ICLR2026刚放榜，先统计了一波rebuttal之前的论文，总结了其中时间序列(Time Series)高分的论文。如有疏漏，欢迎大家补充。

挑选原则：由于（广义）时空比较惨淡，我选择挑选均分要大于5的论文（不取等,即使有2，有8或者更高的分拉回来也算）

时空Topic:轨迹生成，城市智能体，时空图，地球观测，天气预报等等。

注：由于均未正式录用，就不再做详细总结和翻译，关键词直接采用openreview提供的关键词。

注：由于均未正式录用，就不再做详细总结和翻译，关键词直接采用openreview提供的关键词。

1. TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models 2. USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning Capabilities of LLMs as Urban Agents 3. A General Spatio-Temporal Backbone with Scalable Contextual Pattern Bank for Urban Continual Forecasting 4. SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control 5. UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction 6. Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective 7. A Novel Benchmark Framework for Neural Embeddings in Earth Observation 8. Being More Lightweight and Practical: Mini-sized Contrastive Learning Pre-trained Models for Fine-grained Traffic Tasks 9. ClimateAR: Multi-Scale Autoregressive Generative Modeling for Climate Forecasting 10. SPACeR: Self-Play Anchoring with Centralized Reference Models 11. DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning

🌟【紧跟前沿】“时空探索之旅”与你一起探索时空奥秘！🚀
欢迎大家关注时空探索之旅时空探索之旅

1 TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models

链接：https://openreview.net/forum?id=BDOldEjwCE

关键词：Flow matching, Human Trajectory, Generative modeling, Human mobility

分数：10, 4, 6, 6

信心：5, 3, 5, 4

均分：6.5

TL; DR：This paper proposed TrajFM, a flow-matching-based GPS trajectory generation model that overcomes scale, diversity, and efficiency limitations of diffusion approaches to enable nationwide, multi-scale, and multi-modal human mobility data generation.

2 USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning Capabilities of LLMs as Urban Agents

链接：https://openreview.net/forum?id=ETzBStUFJy

关键词：large language model, spatiotemporal reasoning, urban science

分数：6, 6, 4, 8

信心：4, 3, 4, 4

均分：6.0

TL; DR：A benchmark for evaluating the urban spatiotemporal reasoning abilities of LLMs.

3 A General Spatio-Temporal Backbone with Scalable Contextual Pattern Bank for Urban Continual Forecasting

链接：https://openreview.net/forum?id=LHSea6DI8U

关键词：general backbone, contextual pattern bank, continual spatio-temporal forecasting

分数：4, 8, 6

信心：3, 5, 4

均分：6.0

4 SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control

链接：https://openreview.net/forum?id=8soGuDwlxK

关键词：Reinforcement learning, traffic signal control, Monte Carlo tree search

分数：4, 4, 8, 6

信心：5, 4, 4, 5

均分：5.5

TL; DR：Discovering interpretable and deployable symbolic policies for traffic signal control

5 UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction

链接：https://openreview.net/forum?id=ckjNF94cIi

关键词：Spatio-Temporal Graph, Heterogeneous Graph, Dynamic Graph, Physics-Informed ML, Urban Microclimate

分数：4, 6, 6, 6

信心：4, 3, 3, 4

均分：5.5

6 Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective

链接：https://openreview.net/forum?id=b6Py2zy0fK

关键词：Neural operators, Spatio-temporal systems, Graph neural networks, Data mining

分数：6, 4, 6

信心：3, 3, 4

均分：5.33

7 A Novel Benchmark Framework for Neural Embeddings in Earth Observation

链接：https://openreview.net/forum?id=U3k7qLgGN8

关键词：neural embeddings, benchmark framework, spatio-temporal data, Earth observation

分数：2, 6, 8

信心：5, 4, 5

均分：5.33

TL; DR：a novel benchmarking pipeline for spatio-temporal neural embeddings

8 Being More Lightweight and Practical: Mini-sized Contrastive Learning Pre-trained Models for Fine-grained Traffic Tasks

链接：https://openreview.net/forum?id=ZMQAGxMmE2

关键词：Fine-grained traffic prediction, Spatio-temporal modeling, Lightweight models

分数：6, 4, 6

信心：4, 5, 4

均分：5.33

TL; DR：We propose a mini-sized pre-training model for fine-grained traffic. The model provides an efficient and accurate solution for fine-grained traffic with limited computational resources and data.

9 ClimateAR: Multi-Scale Autoregressive Generative Modeling for Climate Forecasting

链接：https://openreview.net/forum?id=MMcyzQUPqb

关键词：Weather and climate forecasting

分数：8, 4, 4

信心：4, 4, 4

均分：5.333333333333333

10 SPACeR: Self-Play Anchoring with Centralized Reference Models

链接：https://openreview.net/forum?id=Q5H3NCy18S

关键词：Multi-agent reinforcement learning, traffic simulation, autonomous vehicles, planning

分数：6, 4, 6

信心：3, 4, 4

均分：5.333333333333333

11 DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning

链接：https://openreview.net/forum?id=AcDx2tUZPb

关键词：traffic simulation, multi-agent imitation learning, generative adversarial imitation learning

分数：4, 4, 8

信心：4, 5, 4

均分：5.33

🌟【紧跟前沿】“时空探索之旅”与你一起探索时空奥秘！🚀
欢迎大家关注时空探索之旅时空探索之旅