Short Bio

Jianguo Li (in some early publications Jianguo Lee) is a tech-director with Ant Group since June 2020. He had been a research scientist with Intel Labs after he got his PhD degree from Tsinghua University. His research interests includes machine learning, deep learning and their applications in vision, hardware, cloud system, and other domains. 

During his tenure at Intel, he won 3 Intel Labs highest Gordy award (in the name of Gordon Moore) including 1 single personal award in 2020 for his great tech contributions. At Ant Group, he led team won 1 T-Star award (highest at CTO BG) in 2021 and 1 SuperMA (highest the whole company) in 2022. His work at Intel has been transferred to and shipped with some Intel Products, including hardware features on CPU & accelerators.  His work at Ant has been widely utilized in various infrastructure of Ant Group. He led the development of the CodeFuse LLM project in Ant Group. 

He had published 60+ peer-reviewed papers with 10,000+ citations in top-tier conferences/journals, and hold 50+ US issued patents. He also led team to win or perform top on several well-known scientific challenges. He is a senior member of IEEE. 

Full Resume

News:  we release CodeFuse, an LLM dedicating for coding, visiting our huggingface, github, ModelScope page for more details. 

Selected Publications 

Note: * for my students & interns

1. Functional Relation Field: A Model-Agnostic Framework for Multivariate Time Series Forecasting

Ting Li, Bing Yu, Jianguo Li, Zhanxing Zhu

Artificial Intelligence 2024, accepted

2. DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

Zhaoru Ke, Hang Yu, Jianguo Li, Haipeng Zhang

ICML 2024, accepted

3. MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning

Bingchang Liu, Chaoyu Chen, Zi Gong, Cong Liao, Wanghuanh, Zhichao Lei, Ming Liang, Chen Dajun, Min Shen, Hailian Zhou, wei jiang, Hang Yu, Jianguo Li

KDD 2024, accepted

4. D2LLM: Decomposed and Distilled Large Language Models for Semantic Search

Zihan Liao, Hang Yu, Jianguo Li, Jun Wang, Wei Zhang

ACL 2024, accepted

5. CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending

Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue, Qi Zhang, Yifan Wu, Jianguo Li

ACL 2024, accepted

6. Enabling Efficient Batch Serving for LMaaS via Generation Length Prediction

Ke Chen, Wen Hu, Zhi Wang, Peng Du, Jianguo Li, Sheng Zhang

ICWS 2024, accepted

7. DeepScaling: Autoscaling Microservices with Stable CPU Utilization for Large Scale Production Cloud Systems 

Ziliang Wang, Shiyi Zhu, Jianguo Li, Wei Jiang,  K. K. Ramakrishnan, ..., Alex X. Liu

IEEE/ACM Trans. on Networking, accepted

8. VDTuner: Automated Performance Tuning for Vector Data Management Systems

Tiannuo Yang, Wen Hu, Wangqi Peng, Yusen Li, Jianguo Li, Gang Wang, Xiaoguang Liu

ICDE 2024, [paper] [code]

9. Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression

Yufeng Zhang, Hang Yu, Jianguo Li, Weiyao Lin

ICLR 2024, spotlight  [paper] [code]

10. AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification

Hang Yu, Cong Liao, Ruolan Liu, Jianguo Li, Yun Hu, Xinzhe Wang

ICLR 2024 [paper]

11. BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

Zelin Ni, Hang Yu, Shizhan Liu, Jianguo Li, Weiyao Lin

NeurIPS 2023 [paper] [code]

12. Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

Ting Li, Jianguo Li, Zhanxing Zhu

NeurIPS 2023 

13. Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System

Jun Huang, Yang Yang, Hang Yu, Jianguo Li, Xiao Zheng

ASE 2023 

14. ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification
    Kaihao Guo, Hang Yu, Cong Liao, Jianguo Li, Haipeng Zhang
    ACL 2023 Findings  [paper]

15. BALANCE: Bayesian Linear Attribution for Root Cause Localization
    Chaoyu Chen, Hang Yu, Zhichao Lei, Jianguo Li, Shaokang Ren, Tingkai Zhang, Silin Hu, Jianchao Wang, Wenhui Shi
    SIGMOD 2023  [paper]

16. An Empirical Study on Change-induced Incidents of Online Service Systems
    Yifan Wu, Bingxu Chai, Ying Li, Bingchang Liu, Jianguo Li, Yong Yang, Wei Jiang
    ICSE (SEIP) 2023

17. Pyraformer: Low complexity pyramidal Attention For Long-range Time Series Modeling and Forecasting
    Shizhan Liu*, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin...
    ICLR 2022 Oral (1.6%)  [paper] [code]

18. DeepScaling: Microservices AutoScaling for Stable CPU Utilization in Large Scale Cloud Systems
    Ziliang Wang, Shiyi Zhu, Jianguo Li, Wei Jiang,  K. K. Ramakrishnan, ..., Alex X. Liu
    ACM SoCC 2022 [Slides]

19. Investigating and Improving Log Parsing in Practice
    Ying Fu, Meng Yan, Jian Xu, Jianguo Li, Zhongxin Liu, Xiaohong Zhang, Dan Yang
    ACM ESEC/FSE 2022

20. Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
    Hongyuan Yu*, Ting Li, Weicheng Yu, Jianguo Li, Yan Huang, Liang Wang...
    IJCAI 2022

21. A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud
    Siqiao Xue, Chao Qu, Xiaoming Shi, Cong Liao, Shiyi Zhu, ..., Jianguo Li and James Zhang
    KDD 2022

22. Learning Scale-Consistent Attention Part Network for Fine-grained Image Recognition
    Huabing Liu*, Jianguo Li, Dian Li, Weiyao Lin
    IEEE Trans. Multimedia 2021.

23. Variational Pedestrian Detection
    YuAng Zhang*, Huanyu He*, Jianguo Li, Yuxi Li, John See, Weiyao Lin
    CVPR 2021

24. Toward Accurate Visual Reasoning With Dual-Path Neural Module Networks
    Ke Su*, Hang Su, Jianguo Li, Jun Zhu
    Frontiers in Robotics and AI published 2020.

25. Story driven Video Editing
    Zheng Wang, Jianguo Li, Yu-Gang Jiang
    IEEE Trans. Multimedia 2021.

26. ATRW: A benchmark for Amur Tiger Re-Identification in the Wild
    Shuyuan Li, Jianguo Li, Hanlin Tang, Rui Qian, Weiyao Lin
    ACM Multimedia 2020

27. AP-Loss for Accurate One-Stage Object Detection
    Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Junni Zou
    IEEE Trans. on PAMI Accepted, April. 2020 [Code]

28. Few Sample Knowledge Distillation for Efficient Network Compression
    Tianhong Li, Jianguo Li, Zhuang Liu, Changshui Zhang
    CVPR 2020

29. Object Detection from Scratch with Deep Supervision
    Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, Xiangyang Xue
    IEEE Trans. on PAMI Feb., 2020

30. Towards Accurate One-Stage Object Detection with AP-Loss
    Kean Chen, Jianguo Li, Weiyao Lin, John See, et al.
    CVPR 2019

31. Stochastic Quantization for Learning Accurate Low-bit Deep Neural Networks
    Yinpeng Dong, Renkun Ni, Jianguo Li, Yurong Chen, Hang Su, Jun Zhu
    IJCV Mar., 2019

32. Composite Binary Decomposition Networks
    You Qiaoben, Zheng Wang, Jianguo Li, Yinpeng Dong, Yu-Gang Jiang, Jun Zhu
    AAAI 2019

33. Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
    Yuxi Li, Jiuwei Li, Weiyao Lin, Jianguo Li
    BMVC 2018 [Code]

34. Network Decoupling: From Regular to Depthwise Separable Convolutions
    Jianbo Guo, Yuxi Li, Weiyao Lin, Yurong Chen, Jianguo Li
    BMVC 2018 [Code]

35. Visual Content Recognition by Exploiting Semantic Feature Map with Attention and Multi-task Learning
    Rui-wei Zhao, Qi Zhang, Zuxuan Wu, Jianguo Li, Yu-gang Jiang
    ACM ToMM Vol 1. 2019

36. Boosting Adversarial Attacks with Momentum
    Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, Jianguo Li
    CVPR 2018 (spotlight) [Code]

37. Learning Visual Knowledge Memory Networks for Visual Question Answering
    Zhou Su, Chen Zhu, Yinpeng Dong, Dongqi Cai, Yurong Chen, Jianguo Li
    CVPR 2018

38. Learning Semantic Feature Map for Visual Content Recognition
    Rui-wei Zhao, Zuxuan Wu, Jianguo Li, Yu-Gang Jiang
    ACM Multimedia 2017 (full-length research paper)

39. Learning Efficient Convolutional Networks through Network Slimming
    Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang
    ICCV 2017 [Code]

40. DSOD: Learning Deeply Supervised Object Detectors from Scratch
    Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, Xiangyang Xue
    ICCV 2017 [Code]

41. BodyFusion: Real-time Capture of Human Motion and Surface Geometry Using a Single Depth Camera
    Tao Yu, Kaiwen Guo, Feng Xu, Yuan Dong, Zhaoqi Su, Jianhui Zhao, Jianguo Li, Qionghai Dai and Yebin Liu
    ICCV 2017 [Project Page]

42. Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
    Yinpeng Dong, Renkun Ni, Jianguo Li, Hang Su, Jun Zhu
    BMVC 2017 (Oral) [Code] (best paper finalist)

43. Weakly Supervised Dense Video Captioning
    Zhiqiang Shen, Jianguo Li, Zhou Su, Minjun Li, Yurong Chen, Yu-Gang Jiang, Xiangyang Xue
    CVPR 2017

44. Binary Optimized Hashing
    Qi Dai, Jianguo Li, Jingdong Wang, Yu-Gang Jiang
    ACM Multimedia 2016 (full-length oral paper)

45. Regional Gating Neural Networks for Multi-Label Image Classification
    Rui-wei Zhao, Jianguo Li, Yurong Chen, Yu-Gang Jiang
    BMVC 2016 (oral)

46. A Bayesian Hashing approach and its application to face recognition
    Qi Dai, Jianguo Li, Jun Wang, Yurong chen, Yu-Gang Jiang
    Neurocomputing June, 2016

47. Deep Attributes from Context-Aware Regional Neural Codes
    Jianwei Luo, Jianguo Li
    [CoRR abs/1509.02470]

48. Optimal Bayesian Hashing for Efficient Face Recognition
    Dai Qi, Jianguo Li, Jun Wang, Yu-Gang Jiang
    IJCAI 2015

49. Learning SURF Cascade for Fast and Accurate Object Detection
    Jianguo Li
    CVPR 2013[Project page]

50. Interactive Object Segmentation from Multi-view Images
    Anh Nguyen, Jianfei Cai, Jianmin Zheng, Jianguo Li
    Journal of Visual Communication and Image Representation, 2013.

51. Face Detection Using SURF Cascade
    Jianguo Li, Tao Wang
    ICCV 2011 workshop on BeFIT. [Project Page]

52. Bundled Depth-Map Merging for Multi-View Stereo
    Jianguo Li, Eric Li, Yurong Cheng, Lin Xu
    CVPR 2010 (oral) [webpage]

53. A general texture mapping framework for image-based 3D modeling
    Lin Xu, Eric Li, Jianguo Li, Yurong Chen
    ICIP 2010.

54. Accelerating Video-Mining Applications Using Many Small, General-Purpose Cores
    Eric Li, Wenlong Li, Xiaofeng Tong, Jianguo Li, et al.
    IEEE Micro vol. 28, no. 5, pp. 8-21, 2008.

55. One step beyond histograms: image representation using Markov stationary features
    Jianguo Li, Weixin Wu, Tao Wang
    CVPR 2008 (Oral) [Win32 binary toolkit]

56. Novel parallel Hough transform on multi-core processors
    Yen-Kuang Chen, Wenlong Li, Jianguo Li, et al.
    ICASSP 2008.

57. Discriminant Additive Tangent Space for Object Recognition
    Liang Xiong, Jianguo Li, Changshui Zhang
    CVPR 2007

58. Cast Indexing for videos by ncuts and page ranking
    Yong Gao, Tao Wang, Jianguo Li, et al.
    ACM CIVR 2007.

59. Generalized Additive Bayesian Network Classifiers
    Jianguo Li, Changshui Zhang, Tao Wang
    IJCAI 2007

60. Face Recognition using Integral Gabor-Haar Transformation
    Jianguo Li, Tao Wang, Yimin Zhang
    IEEE ICIP 2007.[SDK]

61. Semantic Event Detection using Conditional Random Fields
    Tao Wang, Jianguo Li, et al.
    In: Proc. CVPR 2006 Workshop; 109~116

62. Soccer highlight detection Using two-dependence Bayesian network
    Jianguo Li, Tao Wang, et al.
    ICME 2006

63. Classification of Gene-expression Data: the Manifold based Metric Learning Way
    Jianguo Lee, Changshui Zhang
    Pattern Recognition, 39:2450-2463, 2006

64. Visual Object Recognition using Probabilistic Kernel Subspace Similarity
    Jianguo Lee, Jingdong Wang, Changshui Zhang, Zhaoqi Bian
    Pattern Recognition, 38: 997-1008, 2005

65. Probabilistic Tangent Subspace: A Unified View
    Jianguo Lee, Jingdong Wang, Changshui Zhang, Zhaoqi Bian
    ICML 2004

66. Kernel trick embedded Gaussian Mixture model
    Jingdong Wang, Jianguo Lee, Changshui Zhang
    In Algorithmic Learning Theory, 2003

67. Color Image Segmentation: Kernel Do the Feature Space
    Jianguo Lee, Jingdong Wang, Changshui Zhang
    ECML 2003