Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
KDD 2025 - AI Reasoning DayMicrosoft · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025Score-based Generative Modeling for Conditional Independence TestingAlibaba · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025FoRAGe: High-CTR Food Image Synthesis with Retrieval-Augmented Diffusion ModelAlibaba · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025SPARTA: An Optimization Framework for Differentially Private Sparse Fine-TuningAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025Matryoshka Model Learning for Improved Elastic Student ModelsAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 20258th Workshop on Machine Learning in FinanceAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025The 2nd Workshop on Large Language Models for E-CommerceMeta · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025SaviorRec: Semantic-Behavior Alignment for Cold-Start RecommendationAlibaba · arXiv (Cornell University)16 citationsAug 2, 2025ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language ModelsMicrosoft · arXiv (Cornell University)7 citationsAug 2, 2025WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware FrameworkMicrosoft · arXiv (Cornell University)3 citationsAug 2, 2025Generating Long Semantic IDs in Parallel for RecommendationMeta · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)73 citationsAug 1, 2025Disaggregated State Management in Apache Flink® 2.0Alibaba · Proceedings of the VLDB Endowment17 citationsAug 1, 2025Filtered Vector Search: State-of-the-Art and Research OpportunitiesAlphabet · Proceedings of the VLDB Endowment17 citationsAug 1, 2025Still Asking: How Good Are Query Optimizers, Really?Databricks · Proceedings of the VLDB Endowment11 citationsAug 1, 2025From FASTER to F2: Evolving Concurrent Key-Value Store Designs for Large Skewed WorkloadsMicrosoft · Proceedings of the VLDB Endowment10 citationsAug 1, 2025Uniform Sampling of Surfaces by Casting RaysNVIDIA · Computer Graphics Forum9 citationsAug 1, 2025TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series GenerationMicrosoft · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)9 citationsAug 1, 2025Cost-Effective, Low Latency Vector Search with Azure Cosmos DBMicrosoft · Proceedings of the VLDB Endowment8 citationsAug 1, 2025EasyAD: A Demonstration of Automated Solutions for Time-Series Anomaly DetectionMeta · Proceedings of the VLDB Endowment8 citationsAug 1, 2025Automatic Indexing in OracleAlphabet, Databricks, Meta · Proceedings of the VLDB Endowment7 citationsAug 1, 2025Synthetic Tabular Data: Methods, Attacks and DefensesMeta · Proceedings of the VLDB Endowment6 citationsAug 1, 2025From Scale-Up to Scale-Out: PolarDB's Journey to Achieving 2 Billion tpmCAlibaba · Proceedings of the VLDB Endowment6 citationsAug 1, 2025Robust real‐time segmentation of bio‐morphological features in human cherenkov imaging during radiotherapy via deep learningNVIDIA · Medical Physics5 citationsAug 1, 2025AnalyticDB-PG: A Cloud-Native High-Performance Data Warehouse in Alibaba CloudAlibaba · Proceedings of the VLDB Endowment4 citationsAug 1, 2025Bringing the Operational and Analytical Worlds Together with LakebaseDatabricks · Proceedings of the VLDB Endowment4 citationsAug 1, 2025