Publications
The most up-to-date list can be found on my Google Scholar.
2025
- ICML’25Mitigating Heterogeneous Token Overfitting in LLM Knowledge EditingIn The Fourty-Second International Conference on Machine Learning, 2025
- ACL’25RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference OptimizationIn Findings of the Association for Computational Linguistics: ACL 2025, 2025
- ICLR’25Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-TuningIn The Thirteenth International Conference on Learning Representations, 2025
- ICLR’25Towards federated rlhf with aggregated client preference for llmsIn The Thirteenth International Conference on Learning Representations, 2025
- arxivLlms can generate a better answer by aggregating their own responsesarXiv preprint arXiv:2503.04104, 2025
- arxivCollab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM CollaborationarXiv preprint arXiv:2504.04915, 2025
- KDD’25Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate ShiftIn Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025
2024
- ICML’24LIDAO: Towards Limited Interventions for Debiasing (Large) Language ModelsIn The Fourty-First International Conference on Machine Learning, 2024
- ICDE’24LightLT: a lightweight representation quantization framework for long-tail dataIn 2024 IEEE 40th International Conference on Data Engineering (ICDE), 2024
- EMNLP’24BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge FilteringIn Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
- C\^ 3: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language UnderstandingarXiv preprint arXiv:2402.15991, 2024
- EMNLP’24RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuningIn Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
- Minimalism Yields Maximum Results: Deep Learning with Limited ResourcePurdue University, 2024
- TOSNTowards smartphone-based 3d hand pose reconstruction using acoustic signalsACM Transactions on Sensor Networks, 2024
- ICML’24LIDAO: Towards Limited Interventions for Debiasing (Large) Language ModelsIn The Fourty-First International Conference on Machine Learning, 2024
- arxivNEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained ModelsarXiv preprint arXiv:2410.01870, 2024
- SenSys’24mmCLIP: Boosting mmWave-based Zero-shot HAR via Signal-Text AlignmentIn Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems, 2024
- SenSys’24Towards efficient heterogeneous multi-modal federated learning with hierarchical knowledge disentanglementIn Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems, 2024
2023
- AAAI’23Simfair: A unified framework for fairness-aware multi-label classificationIn Proceedings of the AAAI Conference on Artificial Intelligence, 2023
- KDD’23Lighttoken: A task and model-agnostic lightweight token embedding framework for pre-trained language modelsIn Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
- KDD’23Macular: A multi-task adversarial framework for cross-lingual natural language understandingIn Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
- EMNLP’23Hadskip: Homotopic and adaptive layer skipping of pre-trained language models for efficient inferenceIn Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
- EMNLP’23Macedon: Minimizing representation coding rate reduction for cross-lingual natural language understandingIn Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
2022
- WWW’22Fedkc: Federated knowledge composition for multilingual natural language understandingIn Proceedings of the ACM Web Conference 2022, 2022
- SenSys’22M4esh: mmWave-Based 3D Human Mesh Construction for Multiple SubjectsIn Proceedings of the Twentieth ACM Conference on Embedded Networked Sensor Systems, 2022
2021
- SDM’21Fair classification under strict unawarenessIn Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), 2021
- SIGIR’21xLightFM: Extremely memory-efficient factorization machineIn Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021
- KDD’21Multimodal emergent fake news detection via meta neural process networksIn Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 2021
- CIKM’21A lightweight knowledge graph embedding framework for efficient inference and storageIn Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021
- EMNLP’21Knowledge-guided paraphrase identificationIn Findings of the Association for Computational Linguistics: EMNLP 2021, 2021
- BIBM’21Interhg: an interpretable and accurate model for hypothesis generationIn 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021
2020
- WWW’20Lightrec: A memory and search-efficient recommender systemIn Proceedings of The Web Conference 2020, 2020
2019
- IJCAI’19Binarized collaborative filtering with distilling graph convolutional networksIn Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019
- AAAI’19Adversarial Binary Collaborative Filtering for Implicit FeedbackIn Proceedings of the AAAI Conference on Artificial Intelligence, 2019
2018
- KDD’18Discrete ranking-based matrix factorization with self-paced learningIn Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018