Enabling robots to perform precise and generalized manipulation in unstructured environments remains a fundamental challenge in embodied AI. While Vision-Language Models (VLMs) have demonstrated remarkable capabilities in semantic reasoning and task planning, a significant gap persists between their high-level understanding and the precise physical execution required for real-world manipulation. To bridge this "semantic-to-physical" gap, we introduce GRACE, a novel framework that grounds VLM-based reasoning through executable analytic concepts (EAC)-mathematically defined blueprints that encode object affordances, geometric constraints, and semantics of manipulation. Our approach integrates a structured policy scaffolding pipeline that turn natural language instructions and visual information into an instantiated EAC, from which we derive grasp poses, force directions and plan physically feasible motion trajectory for robot execution. GRACE thus provides a unified and interpretable interface between high-level instruction understanding and low-level robot control, effectively enabling precise and generalizable manipulation through semantic-physical grounding. Extensive experiments demonstrate that GRACE achieves strong zero-shot generalization across a variety of articulated objects in both simulated and real-world environments, without requiring task-specific training.
AntiGrounding: Executable Robot Trajectories as Visual Prompts for VLM-Guided Manipulation
School of Software Engineering, South China University of Technology(软件工程学院,华南理工大学);School of Future Technology, South China University of Technology(未来技术学院,华南理工大学);Shien-Ming Wu School of Intelligent Engineering, South China University of Technology(智能工程学院,华南理工大学)
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
Department of Electronics;Information \ 'an Jiaotong University Xi'an China;School of Information;Communications Engineering \ 'an Jiaotong University Xi'an China;School of Mathematics;Statistics \ 'an Jiaotong University Xi'an China;Information \ 'an Jiaotong University;Communications Engineering \ 'an Jiaotong University;Statistics \ 'an Jiaotong University
When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Glasgow(格拉斯哥大学);Boston University(波士顿大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Work Zones challenge VLM Trajectory Planning: Toward Mitigation and Robust Autonomous Driving
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Northwest A&F University(西北农林科技大学);Nanyang Technological University(南洋理工大学);Jinan University(济南大学)
VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning
NLPR&MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室与多模态人工智能系统实验室);School of Advanced Interdisciplinary Science, University of Chinese Academy of Sciences(中国科学院大学前沿交叉科学学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Zhongguancun Academy(中关村学院)
VLMPlanner: Integrating Visual Language Models with Motion Planning
University of Science and Technology of China(科学技术大学);University of Adelaide(阿德莱德大学);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)
CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution
City University of Hong Kong(香港城市大学);Soochow University(苏州大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Honhai Research Institute(鸿海研究院)
Octopus: Embodied Vision-Language Programmer from Environmental Feedback
S-Lab, Nanyang Technological University(新加坡南洋理工大学S-Lab);Shanghai AI Laboratory(上海人工智能实验室);Tsinghua University(清华大学);BUPT(北京邮电大学);XJTU(西安交通大学);Hong Kong Baptist University(香港浸会大学)
Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
Duncan of Jordanstone College of Art & Design (DJCAD), University of Dundee(邓迪大学邓迪艺术与设计学院(DJCAD));Guangzhou Institute of Science and Technology (GZIST)(广州科学技术研究院);Faculty of Arts, Xiamen University(厦门大学艺术学院);University of Birmingham(伯明翰大学)
ViCoR: Reliable Molecular Structure Extraction via Spatially Aligned Verification and Executable Revision
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);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
Fondazione Bruno Kessler(布鲁诺·科塞拉基金会);Department of Computer Science, Aalto University(艾尔沃斯大学计算机科学系);Department of Mathematics, Università degli Studi di Padova(帕多瓦大学数学系)
V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks
Department of Computer Science and Technology, University of Cambridge, Cambridge, England.(计算机科学与技术系,剑桥大学,剑桥,英格兰);Shanghai Jiao Tong University, Shanghai, China(上海交通大学,上海,中国);Wuhan University, Wuhan, Hubei, China(武汉大学,武汉,湖北,中国)
Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents
Qwen Large Model Application Team, Alibaba(阿里云大模型应用团队);Alibaba Zhejiang University(阿里巴巴浙江大学);University of Waterloo(多伦多大学);Vector Institute(向量研究所);Nanjing University(南京大学);Binjiang Institute of Zhejiang University(浙江大学滨江学院)
How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
University of Aberdeen(阿伯丁大学);International Institute of Information Technology Hyderabad(海德拉巴国际信息技术学院);University of Technology Nuremberg(纽伦堡工业大学);University of Southern California(南加利福尼亚大学)
Cross-Modal Instructions for Robot Motion Generation
College of Connected Computing, Vanderbilt University(连接计算学院,范德比尔特大学);Robotics Institute, Carnegie Mellon University(机器人研究所,卡内基梅隆大学);School of Computer Science, The University of Sydney(计算机科学学院,悉尼大学)
FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models
Nanyang Technological University(南洋理工大学);Centre for Frontier AI Research, A*STAR(A*STAR前沿人工智能研究中心);Allen Institute for AI(艾伦人工智能研究所);University of Washington(华盛顿大学)
City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));Zhejiang University(浙江大学);Fudan University(复旦大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Terminus Technologies Co., Ltd.;Pengcheng Laboratory(鹏城实验室)
PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Beijing Academy of Artificial Intelligence (BAAI)(北京人工智能研究院);Peking University(北京大学);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)