Feature-wise change detection and robust indoor positioning using RANSAC-like approach
专题命中 具身推理 :world model(abstract);分类 cs.LG
Comments 36 pages, 20 figures, 2 tables
视觉与机器人
机器人、具身智能、机器人学习、操作、导航和具身世界模型。
专题命中 具身推理 :world model(abstract);分类 cs.LG
Comments 36 pages, 20 figures, 2 tables
专题命中 具身推理 :world model(abstract);分类 cs.LG
专题命中 具身推理 :robotics(abstract);分类 cs.CV
专题命中 具身推理 :world model(abstract);分类 cs.AI
Comments 14 pages, 4 figures, accepted to EMNLP 2019
专题命中 具身推理 :navigation(abstract);分类 cs.CV
Comments Accepted to Women in Computer Vision (WiCV) Workshop at CVPR 2019
专题命中 具身推理 :robotics(abstract);分类 cs.CV
Comments BMVC 2019
专题命中 具身推理 :world model(abstract);分类 cs.LG
Comments To appear in NIPS 2016
专题命中 具身推理 :world model(abstract);分类 cs.RO
专题命中 具身推理 :world model(abstract);分类 cs.LG
Journal ref Neural Information Processing Systems (NeurIPS), 2018
专题命中 具身推理 :world model(abstract);分类 cs.LG
专题命中 具身推理 :world model(abstract);分类 cs.AI
Comments 12 pages, 5 figures, submitted for publications in IEEE Journals Interactive Vesion @ https://uicm-mas.github.io/
专题命中 具身推理 :robotics(abstract);分类 cs.CV
专题命中 具身推理 :world model(abstract);分类 cs.CV
Comments Accepted by IEEE Transactions on Image Processing, 2018
专题命中 具身推理 :robotics(abstract);分类 cs.CV
Comments Accepted in IJCV 2018
专题命中 具身推理 :navigation(abstract);分类 cs.CV
Comments Updates camera ready version. Accepted by CVPR 2017
专题命中 具身推理 :robotics(abstract);分类 cs.CV
专题命中 具身推理 :robotics(abstract);分类 cs.RO
专题命中 具身推理 :robotics(abstract);分类 cs.RO
专题命中 具身推理 :robotics(abstract);分类 cs.AI
Comments 22 pages, 6 figures, Under consideration for publication in TPLP
专题命中 具身推理 :world model(abstract);分类 cs.AI
专题命中 具身推理 :robotics(abstract);分类 cs.AI
Comments pages 13. accepted for publication at: LPNMR 2015 - Logic Programming and Nonmonotonic Reasoning, 13th International Conference, LPNMR 2015, LNAI Vol. 9345., Lexington, September 27-30, 2015. Proceedings., (editors: Francesco Calimeri, Giovambattista Ianni, Miroslaw Truszczynski)
专题命中 具身推理 :robotics(abstract);分类 cs.AI
Comments A short version appeared in KR-10. Several results have been rephrased and omitted proofs are given here. (Sanjiang Li. A Layered Graph Representation for Complex Regions, in Proceedings of the 12th International Conference on the Principles of Knowledge Representation and Reasoning (KR-10), pages 581-583, Toronto, Canada, May 9-13, 2010)
专题命中 具身推理 :world model(abstract);分类 cs.AI
Comments 10 pages
专题命中 具身推理 :world model(abstract);分类 cs.AI
Comments Appears in Proceedings of the Fourth Conference on Uncertainty in Artificial Intelligence (UAI1988)
专题命中 具身推理 :world model(abstract);分类 cs.AI
Comments Appears in Proceedings of the Eighth Conference on Uncertainty in Artificial Intelligence (UAI1992)
专题命中 具身推理 :robotics(abstract);分类 cs.RO
专题命中 具身推理 :world model(abstract);分类 cs.AI
Comments 15 pages, 3 highly compressible low-complexity drawings. Joint Invited Lecture for Algorithmic Learning Theory (ALT 2007) and Discovery Science (DS 2007), Sendai, Japan, 2007
从USD场景到知识图谱:基于LLM的零样本本体接地
机构 * Technical University of Berlin(柏林工业大学) ; Fraunhofer FOKUS(弗劳恩霍夫开放通信系统研究所)
专题命中 具身推理 :分类 cs.RO、cs.AI、cs.CV;robotics(comments)
AI总结 研究利用大语言模型(LLM)零样本地将3D场景对象自动映射到本体类别,无需训练,在厨房场景中达到90-96%准确率,并揭示语义线索是关键。
Comments Accepted to the IEEE ICRA 2026 International Joint Workshop on Ontologies, Semantic Maps and Autonomous Robotics Standardization (J-WOSMARS 2026), Vienna, 2026
BulletGen: 通过子弹时间生成提升4D重建
机构 * Meta Reality Labs(Meta 现实实验室)
专题命中 具身推理 :分类 cs.AI、cs.CV、cs.LG;world model(comments)
AI总结 BulletGen利用生成模型在Gaussian动态场景表示中校正错误并补全缺失信息,通过对扩散视频生成模型输出与4D重建在单个冻结子弹时间步骤的对齐,实现新颖视角合成和2D/3D跟踪任务的最先进结果。
Comments Accepted at CVPR 2026 Workshop "4D World Models: Bridging Generation and Reconstruction"
机构 * National University of Singapore(新加坡国立大学) ; Yale University(耶鲁大学)
专题命中 具身推理 :分类 cs.AI、cs.CV、cs.LG;world model(comments)
Comments ICML 2025 Workshop on Building Physically Plausible World Models (Best Paper), 32 pages, 17 figures