时空大数据智能与计算实验室 Big Data AI & Spatial-Temporal Computing Lab (BAIST)

2026-08-27

近日，实验室研究成果 “DSTA4D: Content-aware Adaptive Decoupling for 4D Point Cloud Video Understanding” 被国际期刊 Pattern Recognition 接收。Recently, our research work “DSTA4D: Content-aware Adaptive Decoupling for 4D Point Cloud Video Understanding” was accepted by the international journal Pattern Recognition.

2026-08-26

近日，实验室研究成果 SHAPE: Spatial Hyperbolic-Embedding Augmented Pretraining for Estimated Time of Arrival on Obfuscated Trajectories 被ICDM 2026接收。Recently, our research work "SHAPE: Spatial Hyperbolic-Embedding Augmented Pretraining for Estimated Time of Arrival on Obfuscated Trajectories" have been accepted by ICDM 2026.

2026-08-21

近日，周逊教授、黄锐同学和鲍侃宇同学参加第十四届 CCF 大数据学术会议（CCF BigData）。Recently, Professor Xun Zhou, PhD student Rui Huang, and PhD student Kanyu Bao attended the 14th CCF Conference on Big Data (CCF BigData).

2026-08-09

近日，周逊教授与肖涵彬同学赴韩国济州岛参加 KDD 2026。Recently, Professor Xun Zhou and Master’s student Hanbin Xiao attended KDD 2026 in Jeju, South Korea.

2026-07-10

近日，实验室两项研究成果 RoPOI 以及 Seeing without Cameras: Interpretable Wireless Fusion for 3D Human Pose Estimation 被 ACM MM 2026 接收。Recently, two research works from our lab, RoPOI and “Seeing without Cameras: Interpretable Wireless Fusion for 3D Human Pose Estimation,” have been accepted by ACM MM 2026.

2026-06-17

近日，实验室2023级硕士研究生周子瑞的毕业论文 《面向城市时空预测的基础模型研究》 被评为 2026年优秀毕业论文，周逊教授获评优秀毕业论文指导教师。Recently, the master’s thesis of Zirui Zhou, a 2023 cohort master’s student in our lab, titled “Foundation Models for Urban Spatiotemporal Forecasting,” was selected as an Outstanding Thesis of 2026. His supervisor, Professor Xun Zhou, was also recognized as an Outstanding Thesis Supervisor.

2026-05-20

近日，实验室两项研究成果 HURST 和 RePatch 被 KDD 2026 接收。Recently, two research works from our lab, HURST and RePatch, were accepted by KDD 2026.

2026-03-01

近日，实验室两项研究成果 “Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization” 和 “SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC” 被 ICLR 2026 接收。Recently, two research papers from our lab, “Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization” and “SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC,” were accepted by ICLR 2026.

2026-01-20

近日，实验室参与申报的广东省重点领域研发计划项目 “面向车路云一体化的高性能通感算关键技术与设备研发” 获批立项。Recently, the project “Research and Development of Key Technologies and Equipment for High-Performance Integrated Communication, Sensing, and Computing in Vehicle-Road-Cloud Integration”, with participation from our lab, was officially approved under the Guangdong Provincial Key-Area R&D Program.

2026-01-01

近日，实验室作为合作单位参与的深圳市科技创新局重点产业研发项目 “面向自主式交通指挥与管控的多模态具身智能关键技术研发” 正式获批立项，实验室负责人周逊教授担任项目高校负责人。Recently, the project “Research and Development of Key Multimodal Embodied Intelligence Technologies for Autonomous Traffic Command and Control”, with our lab serving as a collaborating institution, was officially approved under the Key Industrial R&D Program of the Shenzhen Science, Technology and Innovation Bureau. Professor Xun Zhou, head of our lab, serves as the university lead for the project.

2025-12-12

应周逊教授邀请，京东集团副总裁、首席数据科学家郑宇教授在哈尔滨工业大学（深圳）作题为“时空AI：人工智能进入物理世界的基础理论和关键技术”的学术报告。At the invitation of Professor Xun Zhou, Professor Yu Zheng, Vice President and Chief Data Scientist of JD Group, delivered an academic talk at Harbin Institute of Technology, Shenzhen, titled “Spatio-Temporal AI: Fundamental Theories and Key Technologies for Bringing AI into the Physical World.”