Vision-Language-Action (VLA) models integrate high-level reasoning with low-level action execution for end-to-end robotic control. However, most VLA models target static manipulation in unconstrained environments, overlooking spatial constraints and dynamic obstacles. Fine-tuning VLAs on obstacle-avoidance data is a straightforward solution, but collecting such data is costly, especially for dynamic scenarios, and may degrade their original task capabilities. To address these limitations, we propose VLA-Stem, a lightweight, reinforcement-learning-based safety mechanism for VLA systems. Without fine-tuning the underlying VLA policy, VLA-Stem converts its action chunks into motion references and uses trajectory-level guidance to preserve their spatial intent while allowing flexible motion and timing adjustments. Conditioned on these references, robot proprioception, and local obstacle information, the Stem policy adaptively modifies execution at inference time, preserving the original task intent while enabling responsive adaptation to spatial constraints and dynamic obstacles. For robust and sample-efficient training, we combine teacher-student distillation with curriculum learning. We evaluate VLA-Stem on reference following, static spatial constraints, and dynamic obstacle avoidance. Across six constrained simulation settings, VLA-Stem achieves 52.8% average collision-free task success versus 23.7% for the strongest safety baseline, while preserving base-policy performance in obstacle-free settings; real-world experiments further show consistent collision reductions under static and dynamic obstacles. These results demonstrate that VLA-Stem couples high-level VLA task intent with rapid, reflex-like responses to immediate physical risks, providing a brainstem-inspired mechanism for robust robot execution.
Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision
School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院);Zhejiang University(浙江大学);University of Electronic Science and Technology of China(电子科技大学);QuicRobot
Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Nanyang Technological University(南洋理工大学);School of Cyber Science and Engineering, Southeast University(东南大学网络空间安全学院);Purple Mountain Laboratories(紫金山实验室)
Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院);EvoMind Tech(EvoMind科技);IAAR-Shanghai(IAAR-上海);SII;Carnegie Mellon University(卡内基梅隆大学);University of Cambridge(剑桥大学);Nanyang Technological University(南洋理工大学)
CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models
University of Science and Technology of China (USTC)(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation
Meituan(美团);Beijing Institute of Technology(北京理工大学);Beihang University(北京航空航天大学);State Key Lab of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS(中国科学院自动化研究所多模态人工智能系统国家重点实验室);China University of Mining and Technology (Beijing)(中国矿业大学(北京))
PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies
Jilin University(吉林大学);Astribot;Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));The Hong Kong Polytechnic University(香港理工大学);The University of Tokyo(东京大学)
eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing
Southern University of Science and Technology(南方科技大学);Beijing Zhongguancun Academy(北京中关村学院);Samsung Robotics eXperience(三星机器人体验中心);Wuhan University(武汉大学);Sun Yat-sen University(中山大学)
Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);the School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution
Beijing Forestry University(北京林业大学);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Beijing Innovation Center of Humanoid Robotics(北京人形机器人创新中心)
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
Beijing University of Posts and Telecommunications(北京邮电大学);Westlake University(西湖大学);Zhejiang University(浙江大学);OpenHelix Team(OpenHelix团队);State Key Laboratory of Networking and Switching Technology(网络与交换技术国家重点实验室);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
State Key Lab of Processors, Institute of Computing Technology, CAS(处理器国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Nanjing University(南京大学);Dexmal