Publications (2010-2026)
69
Software Engineering
22
Distributed AI Systems
27
Agentic AI & LLMs
2026
-
[1] Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code AdaptationFSE 2026, Montreal, Canada CCF-A [PDF]
2025
-
[2] Are External Contributions Important to Project Productivity in Open Source Software? A Deep Insight based on Issue EntropyCSCW 2025, Bergen, Norway CCF-A
-
[3] Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt EngineeringICSE 2025, Ottawa, Canada CCF-A [PDF]
-
[4] AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet AdaptationASE 2025, Seoul, Korea CCF-A [PDF]
2024
-
[5] How do Developers Adapt Code Snippets to Their Contexts? An Empirical Study of Context-Based Code Snippet AdaptationsIEEE TSE, 2024 CCF-A
-
[6] Towards More Precise Coincidental Correctness Detection with Deep Semantic LearningIEEE TSE, 2024 CCF-A
-
[7] Cut to the Chase: An Error-Oriented Approach to Detect Error-Handling BugsFSE 2024, Porto de Galinhas, Brazil CCF-A [PDF]
2023
-
[8] PLUMBER: Boosting the Propagation of Vulnerability Fixes in the npm EcosystemIEEE TSE, 2023 CCF-A [PDF]
-
[9] Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code ComprehensionICSE 2023, Melbourne, Australia CCF-A [PDF]
-
[10] Understanding and Detecting On-the-Fly Configuration BugsICSE 2023, Melbourne, Australia CCF-A [PDF]
-
[11] MulCS: Towards a Unified Deep Representation for Multilingual Code SearchSANER 2023, Macao, China CCF-B [PDF]
-
[12] Can Machine Learning Pipelines Be Better Configured?ESEC/FSE 2023, San Francisco, USA CCF-A [PDF]
-
[13] When Database Meets New Storage Devices: Understanding and Exposing Performance Mismatches via ConfigurationsVLDB 2023, Vancouver, Canada CCF-A [PDF]
-
[14] A Two-Stage Framework for Ambiguous Classification in Software EngineeringISSRE 2023, Florence, Italy CCF-B
2022
-
[15] To Follow or Not to Follow: Understanding Issue/Pull-Request Templates on GitHubIEEE TSE, 2022 CCF-A [PDF]
-
[16] Pull Request Decisions Explained: An Empirical OverviewIEEE TSE, 2022 CCF-A [PDF]
-
[17] Opportunities and Challenges in Repeated Revisions to Pull-Requests: An Empirical StudyCSCW 2022, Taipei, China CCF-A [PDF]
-
[18] Who, What, Why and How? Towards the Monetary Incentive in Crowd Collaboration: A Case Study of Github's Sponsor MechanismCHI 2022, New Orleans, USA CCF-A [PDF]
-
[19] Multi-Intention-Aware Configuration Selection for Performance TuningICSE 2022, Pittsburgh, USA CCF-A [PDF]
-
[20] Bridging Pre-trained Models and Downstream Tasks for Source Code UnderstandingICSE 2022, Pittsburgh, USA CCF-A [PDF]
-
[21] A Universal Data Augmentation Approach for Fault LocalizationICSE 2022, Pittsburgh, USA CCF-A [PDF]
-
[22] Reentrancy Vulnerability Detection and Localization: A Deep Learning Based Two-phase ApproachASE 2022, Michigan, USA CCF-A
-
[23] Towards Usable Neural Comment Generation via Code-comment Linkage Interpretation: Method and Empirical StudyIEEE TSE, 2022 CCF-A [PDF]
-
[24] Influential Global and Local Contexts Guided Trace Representation for Fault LocalizationACM TOSEM, 2022 CCF-A [PDF]
-
[25] FENSE: A Feature-Based Ensemble Modeling Approach to Cross-Project Just-in-Time Defect PredictionEMSE, 2022 CCF-B [PDF]
-
[26] deGraphCS: Embedding Variable-based Flow Graph for Neural Code SearchACM TOSEM, 2022 CCF-A [PDF]
2021
-
[27] Are You Still Working on This? An Empirical Study on Pull Request AbandonmentIEEE TSE, 2021 CCF-A
-
[28] MulCode: A Multi-task Learning Approach for Source Code UnderstandingSANER 2021 CCF-B
-
[29] How to Cherry Pick the Bug Report for Better Summarization?EMSE, 2021 CCF-B
-
[30] Dual Channel Among Task and Contribution on OSS Communities: An Empirical StudyIJSEKE, 2021 CCF-C
2020
-
[31] Redundancy, Context, and Preference: An Empirical Study of Duplicate Pull Requests in OSS ProjectsIEEE TSE, 2020 CCF-A
-
[32] BugSum: Deep Context Understanding for Bug Report SummarizationICPC 2020 CCF-B
-
[33] On the Shoulders of Giants: A New Dataset for Pull-based Development ResearchMSR 2020 CCF-C
-
[34] Software Visualization and Deep Transfer Learning for Effective Software Defect PredictionICSE 2020 CCF-A
-
[35] CP-Detector: Using Configuration-related Performance Properties to Expose Performance BugsASE 2020 CCF-A
-
[36] Crowd-intelligence-based software development method and practicesScience China Information Sciences, 2020 CCF-B
2019
-
[37] Detecting Duplicate Contributions in Pull-based Model Combining Textual and Change SimilaritiesJCST, 2019 CCF-B
-
[38] Why API Documentation is Insufficient for Developers: an Empirical StudyScience China Information Sciences, 2019 CCF-B
-
[39] HAF: A Hybrid Annotation Framework Based on Expert Knowledge and Learning TechniqueScience China Information Sciences, 2019 CCF-B
-
[40] Multi-reviewing pull-requests: An exploratory study on GitHub OSS projectsIST, 2019 CCF-B
2018
-
[41] A Dataset of Duplicate Pull-requests in GitHubMSR 2018, Gothenburg, Sweden CCF-C
-
[42] Within-Ecosystem Issue Linking: A Large-scale Study of RailsSoftwareMining@ASE 2018, France
-
[43] A Hybrid Approach for Tag Hierarchy ConstructionICSR 2018, Madrid, Spain
-
[44] Transferring Well-Trained Models for Cross-Project Issue Classification: A Large-Scale Empirical StudyInternetware 2018, Beijing, China
2017
-
[45] Where is the Road for Issue Reports Classification Based on Text MiningESEM 2017, Toronto, Canada CCF-B
-
[46] Automatic Classification of Review Comments in Pull-based Development ModelSEKE 2017, Pittsburgh, USA CCF-C
-
[47] What are they talking about? Analyzing Code Reviews in Pull-based Development ModelJCST, 2017 CCF-B
-
[48] DevRec: A Developer Recommendation System for Open Source RepositoriesICSR 2017 CCF-C
-
[49] Detecting duplicate pull-requests in GitHubInternetware 2017
2016
-
[50] Reviewer Recommendation for Pull-Requests in GitHub: What Can We Learn from Code Review and Bug Assignment?IST, 2016 CCF-B
-
[51] Determinants of pull-based development in the context of continuous integrationScience China Information Sciences, 2016 CCF-B
-
[52] Social media in GitHub: the role of @-mention in assisting software developmentScience China Information Sciences, 2016 CCF-B
-
[53] Correlation-based software search by leveraging software term databaseFCS, 2016 CCF-C
2015
-
[54] Quality and Productivity Outcomes Relating to Continuous Integration in GitHubESEC/FSE 2015, Bergamo, Italy CCF-A
-
[55] Wait For It: Determinants of Pull Request Evaluation Latency on GitHubMSR 2015, Florence, Italy CCF-C
-
[56] Exploring the Use of @-mention to Assist Software Development in GitHubInternetware 2015, Wuhan, China
-
[57] Evaluating Bug Severity Using Crowd-based Knowledge: An Exploratory StudyInternetware 2015, Wuhan, China
2014
-
[58] Reviewer Recommender of Pull-Requests in GitHubICSME 2014, Victoria, Canada CCF-B
-
[59] Who Should Review This Pull-Request: Reviewer Recommendation to Expedite Crowd CollaborationAPSEC 2014, JEJU, KOREA CCF-C 🏆 Best Paper
-
[60] Exploring the Patterns of Social Behavior in GitHubCrowdSoft 2014, Hong Kong
-
[61] Investigating social media in GitHub's pull-requests: a case study on Ruby on RailsCrowdSoft 2014, Hong Kong
-
[62] An Exploratory Study of @-mention in GitHub's Pull-requestsAPSEC 2014, JEJU, KOREA CCF-C
2013
-
[63] HESA: The Construction and Evaluation of Hierarchical Software Feature RepositorySEKE 2013, Boston, USA CCF-C
-
[64] Mining and Recommending Software Features across Multiple Web RepositoriesInternetware 2013, Changsha, China
-
[65] A Trusted Remote Attestation Model based on Trusted ComputingTrustCom 2013, Melbourne, Australia CCF-C
2012
-
[66] Inducing Taxonomy from Tags: An Agglomerative Hierarchical Clustering FrameworkADMA 2012
2011
-
[67] Trusted Computing Dynamic Attestation by Using Static Analysis Based Behavior ModelISPDPAW 2011, Bussan, Korea
-
[68] Optimization of Program Behavior Model for Trusted Computing Dynamic AttestationJournal of Computational Information Systems, 2011
2010
-
[69] Static Analysis-based Behavior Model Building for Trusted Computing Dynamic VerificationWuhan University Journal of Natural Sciences, 2010
2026
-
[70] ParaSync: Exploiting Fine-Grained Parallelism for Efficient File SynchronizationFAST 2026, Santa Clara, USA CCF-A
-
[71] Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer GateWWW 2026, Dubai, UAE CCF-A
2025
-
[72] Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch PipelineASPLOS 2025, Rotterdam, Netherlands CCF-A [PDF]
-
[73] Obscura: Concealing Recomputation Overhead in Training of Large Language Models with Bubble-filling Pipeline TransformationUSENIX ATC 2025, Boston, USA CCF-A [PDF]
-
[74] CrossFS: Improving Cross-Domain File System Performance with CRDT-Based Metadata SynchronizationACM TOS, 2025 CCF-A
-
[75] Looking Back to Move Forward: Unveiling the Mysteries of HBM Errors to Predict Future FailuresACM TOS, 2025 CCF-A
-
[76] NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN ModelsACM TOSEM, 2025 CCF-A [PDF]
-
[77] RingMoE: Mixture-of-modality-experts multi-modal foundation models for universal remote sensing image interpretationIEEE TPAMI, 2025 CCF-A [PDF]
-
[78] Centrality-guided Pre-training for GraphICLR 2025, Singapore - [PDF]
-
[79] CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer InferenceACL 2025, Vienna, Austria CCF-A [PDF]
2024
-
[80] Optimus: Warming Serverless ML Inference via Inter-Function Model TransformationEuroSys 2024, Athens, Greece CCF-A [PDF]
-
[81] Training and Serving System of Foundation Models: A Comprehensive SurveyIEEE OJCS, 2024 SCI [PDF]
-
[82] Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic RegularizationICML 2024, Vienna, Austria CCF-A [PDF]
-
[83] SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPCACL 2024, Bangkok, Thailand CCF-A [PDF]
2023
-
[84] A Survey on Scheduling Techniques in Computing and Network ConvergenceIEEE COMST, 2023 JCR-Q1 [PDF]
-
[85] Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN TrainingNeurIPS 2023, New Orleans, USA CCF-A [PDF]
-
[86] Intelligence-Endogenous Management Platform for Computing and Network ConvergenceIEEE Network, 2023 JCR-Q1 [PDF]
-
[87] FedPETuning: When Federated Learning Meets the Parameter-Efficient Tuning Methods of Pre-trained Language ModelsACL 2023, Toronto, Canada CCF-A [PDF]
-
[88] Ginver: Generative Model Inversion Attacks Against Collaborative InferenceWWW 2023, Austin, USA CCF-A [PDF]
-
[89] Fine-grained Key-Value Memory Enhanced Predictor for Video Representation LearningACM MM 2023, Ottawa, Canada CCF-A [PDF]
-
[90] Mask Again: Masked Knowledge Distillation for Masked Video ModelingACM MM 2023, Ottawa, Canada CCF-A [PDF]
2021
-
[91] PanGu-a: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel ComputationarXiv 2104.12369, 2021
2026
-
[92] GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement LearningICLR 2026, Brazil - [PDF]
-
[93] Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless LocalizationICLR 2026, Brazil - [PDF]
-
[94] Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot LearningICLR 2026, Brazil - [PDF]
-
[95] SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPCICLR 2026, Brazil - [PDF]
-
[96] Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-ExpertsAAAI 2026, Singapore CCF-A [PDF]
2025
-
[97] SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online FeedbackNeurIPS 2025, San Diego, USA CCF-A [PDF]
-
[98] OBDD-NET: End-to-End Learning of Ordered Binary Decision DiagramsCIKM 2025, Seoul, Korea CCF-B [PDF]
-
[99] Correcting Large Language Model Behavior via Influence FunctionAAAI 2025, Pennsylvania, USA CCF-A [PDF]
-
[100] Preference-Strength-Aware Self-Improving Alignment with Generative Preference ModelsSIGIR 2025, Padua, Italy - [PDF]
-
[101] COPR: Continual Human Preference Learning via Optimal Policy RegularizationACL 2025, Vienna, Austria CCF-A [PDF]
-
[102] Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context LearningACL 2025, Vienna, Austria CCF-A [PDF]
2024
-
[103] At Which Training Stage Does Code Data Help LLMs Reasoning?ICLR 2024, Vienna, Austria - [PDF]
-
[104] EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property ProtectionAAAI 2024, Vancouver, Canada CCF-A [PDF]
-
[105] Rethinking the Evaluation of In-Context Learning for LLMsEMNLP 2024, Miami, USA CCF-A [PDF]
-
[106] Easing Concept Bleeding in Diffusion via Entity Localization and AnchoringICML 2024, Vienna, Austria CCF-A [PDF]
-
[107] URG: A Unified Ranking and Generation Method for Ensembling Language ModelsACL 2024, Bangkok, Thailand CCF-A [PDF]
-
[108] GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised LearningECCV 2024, Milan, Italy CCF-A [PDF]
2023
-
[109] DSP: Discriminative Soft Prompts for Zero-Shot Entity and Relation ExtractionACL 2023, Toronto, Canada CCF-A [PDF]
-
[110] Practical Privacy-Preserving Gaussian Process Regression via Secret SharingUAI 2023, Pittsburgh, USA CCF-B [PDF]
-
[111] Multitask joint strategies of self-supervised representation learning on biomedical networks for drug discoveryNature Machine Intelligence, 2023 - [PDF]
-
[112] Re-Thinking the Effectiveness of Batch Normalization and BeyondIEEE TPAMI, 2023 CCF-A [PDF]
2022
-
[113] NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron IdentificationICSE 2022, Pittsburgh, USA CCF-A [PDF]
2021
-
[114] Transductive Relation-Propagation with Decoupling Training for Few-Shot LearningIEEE TNNLS, 2021 CCF-B
-
[115] Detecting Adversarial Samples with Graph-Guided TestingASE 2021 CCF-A
2020
-
[116] Near-Online Multi-pedestrian Tracking via Combining Multiple Consistent Appearance CuesIEEE TCSVT CCF-B
2019
-
[117] TMDA: Task-Specific Multi-Source Domain Adaptation via Clustering Embedded Adversarial TrainingICDM 2019, Beijing, China CCF-B
2010
-
[118] Static Analysis-based Behavior Model Building for Trusted Computing Dynamic VerificationWuhan University Journal of Natural Sciences, 2010