2 citations · 5 across the 29 of their papers we have counts for
29 papers
ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents
Xingjian Wu, Xuhang Zhu, Xingchen Liu +6
As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish…
Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework
Tianen Shen, Zhengyu Li, Yutong Li +4
Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental sensing. Their core challenge…
Contrastive Reinforced Policy Optimization via Privileged Self-Distillation
Xingjian Wu, Junlin Liu, Xingchen Liu +6
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). Whil…
Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models
Xingjian Wu, Junkai Lu, Siyu Yan +4
Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre…
GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables
Zhengyu Li, Xiangfei Qiu, Yuhan Zhu +4
Exogenous variables offer valuable supplementary information for predicting future endogenous variables. Forecasting with exogenous variables needs to consider both past-to-future…
CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter
Hanyin Cheng, Xingjian Wu, Yang Shu +4
Most existing Time Series Foundation Models (TSFMs) use channel independent modeling and focus on capturing and generalizing temporal dependencies, while neglecting the correlation…
Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
Peng Chen, Siyuan Wang, Shiyan Hu +7
While existing time series foundation models primarily rely on large-scale unimodal pretraining, they lack complementary modalities to enhance time series understanding. Building m…
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
Junkai Lu, Peng Chen, Xingjian Wu +4
Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time serie…
ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies
Xingjian Wu, Xvyuan Liu, Junkai Lu +6
LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolv…
SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement
Xiangfei Qiu, Xvyuan Liu, Tianen Shen +4
Time series forecasting is important in many fields that require accurate predictions for decision-making. Patching techniques, commonly used and effective in time series modeling,…
Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting
Xiangfei Qiu, Kangjia Yan, Xvyuan Liu +2
Irregular multivariate time series forecasting (IMTSF) is challenging due to non-uniform sampling and variable asynchronicity. These irregularities violate the equidistant assumpti…
TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
Xingjian Wu, Junkai Lu, Zhengyu Li +5
Time series data widely exist in real-world cyber-physical systems. Though analyzing and interpreting them contributes to significant values, e.g, disaster prediction and financial…
FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
Xingjian Wu, Hanyin Cheng, Xiangfei Qiu +4
In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support versatile forecasting tasks via generative probabilisti…
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
Xiangfei Qiu, Xingjian Wu, Hanyin Cheng +4
Time series forecasting holds significant value in various domains such as economics, traffic, energy, and AIOps, as accurate predictions facilitate informed decision-making. Howev…
Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective
Xingjian Wu, Xiangfei Qiu, Hanyin Cheng +4
Time Series Forecasting has made significant progress with the help of Patching technique, which partitions time series into multiple patches to effectively retain contextual seman…
Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting
Xiangfei Qiu, Liu Yang, Xiangyu Xu +9
Time series forecasting occurs in a range of financial applications providing essential decision-making support to investors, regulatory institutions, and analysts. Unlike multivar…
ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting
Xvyuan Liu, Xiangfei Qiu, Hanyin Cheng +4
Irregular multivariate time series (IMTS) are prevalent in critical domains like healthcare and finance, where accurate forecasting is vital for proactive decision-making. However,…
Aurora: Towards Universal Generative Multimodal Time Series Forecasting
Xingjian Wu, Jianxin Jin, Wanghui Qiu +4
Cross-domain generalization is very important in Time Series Forecasting because similar historical information may lead to distinct future trends due to the domain-specific charac…
Task-Aware Mixture-of-Experts for Time Series Analysis
Xingjian Wu, Zhengyu Li, Hanyin Cheng +4
Time Series Analysis is widely used in various real-world applications such as weather forecasting, financial fraud detection, imputation for missing data in IoT systems, and class…
DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
Xiangfei Qiu, Yuhan Zhu, Zhengyu Li +3
Time series forecasting is essential in various domains. Compared to relying solely on endogenous variables (i.e., target variables), considering exogenous variables (i.e., covaria…
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
Xiangfei Qiu, Zhe Li, Wanghui Qiu +10
Time series anomaly detection (TSAD) plays an important role in many domains such as finance, transportation, and healthcare. With the ongoing instrumentation of reality, more time…
VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
Xingjian Wu, Xiangfei Qiu, Hongfan Gao +3
Probabilistic Time Series Forecasting (PTSF) plays a crucial role in decision-making across various fields, including economics, energy, and transportation. Most existing methods e…
Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
Xvyuan Liu, Xiangfei Qiu, Xingjian Wu +4
The forecasting of irregular multivariate time series (IMTS) is crucial in key areas such as healthcare, biomechanics, climate science, and astronomy. However, achieving accurate a…
A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective
Xiangfei Qiu, Hanyin Cheng, Xingjian Wu +5
Multivariate Time Series Forecasting (MTSF) plays a crucial role across diverse fields, ranging from economic, energy, to traffic. In recent years, deep learning has demonstrated o…