16 papers
TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
Yangze Li, Zhengyang Zhou, Qihe Huang +3
Long-term time series forecasting requires temporal dependency modeling that remains stable and generalizable under temporal distribution shifts. However, real-world time series ar…
AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecasting
Xing Xu, Xu Wang, Yudong Zhang +3
Air-quality forecasting models are commonly evaluated on regional, preprocessed, and normalized datasets, where missing observations are removed or artificially completed. Such pro…
PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting
Jiaming Ma, Qihe Huang, Haofeng Ma +6
While existing multivariate time series forecasting models have advanced significantly in modeling periodicity, they largely neglect the periodic heterogeneity common in real-world…
To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series
Jiaming Ma, Siyuan Mu, Ruilin Tang +6
The prevailing Direct Forecasting (DF) paradigm dominates Long-term Time Series Forecasting (LTSF) by forcing models to predict the entire future horizon in a single forward pass.…
A General ReLearner: Empowering Spatiotemporal Prediction by Re-learning Input-label Residual
Jiaming Ma, Binwu Wang, Pengkun Wang +3
Prevailing spatiotemporal prediction models typically operate under a forward (unidirectional) learning paradigm, in which models extract spatiotemporal features from historical ob…
TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization
Shichao Ma, Zhiyuan Ma, Ming Yang +8
Multi-turn tool-integrated reasoning enables Large Language Models (LLMs) to solve complex tasks through iterative information retrieval. However, current reinforcement learning (R…
Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models
Zhiqing Cui, Binwu Wang, Qingxiang Liu +4
Large language models (LLM) have emerged as a promising avenue for time series forecasting, offering the potential to integrate multimodal data. However, existing LLM-based approac…
DualGR: Generative Retrieval with Long and Short-Term Interests Modeling
Zhongchao Yi, Kai Feng, Xiaojian Ma +5
In large-scale industrial recommendation systems, retrieval must produce high-quality candidates from massive corpora under strict latency. Recently, Generative Retrieval (GR) has…
Talk2Image: A Multi-Agent System for Multi-Turn Image Generation and Editing
Shichao Ma, Yunhe Guo, Jiahao Su +3
Text-to-image generation tasks have driven remarkable advances in diverse media applications, yet most focus on single-turn scenarios and struggle with iterative, multi-turn creati…
QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting
Shichao Ma, Zhengyang Zhou, Qihe Huang +2
Accurate forecasting of sequential data streams is a cornerstone of modern Web services, supporting applications such as traffic management, user behavior modeling, and online anom…
MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning
Kuo Yang, Xingjie Yang, Linhui Yu +5
Large Language Model (LLM)-driven Multi-agent systems (Mas) have recently emerged as a powerful paradigm for tackling complex real-world tasks. However, existing Mas construction m…
SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
Jiayue Liu, Zhongchao Yi, Zhengyang Zhou +4
Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a s…
Soft causal learning for generalized molecule property prediction: An environment perspective
Limin Li, Kuo Yang, Wenjie Du +3
Learning on molecule graphs has become an increasingly important topic in AI for science, which takes full advantage of AI to facilitate scientific discovery. Existing solutions on…
Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
Zhongchao Yi, Zhengyang Zhou, Qihe Huang +4
Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distributi…
FairSTG: Countering performance heterogeneity via collaborative sample-level optimization
Gengyu Lin, Zhengyang Zhou, Qihe Huang +3
Spatiotemporal learning plays a crucial role in mobile computing techniques to empower smart cites. While existing research has made great efforts to achieve accurate predictions o…
ComS2T: A complementary spatiotemporal learning system for data-adaptive model evolution
Zhengyang Zhou, Qihe Huang, Binwu Wang +4
Spatiotemporal (ST) learning has become a crucial technique to enable smart cities and sustainable urban development. Current ST learning models capture the heterogeneity via vario…