CV

Education

• M.S. in Computer Applied Technology, Peking University, 2021
  • Document Analysis
  • Table Detection & Recognition
• B.S. in Computer Science & Technology, Peking University, 2018

Work experience

• 2021.7 - present: Algorithm Engineer @ Alibaba Group
  • Model inference optimization in AI Earth team
  • Neural Architecture Search, Object Detection, Quantization in TinyML team
  • Data-Centric LLMs, Multimodal LLMs in SysML team

Publications

Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models

Jiao, Qirui, Daoyuan Chen, Yilun Huang, Yaliang Li, and Ying Shen. "Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models." arXiv preprint arXiv:2408.04594 (2024).

Data-Juicer Sandbox: A Comprehensive Suite for Multimodal Data-Model Co-development

Chen, Daoyuan, Haibin Wang, Yilun Huang, Ce Ge, Yaliang Li, Bolin Ding, and Jingren Zhou. "Data-Juicer Sandbox: A Comprehensive Suite for Multimodal Data-Model Co-development." arXiv preprint arXiv:2407.11784 (2024).

The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective

Qin, Zhen, Daoyuan Chen, Wenhao Zhang, Liuyi Yao, Yilun Huang, Bolin Ding, Yaliang Li, and Shuiguang Deng. "The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective." arXiv preprint arXiv:2407.08583 (2024).

Enhancing Multimodal Large Language Models with Vision Detection Models: An Empirical Study

Jiao, Qirui, Daoyuan Chen, Yilun Huang, Yaliang Li, and Ying Shen. "Enhancing Multimodal Large Language Models with Vision Detection Models: An Empirical Study." arXiv preprint arXiv:2401.17981 (2024).

Data-Juicer: A One-Stop Data Processing System for Large Language Models

Chen, Daoyuan, Yilun Huang, Zhijian Ma, Hesen Chen, Xuchen Pan, Ce Ge, Dawei Gao et al. "Data-juicer: A one-stop data processing system for large language models." In Companion of the 2024 International Conference on Management of Data, pp. 120-134. 2024.

DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network

Shen, Xuan*, Yaohua Wang*, Ming Lin, Yilun Huang, Hao Tang, Xiuyu Sun, and Yanzhi Wang. "DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6163-6173. 2023.

DAMO-YOLO : A Report on Real-Time Object Detection Design

Xu, Xianzhe*, Yiqi Jiang*, Weihua Chen*, Yilun Huang*, Yuan Zhang*, and Xiuyu Sun. "DAMO-YOLO: A Report on Real-Time Object Detection Design." arXiv preprint arXiv:2211.15444 (2022).

Rethinking table structure recognition using sequence labeling methods

Li, Yibo, Yilun Huang, Ziyi Zhu, Lemeng Pan, Yongshuai Huang, Lin Du, Zhi Tang, and Liangcai Gao. "Rethinking table structure recognition using sequence labeling methods." In International Conference on Document Analysis and Recognition, pp. 541-553. Springer, Cham, 2021.

NTable: A Dataset for Camera-Based Table Detection

Zhu, Ziyi, Liangcai Gao, Yibo Li, Yilun Huang, Lin Du, Ning Lu, and Xianfeng Wang. "NTable: A Dataset for Camera-Based Table Detection." In International Conference on Document Analysis and Recognition, pp. 117-129. Springer, Cham, 2021.

A YOLO-based table detection method

Huang, Yilun, Qinqin Yan, Yibo Li, Yifan Chen, Xiong Wang, Liangcai Gao, and Zhi Tang. "A YOLO-based table detection method." In 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 813-818. IEEE, 2019.

A GAN-based feature generator for table detection

Li, Yibo, Liangcai Gao, Zhi Tang, Qinqin Yan, and Yilun Huang. "A GAN-based feature generator for table detection." In 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 763-768. IEEE, 2019.

ICDAR 2019 Competition on Table Detection and Recognition (cTDaR)

Gao, Liangcai, Yilun Huang, Hervé Déjean, Jean-Luc Meunier, Qinqin Yan, Yu Fang, Florian Kleber, and Eva Lang. "ICDAR 2019 competition on table detection and recognition (cTDaR)." In 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510-1515. IEEE, 2019.