Yanchi Liu


    Email
    LinkedIn
    Google Scholar

I am a Senior Research Staff Member in the Department of Data Science and System Security at NEC Labs America. I got my Ph.D. in Information Technology from Rutgers, the State University of New Jersey, under the supervision of Professor Hui Xiong.
My current research focuses on Large Language Models (LLMs), Agentic AI, AI efficiency, and trustworthy AI, with an emphasis on building reliable, efficient, and domain-specialized AI systems. Specific topics include LLM reasoning and planning, multi-agent systems, domain adaptation, model compression and routing. I am broadly interested in applying these techniques to solve real-world problems in complex system management, cybersecurity, finance, healthcare, and aerospace.
I have published over 100 papers in top AI, NLP, and data mining venues including NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL, EACL, AAAI, IJCAI, KDD, SIGIR, WWW, WSDM, CIKM, ICDM, TKDE, and TKDD, with more than 10,000 citations (H-index: 45). I regularly serve as (senior) program committee member for NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL, AAAI, IJCAI, KDD, WWW, SIGIR, WSDM, CIKM, etc.


News

  • [2026/05] Two papers accepted to ACL 2026.
  • [2026/01] Three papers accepted to EACL 2026.
  • [2025/09] SolverLLM accepted to NeurIPS 2025.
  • [2025/05] Uncertainty Propagation on LLM Agent accepted to ACL 2025.
  • [2025/05] Received the NEC Excellent Invention Award.
  • [2025/02] MixLLM accepted to NAACL 2025.
  • [2024/10] Two papers accepted to EMNLP 2024.
  • [2024/05] Received the NEC Business Contribution Award.


Research Interests

  • Large Language Models: reasoning & planning, domain adaptation, model compression and routing
  • Agentic AI: multi-agent systems, tool use, autonomous workflows, uncertainty quantification
  • Trustworthy AI: reliability, safety, privacy-preserving learning, interpretability


    • Selected Publications

    • Google Scholar | • DBLP

  • Wangyang Ying, Yanchi Liu, Xujiang Zhao, Wei Cheng, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen. Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement. EACL, 2026.
  • Minghua Lin, Zhengzhang Chen, Yanchi Liu, Xujiang Zhao, Zongyu Wu, Junxiang Wang, Xiang Zhang, Suhang Wang, Haifeng Chen. Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation. Findings of the Association for Computational Linguistics (EACL), 2026.
  • Minghao Guo, Qingkai Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng. DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router. Findings of the Association for Computational Linguistics (EACL), 2026.
  • Dong Li, Xujiang Zhao, Linlin Yu, Yanchi Liu, Wei Cheng, Zhengzhang Chen, Zhiqiang Chen, Feng Chen, Chen Zhao, et al. SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search. Advances in Neural Information Processing Systems (NeurIPS), 2025.
  • Qingcheng Zhao, Dong Li, Yanchi Liu, Wei Cheng, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Yao, et al. Uncertainty Propagation on LLM Agent. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
  • Peng Yuan, Lu-An Tang, Yanchi Liu, Kondo Yuji, Masanao Sato, Haifeng Chen. Incident Diagnosing and Reporting System based on Retrieval Augmented Large Language Model. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025.
  • Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen. MixLLM: Dynamic Routing in Mixed Large Language Models. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025.
  • Yufei Li, Xiao Yu, Yanchi Guo, Yanchi Liu, Haifeng Chen, Cong Liu. Distantly-Supervised Joint Extraction with Noise-Robust Learning. Findings of the Association for Computational Linguistics (ACL), 2024.
  • Nan Zhang, Yanchi Liu, Xujiang Zhao, Wei Cheng, Runxue Bao, Rui Zhang, Prasenjit Mitra, Haifeng Chen. Pruning as a Domain-specific LLM Extractor. Findings of the Association for Computational Linguistics (NAACL), 2024.
  • Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, et al. Open-ended Commonsense Reasoning with Unrestricted Answer Candidates. Findings of the Association for Computational Linguistics (EMNLP), 2023.
  • Yufei Li, Yanchi Liu, Haoyu Wang, Zhengzhang Chen, Wei Cheng, Yuncong Chen, Wenchao Yu, Haifeng Chen, Cong Liu. GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection. IEEE International Conference on Knowledge Graph (ICKG), 2023.
  • Shengming Zhang, Yanchi Liu, Xuchao Zhang, Wei Cheng, Haifeng Chen, Hui Xiong. CAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022.
  • Denghui Zhang, Yanchi Liu, Zixuan Yuan, Yanjie Fu, Haifeng Chen, Hui Xiong. Multi-Faceted Knowledge-Driven Pre-training for Product Representation Learning. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022.
  • Denghui Zhang, Zixuan Yuan, Yanchi Liu, Hao Liu, Fuzhen Zhuang, Hui Xiong, Haifeng Chen. Domain-oriented Language Modeling with Adaptive Hybrid Masking and Optimal Transport Alignment. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2021.
  • Xuchao Zhang, Bo Zong, Wei Cheng, Jingchao Ni, Yanchi Liu and Haifeng Chen. Unsupervised Concept Representation Learning for Length-Varying Text Similarity. In Proceedings of The 2021 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL), 2021.
  • Denghui Zhang, Yanchi Liu, Wei Cheng, Bo Zong, Jingchao Ni, Zhengzhang Chen, Haifeng Chen, Hui Xiong. T$^2$-Net: A Semi-supervised Deep Model for Turbulence Forecasting. 2020 IEEE International Conference on Data Mining (ICDM), 2020.
  • Renjun Hu, Yanchi Liu, Yanyan Li, Jingbo Zhou, Shuai Ma, Hui Xiong. Exploiting User Preference and Mobile Peer Influence for Human Mobility Annotation. ACM Transactions on Knowledge Discovery from Data (TKDD), 2020.
  • Pengpeng Zhao, Anjing Luo, Yanchi Liu, Fuzhen Zhuang, Jiajie Xu, Zhixu Li, Victor S Sheng, Xiaofang Zhou. Where to go next: A spatio-temporal gated network for next poi recommendation. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020.
  • Weijia Zhang, Hao Liu, Yanchi Liu, Jingbo Zhou, Tong Xu, Hui Xiong. Semi-Supervised City-Wide Parking Availability Prediction via Hierarchical Recurrent Graph Neural Network. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020.
  • Nengjun Zhu, Jian Cao, Yanchi Liu, Yang Yang, Haochao Ying, Hui Xiong. Sequential Modeling of Hierarchical User Intention and Preference for Next-item Recommendation. Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM), 2020.
  • Jian Liu, Pengpeng Zhao, Fuzhen Zhuang, Yanchi Liu, Victor S Sheng, Jiajie Xu, Xiaofang Zhou, Hui Xiong. Exploiting Aesthetic Preference in Deep Cross Networks for Cross-domain Recommendation. Proceedings of The Web Conference (WWW), 2020.
  • Zixuan Yuan, Hao Liu, Yanchi Liu, Denghui Zhang, Fei Yi, Nengjun Zhu, Hui Xiong. Spatio-Temporal Dual Graph Attention Network for Query-POI Matching. %Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2020.
  • Dongbo Xi, Fuzhen Zhuang, Yanchi Liu, Jingjing Gu, Hui Xiong, Qing He. Modelling of Bi-directional Spatio-Temporal Dependence and Users' Dynamic Preferences for Missing POI Check-in Identification. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019.
  • Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Jiajie Xu, Victor Sheng, Zhiming Cui, Xiaofang Zhou, Hui Xiong. Recurrent Convolutional Neural Network for Sequential Recommendation. World Wide Web conference (WWW), 2019.
  • Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Victor S Sheng, Jiajie Xu, Fuzhen Zhuang, Junhua Fang, Xiaofang Zhou. Graph Contextualized Self-Attention Network for Session-based Recommendation. International Joint Conference on Artificial Intelligence (IJCAI), 2019.
  • Yanchi Liu, Tan Yan, Haifeng Chen. Exploiting Graph Regularized Multi-dimensional Hawkes Processes for Modeling Events with Spatio-temporal Characteristics. the 27th International Joint Conference on Artificial Intelligence (IJCAI), 2018.
  • Pengpeng Zhao, Haifeng Zhu, Yanchi Liu, Zhixu Li, Jiajie Xu, Victor S Sheng. Where to go next: A spatio-temporal lstm model for next poi recommendation. AAAI, 2018.
  • Yanchi Liu, Chuanren Liu, Xinjiang Lu, Mingfei Teng, Hengshu Zhu, Hui Xiong. Point of Interest Demand Modeling with Human Mobility Patterns. The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2017.
  • Pengpeng Zhao, Xiefeng Xu, Yanchi Liu, Victor S. Sheng, Kai Zheng, Hui Xiong. Photo2Trip: Exploiting Visual Contents in Geo-tagged Photos for Personalized Tour Recommendation. Proceedings of the 2017 ACM on Multimedia Conference (MM), 2017.
  • Pengpeng Zhao, Xiefeng Xu, Yanchi Liu, Ziting Zhou, Kai Zheng, Victor S. Sheng, Hui Xiong. Exploiting Hierarchical Structures for POI Recommendation. 2017 IEEE International Conference on Data Mining (ICDM), 2017.
  • Yanchi Liu, Chuanren Liu, Bin Liu, Meng Qu, Hui Xiong. Unified Point-of-Interest Recommendation with Temporal Interval Assessment. The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2016.
  • Lian Duan, Nick Street, Yanchi Liu, Haibing Lu. Community detection in graphs through correlation. Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD), 2014.
  • Yanchi Liu, Chuanren Liu, Nicholas Jing Yuan, Lian Duan, Yanjie Fu, Hui Xiong, Songhua Xu, Junjie Wu. Exploiting heterogeneous human mobility patterns for intelligent bus routing. 2014 IEEE International Conference on Data Mining (ICDM), 2014. (Best paper candidate>)
  • Yanchi Liu, Zhongmou Li, Hui Xiong, Xuedong Gao, Junjie Wu, Sen Wu. Understanding and enhancement of internal clustering validation measures. IEEE Transactions on Cybernetics, 2013.
  • Yu Zheng, Yanchi Liu, Jing Yuan, Xing Xie. Urban computing with taxicabs. Proceedings of the 13th international conference on Ubiquitous computing (UbiComp), 2011. (Best paper candidate>)
  • Yanchi Liu, Zhongmou Li, Hui Xiong, Xuedong Gao, Junjie Wu. Understanding of internal clustering validation measures. 2010 IEEE International Conference on Data Mining (ICDM), 2010.
  • Zhongmou Li, Hui Xiong, Yanchi Liu, Aoying Zhou. Detecting Blackhole and Volcano Patterns in Directed Networks. 2010 IEEE International Conference on Data Mining (ICDM), 2010.


    • Selected Patents

  • Yanchi Liu, Wei Cheng, Xujiang Zhao, Runxue Bao, Haifeng Chen, Nan Zhang. Optimizing Large Language Models with Domain-Oriented Model Compression. US Patent App. 18/805,978, 2025.
  • Xuchao Zhang, Yanchi Liu, Haifeng Chen. Intent Detection via Multi-Hop Unified Syntactic Graph. US Patent 12,153,878, 2024.
  • Yanchi Liu, Haifeng Chen, Masanao Sato. Automated Non-Synchronization Detection and Resolution in Complex Systems. US Patent App. 18/650,930, 2024.
  • Wei Cheng, Yanchi Liu, Haifeng Chen, Xi Yang. Unified Framework for Vision Prompt Tuning. US Patent App. 18/650,174, 2024.
  • Xujiang Zhao, Haifeng Chen, Wei Cheng, Yanchi Liu, Zhengzhang Chen, Haoyu Wang. Information Extraction with Large Language Models. US Patent App. 18/649,145, 2024.
  • Yanchi Liu, Haifeng Chen, Yufei Li. Log Anomaly Detection Using Temporal-Attentive Dynamic Graphs. US Patent App. 18/359,179, 2024.
  • Xuchao Zhang, Bo Zong, Yanchi Liu, Haifeng Chen. Interpreting Cross-Lingual Models for Natural Language Inference. US Patent 12,135,951, 2024.
  • Xuchao Zhang, Yanchi Liu, Bo Zong, Wei Cheng, Haifeng Chen, Jianwu Wang. Cross-Lingual Zero-Shot Transfer via Semantic and Synthetic Representation Learning. US Patent 12,050,870, 2024.


    • Honors and Awards

  • NEC Excellent Invention Award, NEC, 2025
  • NEC Business Contribution Award, NEC, 2024
  • NEC Global Innovation Unit Outstanding Award, NEC, 2022
  • Baidu Research Fellowship (10 PhD worldwide), Baidu, 2018
  • TA/RA Developing Fund Award, Rutgers University, 2018
  • Nominee of Best Paper, IEEE International Conference on Data Mining (ICDM), 2014
  • Nominee of Best Paper, ACM International Conference on Ubiquitous Computing (UbiComp), 2011


    • Mentorship

    I have had the privilege of mentoring many talented PhD interns and visiting students at NEC Labs America, inlcuding Wangyang Ying, Xinyuan Wang, Nan Zhang, Yufei Li, Shengming Zhang, and Denghui Zhang. Please reach out if you are interested in interning with our group.