2 citations · 2 across the 17 of their papers we have counts for
18 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…
DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
Xucong Wang, Zhe Zhao, Liheng Yu +3
Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides…
ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
Xucong Wang, Ziyu Ma, Yong Wang +5
Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods of…
APPO: Agentic Procedural Policy Optimization
Xucong Wang, Ziyu Ma, Yong Wang +5
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing metho…
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Xucong Wang, Ziyu Ma, Shidong Yang +4
Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static tra…
DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification
Pengkun Wang, Weijia Cao, Ning Wang +1
Hyperspectral image (HSI) classification requires reliable pixel-relation modeling under spectral variability, mixed pixels, and heterogeneous boundaries. Existing graph-based HSI…
FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models
Xucong Wang, Pengkun Wang, Zhe Zhao +3
Multi-Label Recognition (MLR) based on Vision-Language Models (VLMs) aims to leverage their pre-trained knowledge to better adapt complex recognition scenarios, thereby enhancing m…
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…
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
Liheng Yu, Zhe Zhao, Yuxuan Wang +4
Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be fo…
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…
Rethinking Crystal Symmetry Prediction: A Decoupled Perspective
Liheng Yu, Zhe Zhao, Xucong Wang +2
Efficiently and accurately determining the symmetry is a crucial step in the structural analysis of crystalline materials. Existing methods usually mindlessly apply deep learning m…
Spatiotemporal Causal Decoupling Model for Air Quality Forecasting
Jiaming Ma, Guanjun Wang, Sheng Huang +4
Due to the profound impact of air pollution on human health, livelihoods, and economic development, air quality forecasting is of paramount significance. Initially, we employ the c…
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…
From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
Zhe Zhao, Haibin Wen, Pengkun Wang +8
Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization. However, current methods such as EoH and FunSearch mainly rely on pre…
A Powder Diffraction-AI Solution for Crystalline Structure
Di Wu, Pengkun Wang, Shiming Zhou +8
Determining the atomic-level structure of crystalline solids is critically important across a wide array of scientific disciplines. The challenges associated with obtaining samples…
Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
Zhe Zhao, Pengkun Wang, Xu Wang +5
Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on desi…
Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
Xu Wang, Pengfei Gu, Pengkun Wang +4
Spatiotemporal learning, which aims at extracting spatiotemporal correlations from the collected spatiotemporal data, is a research hotspot in recent years. And considering the inh…