AAAI 2026 | 时空数据(Spatial-temporal)论文总结[下]（自动驾驶，天气预报，城市科学，POI推荐等）

时空探索之旅

发布于 2026-03-10 14:47:11

850

文章被收录于专栏：时空探索之旅时空探索之旅

AAAI 2026将在2026年1月20日到1月27日于新加坡（Singapore）举行。AAAI 2026会议主会共有23, 680篇论文投稿，其中4, 167 篇被接收，接收率为17.6%。

本文总结了2026 AAAI 上有关时空数据（Spatial-Temporal）相关论文。如有疏漏，欢迎大家补充。

时空数据Topic：时空预测，天气预报，城市区域表示，轨迹表示学习，相似度计算，轨迹预测，自动驾驶，POI推荐等。总计46篇，本文涉及22篇。

注：由于论文数目较多，分为上下篇，此为下篇，主要涵盖自动驾驶（路径规划，交通模拟，地图生成等），天气预报，城市区域表示学习，POI推荐等的文章。

25. DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning26. DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving27. Autonomous Vehicle Path Planning by Searching with Differentiable Simulation28. DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion29. Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving30. Transferring Causal Driving Patterns for Traffic Simulation with Diffusion-Based Distillation31. Diverse Human Driving Vehicle Simulation in Background Traffic for Autonomous Driving Tests32. Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs34. SynWeather: Weather Observation Data Synthesis Across Multiple Regions and Variables via a General Diffusion Transformer35. Tree-Based Stochastic Optimization for Solving Large-Scale Urban Network Security Games36. Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing37. MTP: Exploring Multimodal Urban Traffic Profiling with Spectrum Fusion and Modality Augmentation38. Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision39. Comprehensive Urban Region Representation Learning via Multi-View Joint Learning and Contrastive Learning40. Exploiting Pre-trained Language Model for Cross-city Urban Flow Prediction Guided by Information-theoretic Analysis41. Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization42. Meta Dynamic Graph for Traffic Flow Prediction43. TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation44. Multifaceted Scenario-Aware Hypergraph Learning for Next POI Recommendation45. Task-Aware Meta-Learning on Heterogeneous Knowledge Graph for POI Recommendation46. LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation

25 DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning

链接：https://arxiv.org/abs/2506.06659

作者：Wenhao Yao; Zhenxin Li; Shiyi Lan; Zi Wang; Xinglong Sun; Jose M. Alvarez; Zuxuan Wu

关键词：轨迹选择，自动驾驶

26 DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving

链接：https://arxiv.org/abs/2511.17150

作者：Liuhan Yin; Runkun Ju; Guodong Guo; Erkang Cheng

关键词：轨迹预测，自动驾驶

27 Autonomous Vehicle Path Planning by Searching with Differentiable Simulation

链接：https://arxiv.org/abs/2511.11043

作者：Asen Nachkov; Jan-Nico Zaech; Danda Pani Paudel; Xi Wang; Luc van Gool

关键词：路径规划，自动驾驶，微分模拟

28 DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion

作者：Chenxu Han; Sean Bin Yang; Jilin Hu

关键词：地图匹配，稀疏轨迹，扩散模型

29 Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving

链接：https://arxiv.org/abs/2509.22756

作者：Shiyi Liang; Xinyuan Chang; Changjie Wu; Huiyuan Yan; Yifan Bai; Xinran Liu; Hang Zhang; Yujian Yuan; Shuang Zeng; Mu Xu; Xing Wei

关键词：地图生成

30 Transferring Causal Driving Patterns for Traffic Simulation with Diffusion-Based Distillation

作者：Yuhang Chen; Jie Sun; Jialin Fan; Jian Sun

关键词：交通模拟，蒸馏，因果

31 Diverse Human Driving Vehicle Simulation in Background Traffic for Autonomous Driving Tests

链接：https://arxiv.org/abs/2508.16962v1

作者：Wendi Li; Hao Wu; Han Gao; Bing Mao; Fengyuan Xu; Sheng Zhong

关键词：交通生成，LLM

32 Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs

作者：Yuxuan Liu; Wenchao Xu; Haozhao Wang; Zhiming He; Zhaofeng Shi; Chongyang Xu; Peichao Wang; Boyuan Zhang

关键词：动态时空图，因果，联邦学习

33 A Domain-specific Heuristic for PDDL+-based Traffic Signal Optimisation

作者：Francesco Doria; Francesco Percassi; Marco Maratea; Mauro Vallati

关键词：交通信号优化，启发式

34 SynWeather: Weather Observation Data Synthesis Across Multiple Regions and Variables via a General Diffusion Transformer

链接：https://arxiv.org/abs/2511.08291

作者：Kaiyi Xu; Junchao Gong; Zhiwang Zhou; Zhangrui Li; Yuandong Pu; Yihao Liu; Ben Fei; Fenghua Ling; Wenlong Zhang; LEI BAI

关键词：气象数据合成，DiT

35 Tree-Based Stochastic Optimization for Solving Large-Scale Urban Network Security Games

链接：https://arxiv.org/abs/2511.10072

作者：Shuxin Zhuang; Linjian Meng; Shuxin Li; Minming Li; Youzhi Zhang

关键词：城市网络安全博弈

36 Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing

链接：https://arxiv.org/abs/2408.16027

作者：Hao Du; Wenbin Liu; Ziyu Sun; Haoyang Su; En Wang; Yuanbo Xu

关键词：稀疏移动群智感知

37 MTP: Exploring Multimodal Urban Traffic Profiling with Spectrum Fusion and Modality Augmentation

链接：https://arxiv.org/abs/2511.10218

作者：Haolong Xiang; Peisi Wang; Xiaolong Xu; Kun Yi; Xuyun Zhang; Quan Z. Sheng; Amin Beheshti; Wei Fan

关键词：多模态城市交通分析

38 Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision

链接：https://arxiv.org/abs/2511.07062

作者：Yimei Zhang; Guojiang Shen; Kaili Ning; Tongwei Ren; Xuebo Qiu; Mengmeng Wang; Xiangjie Kong

关键词：城市区域表示学习

39 Comprehensive Urban Region Representation Learning via Multi-View Joint Learning and Contrastive Learning

作者：Yingde Lin; Yuanbo Xu; Lu Jiang; Pengyang Wang

关键词：城市区域表示学习，对比学习

40 Exploiting Pre-trained Language Model for Cross-city Urban Flow Prediction Guided by Information-theoretic Analysis

作者：Qiang Zhou; Xudong Tong; Yuting Liu; ChuanXing Liu; Jingjing Gu

关键词：跨城市流量预测，预训练语言模型

41 Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization

链接：https://arxiv.org/abs/2511.07098

作者：Yuanshao Zhu; Xiangyu Zhao; Zijian Zhang; Xuetao Wei; James Jianqiao Yu

关键词：细粒度城市流量推理，轻量化

42 Meta Dynamic Graph for Traffic Flow Prediction

作者：Yiqing Zou; Hanning Yuan; Qianyu Yang; Ziqiang Yuan; Shuliang Wang; Sijie Ruan

关键词：交通预测，动态图

43 TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation

链接：https://arxiv.org/abs/2511.06405

作者：Dongsheng Wang; Shen Gao; Chengrui Huang; Yuxi Huang; Ruixiang Feng; Shuo Shang

关键词：POL推荐,LLM

44 Multifaceted Scenario-Aware Hypergraph Learning for Next POI Recommendation

作者：Yuxi Lin; Yongkang Li; Jie Xing; Zipei Fan

关键词：POI推荐，超图

45 Task-Aware Meta-Learning on Heterogeneous Knowledge Graph for POI Recommendation

作者：Jingyuan Wang; Zhichun Wang; Tong Lu; Yiming Guan

关键词：POI推荐，异质知识图谱

46 LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation

作者：Hao Jiang; Guoquan Wang; Donglin Zhou; Sheng Yu; Yang Zeng; Wencong Zeng; Kun Gai; Guorui Zhou

关键词：本地生活推荐，地理语义tokenize，LLM