Image de couverture de livre

From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Zhuofan, Yang, Hongkun, Chen, Zhenyang, Chen, Yangxuan, Yingyan, Lin, Li, Chaojian
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
par: Guan, Weifan, et autres
Publié: (2025)

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
par: Zheng, Zihao, et autres
Publié: (2026)

HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
par: Zheng, Zihao, et autres
Publié: (2026)

2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency
par: Fu, Yonggan, et autres
Publié: (2021)

MEM: Multi-Scale Embodied Memory for Vision Language Action Models
par: Torne, Marcel, et autres
Publié: (2026)

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
par: Lyu, Mingyang, et autres
Publié: (2025)

APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model
par: Lu, Yuanjie, et autres
Publié: (2026)

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
par: Chen, Xiaoyu, et autres
Publié: (2025)

VLP: Vision-Language Preference Learning for Embodied Manipulation
par: Liu, Runze, et autres
Publié: (2025)

HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks
par: Xiong, Zheng, et autres
Publié: (2025)

XPG-RL: Reinforcement Learning with Explainable Priority Guidance for Efficiency-Boosted Mechanical Search
par: Zhang, Yiting, et autres
Publié: (2025)

Understanding Asynchronous Inference Methods for Vision-Language-Action Models
par: Agouzoul, Ayoub
Publié: (2026)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
par: Li, Runze, et autres
Publié: (2026)

Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization
par: Gao, Tianci, et autres
Publié: (2024)

Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
par: Huang, Jialei, et autres
Publié: (2025)

FAST: Efficient Action Tokenization for Vision-Language-Action Models
par: Pertsch, Karl, et autres
Publié: (2025)

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
par: Zhang, Zhilong, et autres
Publié: (2026)

RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models
par: Chen, Liangliang, et autres
Publié: (2024)

Confidence Calibration in Vision-Language-Action Models
par: Zollo, Thomas P, et autres
Publié: (2025)

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
par: Huang, Dongchi, et autres
Publié: (2025)

Prediction Horizon Requirements for Automated Driving: Optimizing Safety, Comfort, and Efficiency
par: Sánchez, Manuel Muñoz, et autres
Publié: (2024)

EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learning
par: Poudel, Bibek, et autres
Publié: (2023)

From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
par: Zhang, Zhengshen, et autres
Publié: (2025)

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
par: Zhang, Hongyin, et autres
Publié: (2025)

Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency
par: Kobayashi, Taisuke, et autres
Publié: (2024)

Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
par: Cai, Rui, et autres
Publié: (2026)

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
par: Hu, Jiaheng, et autres
Publié: (2026)

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
par: Zheng, Zihao, et autres
Publié: (2026)

OpenVLA: An Open-Source Vision-Language-Action Model
par: Kim, Moo Jin, et autres
Publié: (2024)

Few-Shot Vision-Language Action-Incremental Policy Learning
par: Song, Mingchen, et autres
Publié: (2025)

RL Token: Bootstrapping Online RL with Vision-Language-Action Models
par: Xu, Charles, et autres
Publié: (2026)

Sigma: The Key for Vision-Language-Action Models toward Telepathic Alignment
par: Wang, Libo
Publié: (2025)

CADENCE: Context-Adaptive Depth Estimation for Navigation and Computational Efficiency
par: Johnsen, Timothy K, et autres
Publié: (2026)

Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
par: Obando-Ceron, Johan, et autres
Publié: (2025)

Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
par: Driess, Danny, et autres
Publié: (2025)

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
par: Zhao, Yanpeng, et autres
Publié: (2026)

$π_0$: A Vision-Language-Action Flow Model for General Robot Control
par: Black, Kevin, et autres
Publié: (2024)

Improving Vision-Language-Action Model with Online Reinforcement Learning
par: Guo, Yanjiang, et autres
Publié: (2025)

$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
par: Intelligence, Physical, et autres
Publié: (2025)

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
par: Francis-Meretzki, Shelly, et autres
Publié: (2026)