As robots are expected to perform increasingly diverse tasks, they must understand not only low-level actions but also the higher-level structure that determines how a task should unfold. Existing vision-language-action (VLA) models struggle with this form of task-level reasoning. They either depend on prompt-based in-context decomposition, which is unstable and sensitive to linguistic variations, or end-to-end long-horizon training, which requires large-scale demonstrations and entangles task-level reasoning with low-level control. We present in-parameter structured task reasoning (iSTAR), a framework for enhancing VLA models via functional differentiation induced by in-parameter structural reasoning. Instead of treating VLAs as monolithic policies, iSTAR embeds task-level semantic structure directly into model parameters, enabling differentiated task-level inference without external planners or handcrafted prompt inputs. This injected structure takes the form of implicit dynamic scene-graph knowledge that captures object relations, subtask semantics, and task-level dependencies in parameter space. Across diverse manipulation benchmarks, iSTAR achieves more reliable task decompositions and higher success rates than both in-context and end-to-end VLA baselines, demonstrating the effectiveness of parameter-space structural reasoning for functional differentiation and improved generalization across task variations.
Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；A*STAR Institute of High Performance Computing (A*STAR IHPC)（新加坡A*STAR高性能计算研究所）；A*STAR Centre for Frontier AI Research (A*STAR CFAR)（新加坡A*STAR前沿人工智能研究中心）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；College of Design and Engineering, Nanyang Technological University（南洋理工大学设计与工程学院）；Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University（武汉大学测绘遥感信息工程国家重点实验室（LIESMARS））
What Matters in Building Vision-Language-Action Models for Generalist Robots
Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；ByteDance Research（字节跳动研究院）；CASIA MAIS-NLPR；Shanghai Jiao Tong University（上海交通大学）；National University of Singapore（新加坡国立大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）
