Research & Publications
Selected Conference Papers
- Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment. X Chu, Z Zhang, T Jia, Y Jin. NeurIPS 2025
- MODEL SHAPLEY: Find Your Ideal Parameter Player via One Gradient Backpropagation. X Chu, X Jiang, R Qiu, J Gao, J Zhao. NeurIPS 2025
- Mechanism Design for LLM Fine-tuning with Multiple Reward Models. Haoran Sun, Yurong Chen, Siwei Wang, Wei Chen, Xiaotie Deng, Xu Chu. NeurIPS 2025
- Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation. R Qiu, X Jiang, Y Fang, H Lai, H Miao, X Chu, J Zhao, Y Wang. ICML 2025
- Geoedit: Geometric knowledge editing for large language models. Y Feng, LM Zhan, Z Lu, Y Xu, X Chu, Y Wang, J Cao, PS Yu, XM Wu. EMNLP 2025
- 3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection. H Ding, Y Fang, R Zhu, X Jiang, J Zhang, Y Xu, W Liao, X Chu, J Zhao, .... EMNLP 2025
- AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning. Y Feng, J Li, X Dong, P Xu, X Zhou, Y Zhang, Z Lu, Y Wang, A Zhao, .... EMNLP 2025
- TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems. X Jiang, Y Fang, R Qiu, H Zhang, Y Xu, H Chen, W Zhang, R Zhang, .... ACL 2025
- Parenting: Optimizing knowledge selection of retrieval-augmented language models with parameter decoupling and tailored tuning. Y Xu, R Zhang, X Jiang, Y Feng, Y Xiao, X Ma, R Zhu, X Chu, J Zhao, .... ACL 2025
- Hykge: A hypothesis knowledge graph enhanced rag framework for accurate and reliable medical llms responses. X Jiang, R Zhang, Y Xu, R Qiu, Y Fang, Z Wang, J Tang, H Ding, X Chu, .... ACL 2025
- Recurrent knowledge identification and fusion for language model continual learning. Y Feng, X Wang, Z Lu, S Fu, G Shi, Y Xu, Y Wang, PS Yu, X Chu, XM Wu. ACL 2025
- Knowpo: Knowledge-aware preference optimization for controllable knowledge selection in retrieval-augmented language models. R Zhang, Y Xu, Y Xiao, R Zhu, X Jiang, X Chu, J Zhao, Y Wang. AAAI 2025
- DearLLM: Enhancing Personalized Healthcare via Large Language Models-Deduced Feature Correlations. Y Xu, X Jiang, X Chu, R Qiu, Y Feng, H Ding, J Zhao, Y Wang, B Xie. AAAI 2025
- Learnable prompt as pseudo-imputation: Rethinking the necessity of traditional ehr data imputation in downstream clinical prediction. W Liao, Y Zhu, Z Zhang, Y Wang, Z Wang, X Chu, Y Wang, L Ma. KDD 2025
- Adaptive activation steering: A tuning-free llm truthfulness improvement method for diverse hallucinations categories. T Wang, X Jiao, Y Zhu, Z Chen, Y He, X Chu, J Gao, Y Wang, L Ma. WWW 2025
- Game theory meets large language models: A systematic survey. H Sun, Y Wu, Y Cheng, X Chu. IJCAI 2025 Survey track
- DRESSing up LLM: Efficient stylized question-answering via style subspace editing. X Ma, Y Xu, Y Lin, T Wang, X Chu, X Gao, J Zhao, Y Wang. ICLR 2025
- TPO: Aligning large language models with multi-branch & multi-step preference trees. W Liao, X Chu, Y Wang. ICLR 2025
- Ragraph: A general retrieval-augmented graph learning framework. X Jiang, R Qiu, Y Xu, Y Zhu, R Zhang, Y Fang, C Xu, J Zhao, Y Wang. NeurIPS 2024
- Smart: Towards pre-trained missing-aware model for patient health status prediction. Z Yu, C Xu, Y Jin, Y Wang, J Zhao. NeurIPS 2024
- Graph interpolation via fast Fused-Gromovization. X Ma, X Chu, Y Wang, Y Lin, J Zhao, L Ma, W Zhu. NeurIPS 2024
- Parameter efficient quasi-orthogonal fine-tuning via givens rotation. X Ma, X Chu, Z Yang, Y Lin, X Gao, J Zhao. ICML 2024
- Disentangled continual graph neural architecture search with invariant modular supernet. Z Zhang, X Wang, Y Qin, H Chen, Z Zhang, X Chu, W Zhu. ICML 2024
- Combating label sparsity in short text topic modeling via nearest neighbor augmentation. Y Lin, X Ma, X Gao, R Li, Y Wang, X Chu. ACL Findings 2024
- Tasl: Continual dialog state tracking via task skill localization and consolidation. Y Feng, X Chu, Y Xu, G Shi, B Liu, XM Wu. ACL 2024
- Enhancing topic interpretability for neural topic modeling through topic-wise contrastive learning. X Gao, Y Lin, R Li, Y Wang, X Chu, X Ma, H Yu. ICDE 2024
- Temporal domain generalization via learning instance-level evolving patterns. Y Jin, Z Yang, X Chu, L Ma. IJCAI 2024
- Protomix: Augmenting health status representation learning via prototype-based mixup. Y Xu, X Jiang, X Chu, Y Xiao, C Zhang, H Ding, J Zhao, Y Wang, B Xie. KDD 2024
- Fused gromov-wasserstein graph mixup for graph-level classifications. X Ma, X Chu, Y Wang, Y Lin, J Zhao, L Ma, W Zhu. NeurIPS 2023
- Wasserstein Barycenter Matching for Graph Size Generalization of Message Passing Neural Networks. X Chu, Y Jin, X Wang, S Zhang, Y Wang, W Zhu, H Mei. ICML 2023
- Enhancing neural topic model with multi-level supervisions from seed words. Y Lin, X Gao, X Chu, Y Wang, J Zhao, C Chen. ACL 2023
- Seqcare: Sequential training with external medical knowledge graph for diagnosis prediction in healthcare data. Y Xu, X Chu, K Yang, Z Wang, P Zou, H Ding, J Zhao, Y Wang, B Xie. WWW 2023
- Improving ar of meta-learning with inverted regularization at inner-level. L Wang, S Zhou, S Zhang, X Chu, H Chang, W Zhu. CVPR 2023
- Positive Sample Augmentation with Graph Mixup for DDI Prediction. H Yu, X Ma, X Chu, Y Wang, R Wu, Q Zhou. MedAI 2023
- DNA: Domain generalization with diversified neural averaging. X Chu, Y Jin, W Zhu, Y Wang, X Wang, S Zhang, H Mei. ICML 2022
- M3care: Learning with missing modalities in multimodal healthcare data. C Zhang, X Chu, L Ma, Y Zhu, Y Wang, J Wang, J Zhao. KDD 2022
- Domain generalization through the lens of angular invariance. Y Jin, X Chu, Y Wang, W Zhu. IJCAI 2022
- Enhancing robust text classification via category description. X Gao, Z Zhu, X Chu, Y Wang, W Ruan, J Zhao. ICDM 2022
- Distance Metric Learning with Joint Representation Diversification. X Chu, Y Lin, Y Wang, X Wang, H Yu, X Gao, Q Tong. ICML 2020
- Neighbor profile: Bagging nearest neighbors for unsupervised time series mining. Y He, X Chu, Y Wang. ICDE 2020
- Set-sequence-graph: A multi-view approach towards exploiting reviews for recommendation. J Gao, Y Lin, Y Wang, X Wang, Z Yang, Y He, X Chu. CIKM 2020
- Mlrda: A multi-task semi-supervised learning framework for drug-drug interaction prediction. X Chu, Y Lin, Y Wang, L Wang, J Wang, J Gao. IJCAI 2019
- Star: Spatio-temporal taxonomy-aware tag recommendation for citizen complaints. J Gao, Y He, Y Wang, X Wang, J Wang, G Peng, X Chu. CIKM 2019
- CAPED: Context-Aware Powerlet-Based Energy Disaggregation. J Gao, Y Wang, X Chu, Y He, Z Mao. KDD 2018
- Mining Rules from Real-Valued Time Series: A Relative Information-Gain-Based Approach. Y He, X Chu, G Peng, Y Wang, Z Jin, X Wang. COMPSAC 2018
- Characteristic subspace learning for time series classification. Y He, J Pei, X Chu, Y Wang, Z Jin, G Peng. ICDM 2018
Selected Journal Papers
- LoRA Dropout as a Sparsity Regularizer for Overfitting Reduction. Y Lin, X Ma, X Chu, Y Jin, Z Yang, Y Wang. KBS 2025
- Exploring the relationship between dietary intake and clinical outcomes in peritoneal dialysis patients stratified by serum albumin levels: A 12-year follow-up using fine…. Y Wu, J Gao, W Tang, C Su, Y Zhu, T Wang, L Wang, W Liao, X Chu, .... HDS 2025
- Imputation with Inter-Series Information from Prototypes for Healthcare Time Series. Z Yu, X Chu, L Ma, Y Wang, W Zhu. JCST 2025
- NPC: Negative Prototypical Contrasting for Label Disambiguation of Partial Label Learning . Y Jin, Y Wang, X Chu. Journal of Computer Science and Technology (JCST), 2025, 40(5): 1386-1400.
- Towards sustainable compressive population health: A GAN-based year-by-year imputation method. Y Feng, J Wang, Y Wang, X Chu. ACM TCH 2023
- An Adaptive Fusion Risk-Zone Detection Network and its Application. J Ma, X Wang, Y Wang, X Chu, J Zhao. IJPRAI 2023
- Patient health representation learning via correlational sparse prior of medical features. X Ma, Y Wang, X Chu, L Ma, W Tang, J Zhao, Y Yuan, G Wang. TKDE 2022
- Spatial-attention and demographic-augmented generative adversarial imputation network for population health data reconstruction. Y Feng, J Wang, Y Wang, X Chu. IEEE TBD 2022
- Enhancing online epidemic supervising system by compartmental and gru fusion model. J Ma, X Wang, Y Wang, J Wang, X Chu, J Zhao. Mob. Inf. Syst. 2022
- 面向鲁棒图结构防御的过参数化图神经网络. 初旭， 马辛宇， 林阳， 王鑫， 王亚沙， 朱文武， 梅宏. 软件学报 2024
Preprints Papers
- Dfams: Dynamic-flow guided federated alignment based multi-prototype search. Z Yang, X Jiang, R Qiu, R Li, Y Zhang, Y Fang, Y Xu, H Ding, X Chu, .... arXiv 2025
- LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models. W Liao, X Gao, T Jia, R Qiu, Y Zhu, Y Lin, X Chu, J Zhao, Y Wang. arXiv 2025
- Exploring the potential of large language models in graph generation. Y Yao, X Wang, Z Zhang, Y Qin, Z Zhang, X Chu, Y Yang, W Zhu, H Mei. arXiv 2024
- Infinite-horizon graph filters: Leveraging power series to enhance sparse information aggregation. R Zhang, X Jiang, Y Fang, J Luo, Y Xu, Y Zhu, X Chu, J Zhao, Y Wang. arXiv 2024
- Think and retrieval: A hypothesis knowledge graph enhanced medical large language models. X Jiang, R Zhang, Y Xu, R Qiu, Y Fang, Z Wang, J Tang, H Ding, X Chu, .... arXiv 2023
- MedFACT: Modeling Medical Feature Correlations in Patient Health Representation Learning via Feature Clustering. X Ma, X Chu, Y Wang, H Yu, L Ma, W Tang, J Zhao. arXiv 2022
- Multi-label robust factorization autoencoder and its application in predicting drug-drug interactions. X Chu, Y Lin, J Gao, J Wang, Y Wang, L Wang. arXiv 2018
- Motif-based Rule Discovery for Predicting Real-valued Time Series. Y He, X Chu, J Peng, J Gao, Y Wang. arXiv 2017