Efficient VLA Model Inference

VLA: Vision-Language-Action

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 300% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 104

All topics

REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
Oct 8, 2026Houlong Xiong, Zhenqi Qiu, Zechen Wang +8Robotic Control Vision-Language-Action Models
Shanghai Jiao Tong University · PrimeBot · ShanghaiTech University +2
FastJEV: Understanding Redundancy for Compact JEV Inference
Oct 8, 2026Jie Ma, Jie Gao, Yihang Liu +5Efficient Multimodal Inference Efficient VLA Model Inference
Xiamen University
SpikingVLA: Asynchronous Spiking Vision-Language-Action Models
Oct 7, 2026Jingya Wang, Dehao Zhang, Shuai Wang +3Efficient VLA Model Inference Spiking Neural Networks
University of Electronic Science and Technology of China · Shenzhen Loop Area Institute · The Chinese University of Hong Kong (Shenzhen)
CARE: Certifying Acceleration for Vision-Language-Action Inference
Oct 6, 2026Rui Liu, Tong Zheng, Jindong Gu +1Efficient VLA Model Inference Vision-Language-Action Models
University of Maryland, College Park · University of Oxford · Google
ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference
Oct 6, 2026Zou Qingyun, Bin Gao, Wenju Zhao +3Energy-Efficient ML VLM Quantization
National University of Singapore · Huazhong University of Science and Technology
StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
Oct 6, 2026Shangyuan Yuan, Xinda Qi, Yujiang Pu +2Efficient VLA Model Inference Vision-Language-Action Models
Michigan State University · Ant Technology U.S., Inc.
ESP: Energy-Score Policy for One-Step Multimodal Action Generation
Oct 6, 2026Lilika Makabe, Heecheol Kim, Yasuyuki MatsushitaEfficient VLA Model Inference Vision-Language-Action Models
Microsoft Research Asia - Tokyo · Graduate School of Information Science and Technology, the University of Osaka
VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models
Oct 5, 2026Jaemin Kim, Jiahn Kim, Taesik GongZeroth-Order Optimization Efficient VLA Model Inference
UNIST
When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models
Oct 5, 2026Seonghoon Yu, Dongwon Kim, HyungRok Jung +4Efficient VLA Model Inference Robotic Manipulation
KAIST · GIST · POSTECH +1
When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA
Oct 4, 2026Tianjun Shi, Haotian Xiong, Ziyu Gong +2Efficient VLA Model Inference Vision-Language-Action Models
University of Macau
Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design
Oct 4, 2026Seonghun Jung, Sieun Moon, Jiyoung Jeong +2Efficient VLA Model Inference Vision-Language-Action Models
KAIST Daejeon, Republic of Korea
Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
Oct 4, 2026Hyemin Yang, Wooseong Jeong, Giwon Lee +1Uncertainty Estimation for VLA Models Efficient VLA Model Inference
KAIST
Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination
Oct 2, 2026Shenglan Li, Zhendong Mi, Hengyi Zhu +6VLMs for Robotics Reasoning for VLA Models
Stevens Institute of Technology · Northeastern University · Arizona State University +1
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
Oct 1, 2026Jiawei Fan, Sifeng Wang, Yuqing Hou +1Flow Matching Robot Foundation Models
Intel Labs China · Midea AI Research
Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation
Sep 30, 2026Di Wu, Rongtian Shen, Ping Liu +8Robotic Control Flow Matching
Magic-Lab Team, Magiclab Robotics Inc. · Southeast University · Harbin Institute of Technology +3
Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts
Sep 30, 2026Jingbo Wang, Wenxuan Song, Wenhao Yu +6Flow Matching Efficient VLA Model Inference
The Hong Kong University of Science and Technology (Guangzhou) · South China University of Technology · University of Science and Technology of China +3
WayFinder: Hierarchical Visual-Language-Action for Zero-Shot Waypoint Generation and Low-Level Kinematic Control
Sep 29, 2026Timothy K Johnsen, Marco LevoratoRobotic Control Large Language Model-Based Robot Planning
San Diego State University and The University of California, Irvine in CA, USA · University of California, Irvine in CA, USA
Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control
Sep 29, 2026Zibo Wang, Haochen Han, Pengzhen Ren +2Robotic Control Efficient VLA Model Inference
Pengcheng Laboratory
Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration
Sep 29, 2026Qiwei Chen, Kaijun Zhou, Nuohui Shi +3VLM Evaluation Efficient VLA Model Inference
Shanghai Jiao Tong University
Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference
Sep 29, 2026Jiayu Chen, Shuyong Gao, Jingkai Jia +6Efficient VLA Model Inference VLMs for Robotics
Fudan University · The Hong Kong Polytechnic University
Reactive Real-Time Flow Policies via Asynchronous Distribution Alignment
Sep 29, 2026Moritz Zoellner, Reece O'Mahoney, Ioannis Havoutis +1Robot Policy Learning Efficient VLA Model Inference
Department of Computer Science, Purdue University · Oxford Robotics Institute, University of Oxford
Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks
Sep 29, 2026Guoheng Sun, Chen Chen, Jin Wang +2Long-Horizon Robotic Manipulation Action-Conditioned World Models
University of Maryland, College Park · Independent Researcher · Oxford Robotics Institute, University of Oxford
EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model
Sep 28, 2026Rithvik Jonna, Man Namgung, Aakash Gurram +1Visual Navigation VLM Quantization
Department of Electrical and Computer Engineering Johns Hopkins University · Laboratory for Computational Sensing and Robotics Johns Hopkins University
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 Models Efficient VLA Model Inference
Leap Lab, Tsinghua University · University of Science and Technology of China · Beijing Institute of Technology
Don't Throw Away the Tail: Action Upcycling for Policy Acceleration
Sep 28, 2026Taesung Kwon, Jangho Park, Sunwoo Park +5Robot Policy Learning Efficient VLA Model Inference
KAIST · Sungkyunkwan University
D $^2$ -VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
Sep 28, 2026Zijian Ye, Chengqi Wei, Wei Huang +9Memory-Augmented VLMs Long-Horizon Robotic Manipulation
The University of Hong Kong · Southern University of Science and Technology
Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning
Sep 28, 2026Shengchao Hu, Peng Wang, Qiyang Zhou +5Efficient VLA Model Inference Vision-Language-Action Models
Shanghai Jiao Tong University · Shenzhen Campus of Sun Yat-sen University · Nanyang Technological University
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 Model Inference Vision-Language-Action Models
College of Engineering, Southern University of Science and Technology (SUSTech), Shenzhen 518055, China · Master of Science in Data Science and Machine Learning, Department of Mathematics, Faculty of Science, National University of Singapore, Singapore
RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
Sep 28, 2026Yuhan Chen, Ke Yu, Pengfei Liu +3Efficient VLA Model Inference Vision-Language-Action Models
Zhejiang University · Nanyang Technological University
Quantile Head for Vision-Language-Action Models
Sep 28, 2026Xuan Wang, Yinan Wu, Haoran Duan +1Quantile Regression Efficient VLA Model Inference
Department of Automation Tsinghua University

Oct 8, 2026, cs.ROJ/K move · Enter open · S save

REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models

Houlong Xiong, Zhenqi Qiu, Zechen Wang, Suohang Zhang+7

Shanghai Jiao Tong University · PrimeBot · ShanghaiTech University+2

Robotic Control Vision-Language-Action Models Action Chunking Efficient VLA Model Inference

Open paper AskPDF arXiv

Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-off: long chunks provide smooth execution, whereas frequent replanning improves reactivity at the cost of action discontinuities. We introduce REACT, a rolling-denoising framework that makes flow-based VLAs more reactive while preserving long-horizon context. Instead of regenerating entire action chunks from scratch, REACT maintains a persistent action buffer with staggered flow timesteps. At each control step, the full horizon is denoised using the latest observation, the cleanest action block is executed, partially refined future blocks are shifted forward, and fresh noise is appended to the tail. As a result, each executed action block is refined across multiple recent observations before deployment. To support real-time control, we further introduce dual decoupling, which separates sensing, VLM encoding, DiT denoising, and action execution, enabling high-frequency observation updates and action streaming under practical compute constraints. Across the RoboTwin 2.0 simulation benchmark and real-world tasks spanning bimanual manipulation and dynamic control on multiple robot platforms, REACT improves task success and reduces reaction latency while producing smoother trajectories than frequent-replanning and asynchronous baselines.

Momentum

Related topics

Latest papers 104