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

Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution
Aug 4, 2026Weichen Xu, Zhenhua Liu, Lin Luo +8Efficient VLA Model Inference Robotic Manipulation
1Peking University · 2Microsoft Research Asia
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 Driving Diffusion Model Distillation
Fudan University · Yinwang Inttelligent Technology Co.,Ltd
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 Model Inference Vision-Language-Action Models
The Hong Kong University of Science and Technology (Guangzhou) · Shenzhen University of Advanced Technology · Sangfor Technologies Inc. +1
Action Chunk Scheduling for Batched Robot Policy Serving
Jul 31, 2026Rohan Bansal, David He, Nadun Ranawaka Arachchige +4Multi-Robot Systems Robot Foundation Models
Georgia Institute of Technology
FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling
Jul 31, 2026Li Lin, Wujun Xu, Weiwei Meng +3Efficient VLA Model Inference Efficient VLA Models
Southeast University, Nanjing, Jiangsu, China · Nanyang Technological University, Singapore.
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 Model Inference Efficient VLA Models
Huazhong University of Science and Technology
Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control
Jul 29, 2026Weili Zeng, Yitong Xing, Fulong Liu +10World Models Efficient VLA Model Inference
Shanghai Jiao Tong University · Qilu University of Technology (Shandong Academy of Sciences)
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
Jul 28, 2026Minhyeok Lee, Chiyoung Kim, Chanhoe Gu +5CoT Distillation Efficient VLA Model Inference
Chung-Ang University, Republic of Korea
A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference
Jul 27, 2026Zhuoran Song, Haozhe Jiang, Chunyu Qi +4AI Accelerator Inference Efficient VLA Model Inference
School of Computer Science, Shanghai Jiao Tong University, 2 Institute of Automation, Chinese Academy of Sciences China
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
Jul 17, 2026Haoran Sun, Wentao Zhang, Junyang Hua +18Efficient VLA Model Inference Vision-Language-Action Models
JDT AI Infra · Peking University · Beihang University +2
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 Model Inference Vision-Language-Action Models
The University of Tokyo, Tokyo, Japan · TIER IV, Inc., Tokyo, Japan · Huawei
Reflex: Real-Time VLA Control through Streaming Inference
Jul 16, 2026Yuanchun Guo, Bingyan LiuFlow Matching KV Caching
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China.
Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference
Jul 14, 2026Zebin Yang, Qi Wang, Yunhe Wang +6Efficient VLA Model Inference Vision-Language-Action Models
Peking University · PrimeBot Research Institute · AIRS
Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference
Jul 14, 2026Yuzhou Wu, Yuxin Zheng, Muchun Niu +6Efficient VLA Model Inference Efficient VLA Models
1Tianji KernalMind co ltd · 2Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · 3Shanghai Jiao Tong University, Shanghai, China +2
Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
Jul 7, 2026Ryuji Oi, Hikari Otsuka, Kosuke Matsushima +4Efficient VLA Model Inference Vision-Language-Action Models
Institute of Science Tokyo
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Jul 2, 2026Ling Xu, Chuyu Han, Borui Li +6Efficient Neural Network Inference Efficient VLA Model Inference
Southeast University · Nanjing University · Microsoft Research +1
Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models
Jun 24, 2026Tiecheng Guo, Meng GuoRobotic Control Language-Conditioned Robot Manipulation
The authors are with the School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China.
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
Jun 22, 2026Lin Sun, Zhiwei Guan, Conglin Wang +7Efficient VLM Inference Efficient VLA Model Inference
JD.com, China · Yiwu Research Institute of Fudan University, China · Tianjin University, China
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
Jun 18, 2026Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18Model Compression Efficient VLA Model Inference
Center for AI Research, VinUniversity · VinRobotics · University of Arkansas +10
Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
Jun 17, 2026Navin Ranjan, Andreas SavakisMixed-Precision Quantization VLM Quantization
Rochester Institute of Technology Rochester, New York 14623, USA
Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models
Jun 13, 2026Shenhao Yan, Ge Wang, Qi Liu +7Efficient VLM Inference Efficient VLA Model Inference
Northeastern University · Ising AI · CUHK-Shenzhen
Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
Jun 13, 2026Dianqiao Lei, Lianlei ShanEfficient Inference Efficient VLA Model Inference
1Tsinghua University, Beijing, China.
RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation
Jun 12, 2026Xiangyu Huang, Zhenlin Hua, Han Zhou +2End-to-End Autonomous Driving Efficient VLM Inference
Carnegie Mellon University
vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
Jun 6, 2026Khanh D. Nguyen, Hung T. Ho, Chinh T. Nguyen +5AI Accelerator Inference Efficient VLM Inference
VinRobotics, Vietnam · Max Planck Research School for Intelligent Systems, Germany · University of Stuttgart, Germany +3
TBD-VLA: Temporal Block Diffusion Vision Language Action Model
Jun 5, 2026Sung-Wook Lee, Xuhui Kang, Yen-Ling KuoEfficient VLA Model Inference Efficient VLA Models
University of Virginia
RhinoVLA Technical Report
Jun 5, 2026Huixi Technology, :, Chen Zhang +13Efficient VLM Inference Efficient VLA Model Inference
Huixi Technology
Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural Manipulation
May 31, 2026Keith Truongcao, Christopher Nhu, Zijian An +3Efficient VLA Model Inference Robotic Manipulation
Department of Electrical Engineering, Drexel University, Philadelphia, USA
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
May 28, 2026Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9Efficient VLM Inference Efficient VLA Model Inference
1Zhejiang University · 2Cornell University · 3National University of Singapore +1
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
May 28, 2026Ye Li, Huanan Liu, Kangye Ji +7Efficient VLM Inference Efficient VLA Model Inference
Tsinghua University · University of Illinois at Urbana-Champaign
Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling
May 27, 2026Xinyu Wang, Mingze Li, Sicheng Lyu +6VLM Quantization Efficient VLA Model Inference
McGill University · Université de Montréal · Mila – Quebec AI Institute +2

Aug 4, 2026, cs.ROJ/K move · Enter open · S save

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

Weichen Xu, Zhenhua Liu, Lin Luo, Yaobo Liang+7

1Peking University · 2Microsoft Research Asia

Efficient VLA Model Inference Robotic Manipulation Vision-Language-Action Models RL for VLMs

Open paper AskPDF arXiv

Existing chunk-based Vision-Language-Action (VLA) models execute a fixed number of actions (i.e., execution horizon) before replanning, turning replanning into a task-agnostic periodic schedule that is independent of task progress. As a result, when no replanning boundary falls before a critical manipulation stage, it is executed from a stale chunk rather than a freshly replanned one. To address this limitation, we propose Bernoulli-Continuation Policy (BCP), a lightweight, plug-and-play framework for adaptive horizon execution that keeps the base VLA frozen. Given a fixed-length action chunk, its continuation head decomposes execution-horizon selection into a sequence of continue-or-replan decisions, which imposes an ordinal, prefix-sharing inductive bias over candidate horizons rather than treating them as independent classes. Since the optimal horizon for each chunk is not observable, we train this head with reinforcement learning from trajectory-level outcomes and introduce a Replanning-Efficiency Reward that jointly rewards task success and efficient VLA usage, discouraging the policy from collapsing to unnecessarily short horizons. On RoboTwin 2.0 with LingBot-VLA as the base policy, BCP improves the average success rate by +11.08% on 13 low-success tasks and from 89.88% to 93.94% (+4.06%) across all 50 tasks. Although trained only under the Clean setting, BCP generalizes to the Randomized setting, raising the average success rate by +4.06%. It also transfers to a different base policy

π_{0.5}

, achieving a better result on LIBERO (+1.7%) and, notably, on the harder LIBERO-PRO (+6.8%). On a real robot, BCP lifts success from 74% to 92% and from 44% to 84% on two manipulation tasks. Meanwhile, its negligible overhead, combined with higher success, makes BCP's overall runtime even lower than the fixed-horizon baselines.

Momentum

Related topics

Latest papers 104