Publications, pre-prints and patents:

Systems for AI:

  • Y. Lu, et al. Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native. Technical Report. 2023. [PDF]

  • G. Kakkar, et al. EVA: An End-to-End Exploratory Video Analytics System. Proceedings of the 7th Workshop on Data Management for End-to-End Machine Learning. (DEEM). 2023. [PDF]

  • Y. Wu, M. Lentz, D. Zhuo, Y. Lu. Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures. International Conference on Very Large Data Bases (VLDB). Vancouver, Canada. 2023. [PDF][Code]

  • Z. Yang, Z. Wang, Y. Huang, F. Gao, Y. Lu, C. Li, X. Wang. Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models. International Conference on Very Large Data Bases (VLDB) Demo. Sydney, Australia. 2022. [PDF]

  • Z. Yang, Z. Wang, Y. Huang, Y. Lu, C. Li, X. Wang. Optimizing Machine Learning Inference Queries with Correlative Proxy Models. International Conference on Very Large Data Bases (VLDB). Sydney, Australia. 2022. [PDF]

  • P. Chunduri, J. Bang, Y. Lu, J. Arulraj. Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning. ACM International Conference on Management of Data (SIGMOD). Philadelphia, USA. 2022. [PDF]

  • Y. Lu. Building and Accelerating a Declarative Platform for Machine Learning Model Serving. Doctoral Dissertation. University of Washington. 2018. [PDF]

  • Y. Lu, A. Chowdhery, S. Kandula, S. Chaudhuri. Accelerating Machine Learning Inference with Probabilistic Predicates. ACM International Conference on Management of Data (SIGMOD). Houston, USA. 2018. [PDF][slides][Talk video][Errata]

  • Y. Lu, S. Kandula, S. Chaudhuri. Interactive Demonstration of Probabilistic Predicates. ACM International Conference on Management of Data (SIGMOD) Demo. Houston, USA. 2018. [PDF][Code]. Best Demonstration Award.

  • S. Chaudhuri, S. Kandula, Y. Lu. Accelerating machine learning inference with probabilistic predicates. US Patent App. 16/003,495.

  • Y. Lu, A. Chowdhery, S. Kandula. Optasia: A Relational Platform for Efficient Large-Scale Video Analytics. ACM Symposium on Cloud Computing (SoCC). Santa Clara, USA. 2016. [PDF][Proj][Demo][Slides].

AI for systems:

  • Y. Lu, S. Kandula, A. Konig, S. Chaudhuri. Pre-training Summarization Models of Structured Datasets for Cardinality Estimation. International Conference on Very Large Data Bases (VLDB). Sydney, Australia. 2022. [PDF][Code][Slides]

  • B. Li, Y. Lu, C. Wang, S. Kandula. Cardinality Estimation: Is Machine Learning a Silver Bullet? 3rd International Workshop on Applied AI for Database Systems and Applications (AIDB). Copenhagen, Denmark. 2021. [PDF]

  • B. Li, Y. Lu, C. Wang, S. Kandula. Q-error Bounds of Random Uniform Sampling for Cardinality Estimation. arXiv preprint 2021. arxiv:2108.02715. [PDF]

  • K. Rong, Y. Lu, P. Bailis, S. Kandula, P. Levis. Approximate Partition Selection for Big-Data Workloads using Summary Statistics. International Conference on Very Large Data Bases (VLDB). Tokyo, Japan. 2020. [PDF]

  • B. Li, Y. Lu, S. Kandula. Warper: Efficiently Adapting Learned Cardinality Estimators to Data and Workload Drifts. ACM International Conference on Management of Data (SIGMOD). Philadelphia, USA. 2022. [PDF]

  • Y. Lu, S. Kandula. Adapting Learned Cardinality Estimators to Data and Workload Drifts. US Patent App. 17566996.

AI and computer vision:

  • H. Qiu, Y. Zheng, H. Ye, Y. Lu, F. Wang, L. He. Precise Temporal Action Localization by Evolving Temporal Proposals. ACM International Conference on Multimedia Retrieval (ICMR). Yokohama, Japan. 2018. [PDF]

  • L. Wang, W. Shao, Y. Lu, H. Ye, J. Pu, Y. Zheng. Crowd Counting with Density Adaption Networks. arXiv preprint 2018. arXiv:1806:10040. [Pdf]

  • S. Lyu, et al. UA-DETRAC 2017: Report of AVSS2017 & IWT4S Challenge on Advanced Traffic Monitoring. IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). Lecce, Italy. 2017. [PDF]

  • Y. Peng, H. Ye, Y. Lin, Y. Bao, Z. Zhao, H. Qiu, Y. Lu, L. Wang, Y. Zheng. Large-Scale Video Classification with Elastic Streaming Sequential Data Processing System. ACM Multimedia Workshop on Large-Scale Video Classification Challenge (LSVC). Mountain View, USA. 2017. [PDF]

  • L. Wang, Y. Lu, H. Wang, Y. Zheng, H. Ye, X. Xue. Evolving Boxes for Fast Vehicle Detection. IEEE International Conference on Multimedia and Expo (ICME). HongKong, China. 2017. [PDF][Code&Results]. Platinum Best Paper Award.

  • Y. Lu, L. Shapiro. Closing the Loop for Object Proposals and Edge Detection. The Thirty-First AAAI Conference on Artificial Intelligence. (AAAI). San Fransisco, USA. 2017. [PDF][Slides]

  • Y. Lu, X. Bai, L. Shapiro, J. Wang. Coherent Parametric Contours for Interactive Video Object Segmentation. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA. 2016. [PDF][Proj]

  • X. Bai, J. Wang, Y. Lu. Flexible video object boundary tracking. US Patent 9,569,866.

  • Y. Lu, W. Zhang, K. Zhang, X. Xue. Semantic Context Learning with Large-Scale Weakly-Labeled Image Set. ACM Conference on Information and Knowledge Management (CIKM). Hawaii, USA, 2012. [PDF][Proj]

  • Y. Lu, W. Zhang, C. Jin, X. Xue. Learning Attention Map from Images. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR). Providence, USA. 2012. [PDF][Proj]

  • W. Zhang, Y. Lu, X. Xue, J. Fan. Automatic Image Annotation with Weakly Labeled Datasets. ACM Multimedia. Scottsdale, USA. 2011.[PDF][Proj]

  • X. Xue, W. Zhang, J. Zhang, B. Wu, J. Fan, Y. Lu. Correlative Multi-Label Multi-Instance Image Annotation. 13th International Conference on Computer Vision (ICCV). Barcelona, Spain. 2011. [PDF]

  • Y. Lu, W. Zhang, H. Lu, X. Xue. Salient Object Detection using Concavity Context. 13th IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain. 2011.[PDF][Proj]