About Me

I am currently a Professor at Pengcheng Laboratory (PCL). Prior to joining PCL, I was with the Trustie Group at the National University of Defense Technology (NUDT) from 2011 to 2024. My research interests lie at the intersection of Software Engineering, Distributed & Cloud Computing, and Artificial Intelligence. Currently, my work focuses on Distributed AI Systems and Computing Power Networks, with an emphasis on efficient training/inference of foundation models, resource scheduling for heterogeneous computing, and intelligent software infrastructure.

Prospective Students and Collaborators: I am actively recruiting PhD students, postdoctoral researchers, and young faculty members. If you are interested in building next-generation AI systems or intelligent computing infrastructure, please feel free to contact me.

Selected Publications (2024-2026)

View all my publications

• Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-Experts Distributed AI Systems
  Qi Wang, Hanyang Peng, Yue Yu (corresponding author)
  AAAI 2026, Singapore CCF-A [PDF]
• Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code Adaptation Software Engineering
  Tanghaoran Zhang, Xinjun Mao, Shangwen Wang, Yuxin Zhao, Yao Lu, Zezhou Tang, Wenyu Xu, Longfei Sun, Changrong Xie, Kang Yang, Yue Yu (corresponding author)
  FSE 2026, Montreal, Canada CCF-A [PDF]
• GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning Agentic AI & LLMs
  Han Zhang, Ruibin Zheng, ZeXuan Yi, Zhuo Zhang, Hanyang Peng, Hui Wang, Jiayin Qi, Binxing Fang, Ruifeng Xu, Yue Yu (corresponding author)
  ICLR 2026, Brazil [PDF]
• Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization Agentic AI & LLMs
  Yong Chu, Xun Zhou, Zenglin Xu, Hui Wang, Yue Yu
  ICLR 2026, Brazil [PDF]
• Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning Agentic AI & LLMs
  Dexia Chen, Qianjie Zhu, Weibing Li, Yue Yu , Tong Zhang, Ruixuan Wang
  ICLR 2026, Brazil [PDF]
• SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC Agentic AI & LLMs
  Jinglong Luo, Zhuo Zhang, Yehong Zhang, Shiyu Liu, Ye Dong, Hui Wang, Yue Yu , Xun Zhou, Zenglin Xu
  ICLR 2026, Brazil [PDF]
• Survey on Learning-based Dynamic Fault Localization: From Traditional Machine Learning to Large Language Models Agentic AI & LLMs
  Chunyan Liu, Yan Lei, Huan Xie, Jinping Wang, Yue Yu , David Lo
  CSUR 2026 JCR-1 [PDF]
• ParaSync: Exploiting Fine-Grained Parallelism for Efficient File Synchronization Distributed AI Systems
  Zhihao Zhang, Lu Tang, Huiba Li, Yue Yu , Jiwu Shu, Yiming Zhang
  FAST 2026, Santa Clara, USA CCF-A[PDF]
• Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate Distributed AI Systems
  Zhiyuan Fang, Xingfan Yu, Yuegui Huang, Zicong Hong, Yufeng Lyu, Wuhui Chen, Yue Yu , Fan Yu
  WWW 2026, Dubai, UAE CCF-A[PDF]

• Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline Distributed AI Systems
  Zhiyuan Fang, Yuegui Huang, Zicong Hong, Yufeng Lyu, Wuhui Chen, Yue Yu (corresponding author), Fan Yu, Zibin Zheng
  ASPLOS 2025, Rotterdam, Netherlands CCF-A[PDF]
• SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback Agentic AI & LLMs
  Bo Lv, Nayu Liu, Chen Tang, Xin Liu, Yue Yu (corresponding author), Ping Luo
  NeurIPS 2025, San Diego, USA CCF-A[PDF]
• Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering Software Engineering
  Tanghaoran Zhang, Yue Yu (corresponding author), Xinjun Mao, Shangwen Wang, Kang Yang, Yao Lu, Zhang Zhang, Yuxin Zhao
  ICSE 2025, Ottawa, Canada CCF-A[PDF]
• AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation Software Engineering
  Tanghaoran Zhang, Xinjun Mao, Shangwen Wang, Yuxin Zhao, Yao Lu, Jin Zhang, Zhang Zhang, Kang Yang, Yue Yu (corresponding author)
  ASE 2025, Seoul, Korea CCF-A[PDF]
• OBDD-NET: End-to-End Learning of Ordered Binary Decision Diagrams Agentic AI & LLMs
  Junming Qiu, Rongzhen Ye, Weilin Luo, Kunxun Qi, Hai Wan*, Yue Yu (corresponding author)
  CIKM 2025, Seoul, Korea CCF-B[PDF]
• Obscura: Concealing Recomputation Overhead in Training of Large Language Models with Bubble-filling Pipeline Transformation Distributed AI Systems
  Y. Huang, Y. Jiang, Z. Hong, W. Chen, B. Wang, W. Zhu, Yue Yu , Zibin Zheng
  ATC 2025, Boston, USA CCF-A[PDF]
• Correcting Large Language Model Behavior via Influence Function Agentic AI & LLMs
  Han Zhang, Zhuo Zhang, Yi Zhang, Yuanzhao Zhai, Hanyang Peng, Yu Lei, Yue Yu , Hui Wang, Bin Liang, Lin Gui, Ruifeng Xu
  AAAI 2025, Pennsylvania, USA CCF-A[PDF]
• Centrality-guided Pre-training for Graph Agentic AI & LLMs
  Bin Liang, Shiwei Chen, Lin Gui, Hui Wang, Yue Yu , Ruifeng Xu, Kam-Fai Wong
  ICLR 2025, Singapore [PDF]
• Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models Agentic AI & LLMs
  Yuanzhao Zhai, Zhuo Zhang, Cheng Yang, Kele Xu, Yue Yu , Wei Li, Hui Wang, Zenglin Xu, Dawei Feng, Bo Ding, Huaimin Wang
  SIGIR 2025, Padua, Italy CCF-A [PDF]
• COPR: Continual Human Preference Learning via Optimal Policy Regularization Agentic AI & LLMs
  Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu , Kam-Fai Wong, Bin Liang, Ruifeng Xu
  ACL 2025, Vienna, Austria CCF-A [PDF]
• Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context Learning Agentic AI & LLMs
  Bo Lv, Nayu Liu, Yang Shen, Xin Liu, Ping Luo, Yue Yu
  ACL 2025, Vienna, Austria CCF-A [PDF]
• CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference Agentic AI & LLMs
  Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu , Xun Zhou, Yuan Qi, Zenglin Xu
  ACL 2025, Vienna, Austria CCF-A [PDF]
• Are External Contributions Important to Project Productivity in Open Source Software? A Deep Insight based on Issue Entropy Software Engineering
  Yang Shen, Tao Wang, Xunhui Zhang, Yang Zhang, Cheng Yang, Yue Yu , Huaimin Wang
  CSCW 2025, Bergen, Norway CCF-A [PDF]
• CrossFS: Improving Cross-Domain File System Performance with CRDT-Based Metadata Synchronization Distributed AI Systems
  Qiwen Ke, Yina Lv, Zhihao Zhang, Zhirong Shen, Yue Yu , Hailiang Chen, Zhenglong Song, Xinbiao Gan, Jiaxin Li, Dongsheng Li, Xin Yao, Meiling Wang, Yiming Zhang
  TOS 2025 CCF-A [PDF]

• At Which Training Stage Does Code Data Help LLMs Reasoning? Agentic AI & LLMs
  Yingwei Ma, Yue Liu, Yue Yu (corresponding author), et al.
  ICLR 2024, Vienna, Austria [PDF]
• EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection Agentic AI & LLMs
  Xin Mu, Yu Wang, Zhengan Huang, et al., Yue Yu (corresponding author)
  AAAI 2024, Vancouver, Canada CCF-A [PDF]
• Rethinking the Evaluation of In-Context Learning for LLMs Agentic AI & LLMs
  Guoxin Yu, Lemao Liu, Mo Yu, Yue Yu (corresponding author), Xiang Ao
  EMNLP 2024, Miami, USA CCF-A [PDF]
• Cut to the Chase: An Error-Oriented Approach to Detect Error-Handling Bugs Software Engineering
  Zhenyu Wu, Zhi Li, Yue Yu (corresponding author), et al.
  FSE 2024, Porto de Galinhas, Brazil CCF-A [PDF]
• Optimus: Warming Serverless ML Inference via Inter-Function Model Transformation Distributed AI Systems
  Zicong Hong, Jian Lin, Song Guo, et al., Yue Yu
  EuroSys 2024, Athens, Greece CCF-A [PDF]
• How do Developers Adapt Code Snippets to Their Contexts? An Empirical Study of Context-Based Code Snippet Adaptations Software Engineering
  Tanghaoran Zhang, Yao Lu, Yue Yu, Xinjun Mao, Yang Zhang, Yuxin Zhao
  IEEE TSE, 2024 CCF-A [PDF]
• Towards More Precise Coincidental Correctness Detection with Deep Semantic Learning Software Engineering
  Huan Xie, Yan Lei, Meng Yan, Shanshan Li, Xiaoguang Mao, Yue Yu, David Lo
  IEEE TSE, 2024 CCF-A [PDF]
• Training and Serving System of Foundation Models: A Comprehensive Survey Software Engineering
  Jiahang Zhou, Yanyu Chen, Zicong Hong, Wuhui Chen, Yue Yu, Tao Zhang, Hui Wang, Chuanfu Zhang, Zibin Zheng
  IEEE OJCS, 2024 SCI [PDF]
• Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization Distributed AI Systems
  Xueyang Tang, Song Guo, Jingcai Guo, Jie Zhang, Yue Yu
  ICML 2024, Vienna, Austria CCF-A [PDF]
• SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC Agentic AI & LLMs
  Jinglong Luo, Yehong Zhang, Zhuo Zhang, Jiaqi Zhang, Xin Mu, Hui Wang, Yue Yu, Zenglin Xu
  ACL 2024, Bangkok, Thailand CCF-A [PDF]
• Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring Agentic AI & LLMs
  Jiewei Zhang, Song Guo, Peiran Dong, Jie Zhang, Ziming Liu, Yue Yu, Xiaoming Wu
  ICML 2024, Vienna, Austria CCF-A [PDF]
• URG: A Unified Ranking and Generation Method for Ensembling Language Models Agentic AI & LLMs
  Bo Lv, Chen Tang, Yanan Zhang, Xin Liu, Ping Luo, Yue Yu
  ACL 2024, Bangkok, Thailand CCF-A [PDF]
• GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning Software Engineering
  Xiaojie Li, Yibo Yang, Xiangtai Li, Jianlong Wu, Yue Yu, Bernard Ghanem, Min Zhang
  ECCV 2024, Milan, Italy CCF-A [PDF]

View all my publications →

Awards & Honors

• 2025
  ACM Gordon Bell Prize Finalist for Climate Modelling

  AP3ESM: Kilometer-Scale AI-Powered Earth System Model (SC 2025)
• 2024
  ACM Gordon Bell Prize Finalist for Climate Modelling

  Global Ocean Model on Heterogeneous Supercomputers (SC 2024)
• 2024
  CCF NASAC Youth Software Innovation Award

  中国计算机学会 NASAC 青年软件创新奖
• 2024
  DAMO Academy Young Science Talent "Most Promising Award"

  阿里巴巴达摩院青橙奖最具潜力奖
• 2018
  Outstanding Ph.D. Thesis Award of Hunan Province

  湖南省优秀博士学位论文奖
• 2016
  ACM Changsha Doctoral Dissertation Award

  ACM 中国长沙分会优秀博士论文奖