Frozen Vision-Language-Action (VLA) policies cannot incorporate previously encountered failures without updating the underlying model. We present retrieval-triggered projection correction (RTPC), an auditable external-memory wrapper for frozen OpenVLA policies that retrieves stress-collected local-depth records and applies translation-only projection correction while keeping rotation and gripper commands unchanged. RTPC is evaluated on CALVIN single-task manipulation using primary and independent replication cohorts. In the primary evaluation, RTPC reduced a depth-based near-collision or stall proxy event rate without changing task-success count. However, this reduction was not reproduced in the independent replication, and retrieved correction directions were not distinguishable from random same-family directions. Analysis identifies endpoint coupling, batch sensitivity, and the lack of a trigger-matched memory-free baseline as limitations for attributing effects to retrieval-based correction. These findings do not establish physical safety improvement or memory-specific benefits, but provide an empirical evaluation and failure analysis of retrieval-conditioned intervention for frozen VLA policies.
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
School of Computer Science, Wuhan University(武汉大学计算机科学学院);D-Robotics(D-机器人公司);HUST(华中科技大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
School of Computer Science, Peking University, Beijing, China(北京大学计算机科学学院);School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China(中国地质大学(武汉)计算机科学学院)
VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China(南方科技大学电子与电气工程系,深圳,中国);Zhongguancun Academy, Beijing, China(中关村学院,北京,中国);National Cybersecurity Academy, Wuhan University, Wuhan, China(武汉大学国家网络安全学院,武汉,中国)
Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
Stanford University(斯坦福大学);Technical University of Munich(慕尼黑技术大学);University of Washington(华盛顿大学);Allen Institute for Artificial Intelligence(人工智能研究院)
RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
School of Computer Science, Peking University, Beijing, China(北京大学计算机科学学院);School of Computer Science, South China University of Technology, Guangzhou, China(华南理工大学计算机科学学院);School of Artificial Intelligence, Beijing Normal University, Beijing, China(北京师范大学人工智能学院);School of EECS, Peking University, Beijing, China(北京大学电子工程与科学学院)
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences(重庆绿色智能技术研究院,中国科学院);Chongqing School, University of Chinese Academy of Sciences(重庆学校,中国科学院大学);Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland(奥卢大学信息科技与电气工程学院,芬兰)
UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models
Harbin Institute of Technology(哈尔滨工业大学);Great Bay University(大湾区大学);Shanghai Jiao Tong University(上海交通大学);Fudan University(复旦大学);Nanjing University(南京大学);Daimon Robotics
REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control
National University of Singapore(新加坡国立大学);InfRec;Cardinal AI Lab(Cardinal AI实验室);University of California, Berkeley(加利福尼亚大学伯克利分校);The University of Tokyo(东京大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Hong Kong University of Science and Technology(香港科技大学)
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Huazhong University of Science and Technology(华中科技大学);Zhongguancun Academy(中关村学院);DeepCybo;Harbin Institute of Technology(哈尔滨工业大学);Beihang University(北京航空航天大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Zhengzhou University(郑州大学);Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院)
A Vision-Language-Action Model for Adaptive Ultrasound-Guided Needle Insertion and Needle Tracking
Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong(香港中文大学机械与自动化工程系);Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科学与技术大学计算机科学与工程系);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Department of Mechanical and Automation Engineering, T Stone Robotics Institute, Shun Hing Institute of Advanced Engineering, Multi-Scale Medical Robotics Center, and Institute of Medical Intelligence and XR, The Chinese University of Hong Kong(香港中文大学机械与自动化工程系、T Stone机器人研究所、Shun Hing先进工程研究所、多尺度医疗机器人中心以及医学智能与XR研究所)
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);State Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室);Alibaba DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Tsinghua University(清华大学);University of Technology Sydney(悉尼科技大学);University of Liverpool(利物浦大学)
RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control
The Hong Kong University of Science and Technology(香港科技大学);The Chinese University of Hong Kong(香港中文大学);SmartMore(思谋科技);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Shenzhen Loop Area Institute(深圳河套学院)
MorphAct: Robot Policies Morphing with the Worlds They Act In
University of Science and Technology of China(中国科学技术大学);School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);National University of Singapore(新加坡国立大学);Nanyang Technological University(南洋理工大学);Tongji University(同济大学);Shenzhen Technology University(深圳技术大学)