstruction Generalization in VLAs

  3. GraSLA: A Lightweight Spatial-Language-Action Model with Grasp Hypotheses as Geometric Priors

    Nov 11, 2026Jibao Yuan, Zixiang Zhao, Wensong Xu +2Language-Conditioned Robot ManipulationRobotic Manipulation

  4. Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models

    Nov 7, 2026Jungin Park, Chaoran Zhu, Changjae Oh +1Vision-Language-Action ModelsEfficient VLAs

  5. OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation

    Oct 29, 2026Junli Liu, Zhongrui You, Chenhui Li +9Aerial VLNVision-Language-Action Models

  6. Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models

    Oct 28, 2026Jiuyi Xu, Xiao Hu, Meida Chen +3Mixed-Precision QuantizationVLM Quantization

  7. Vision-Language-Action or World-Action? Just Action Models

    Oct 27, 2026Yonghao Yu, Lang Huang, Runyi Li +1VLA TrainingWorld Action Models

  8. SmolVLA-MoE: Sparse Mixture-of-Experts for Efficient Multi-Task Robotic Manipulation

    Oct 22, 2026Shiyang Zhang, Miao Yang, Zhengda Li +4Efficient VLAsVision-Language-Action Models

  9. CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA

    Oct 19, 2026Feiyang Hong, Yujie Wei, Bo Zhao +3Vision-Language-Action ModelsEfficient VLAs

  10. Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving

    Oct 19, 2026Jie Wang, Guang Li, Zhijian Huang +5VLMs for Autonomous DrivingEfficient VLAs

  11. NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models

    Oct 16, 2026Guodong Du, Wanyu LinVision-Language-Action ModelsContinual Learning for VLAs

  12. REKI: Registering Knowledge in VLAs

    Oct 15, 2026Juliette Marrie, Paul Pacaud, Adrien Ramanana Rahary +2Vision-Language-Action ModelsEfficient VLAs

  13. Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision

    Oct 9, 2026Zile Zhong, Yuxin Du, Tao Lin +4Vision-Language-Action ModelsEfficient VLAs

  14. Tell Robot What Not to Do: A Negation Understanding Perspective

    Oct 8, 2026Fazeng Li, Gan Sun, Hao Cheng +2Vision-Language-Action ModelsReasoning for VLAs

  15. NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime

    Oct 7, 2026Gengze Zhou, Yicong Hong, Jiazhao Zhang +9Robot NavigationVision-Language Navigation

  16. GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation

    Oct 2, 2026Yixuan Jiang, Wentong Li, An Liu +5Vision-Language NavigationEfficient VLAs

  17. eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing

    Oct 1, 2026Dehao Huang, Jianbang Liu, Jianpan Gao +7Efficient VLAsRobotic Manipulation

  18. Spike-driven Vision-Language-Action Model

    Sep 30, 2026Shuai Wang, Malu Zhang, Mingquan Liu +8Efficient VLAsVision-Language-Action Models

  19. ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning

    Sep 28, 2026Di Zhu, Ziheng Yan, Fang WanRobotic ControlEfficient VLAs

  20. Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies

    Sep 28, 2026Jeongsol Kim, Youngjun Jun, Kyumin Choi +6Efficient VLAsVision-Language-Action Models

  21. FailPatch: Failure Residual Patching for Vision-Language-Action Models

    Sep 28, 2026Peng Yu, Jiacheng Wang, Ziheng Zhang +6Robot Policy LearningRobot Policy Adaptation

  22. SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models

    Sep 27, 2026Tianfu Li, Haoxuan Xu, Wenbo Chen +7World Model LearningVisuomotor Policy Learning

  23. Towards VLA-Dreamer: Refining VLA Behavior Using World Models

    Sep 25, 2026Parsa Mastouri Kashani, Jan-Gerrit Habekost, Stefan WermterWorld Models for VLAsVision-Language-Action Models

  24. FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation

    Sep 25, 2026Hiroshi Ito, Hyogo Hiruma, Yoshiki Kanai +3Language-Conditioned Robot ManipulationEfficient VLAs

  25. VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control

    Sep 25, 2026Kemou Jiang, Maonan Wang, Xingchen Zou +6Traffic Signal ControlEfficient VLAs

  26. SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists

    Sep 19, 2026Jan-Gerrit Habekost, Parsa Mastouri Kashani, Connor Gäde +5Flow Matching for Action GenerationVision-Language-Action Models