Chengyue Wu - 吴成岳

Biography

Chengyue Wu is a second year Ph.D. student at the Department of Computer Science, The University of Hong Kong (HKU), fortunately advised by Prof. Ping Luo and Prof. Wenping Wang (IEEE Fellow and ACM Fellow). Previously, Chengyue obtained his Bachelor’s degree from Harbin Institute of Technology (HIT) in June 2023.

His current research interest lies at Vision-Language models, Large Language Model (LLM).

Education

  • Ph.D. in Computer Science, The University of Hong Kong, 2023-now
    • Supervisor: Prof. Ping Luo and Prof. Wenping Wang
    • Hong Kong PhD Fellowship Scheme (HKPFS)
  • B.Eng. in Computer Science, Harbin Institute of Technology, 2019-2023
    • GPA: 95.56 / 100, Rank: 1 / 144

Publications

  • Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
    • Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, Ping Luo
    • Arxiv 2024.10 [paper] [project page]
  • JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
    • Yiyang Ma, Xingchao Liu, Xiaokang Chen, Wen Liu, Chengyue Wu, Zhiyu Wu, Zizheng Pan, Zhenda Xie, Haowei Zhang, Liang Zhao, Yisong Wang, Jiaying Liu, Chong Ruan
    • Arxiv 2024.11 [paper] [project page]
  • Autoregressive Models in Vision: A Survey
    • Jing Xiong, Gongye Liu, Lun Huang, Chengyue Wu, Taiqiang Wu, Yao Mu, Yuan Yao, Hui Shen, Zhongwei Wan, Jinfa Huang, Chaofan Tao, Shen Yan, Huaxiu Yao, Lingpeng Kong, Hongxia Yang, Mi Zhang, Guillermo Sapiro, Jiebo Luo, Ping Luo, Ngai Wong
    • Arxiv 2024.11 [paper] [project page]
  • Llama pro: Progressive llama with block expansion
    • Chengyue Wu, Yukang Gan, Yixiao Ge, Zeyu Lu, Jiahao Wang, Ye Feng, Ping Luo, Ying Shan
    • ACL 2024, Main Conference [paper] [project page]
  • $\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
    • Chengyue Wu, Teng Wang, Yixiao Ge, Zeyu Lu, Ruisong Zhou, Ying Shan, Ping Luo
    • ICML 2023 [paper] [project page]
  • Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots
    • Chengyue Wu, Yixiao Ge, Qiushan Guo, Jiahao Wang, Zhixuan Liang, Zeyu Lu, Ying Shan, Ping Luo
    • Arxiv 2024.05 [paper] [project page]
  • Hierarchical diffusion autoencoders and disentangled image manipulation
    • Zeyu Lu, Chengyue Wu, Xinyuan Chen, Yaohui Wang, Lei Bai, Yu Qiao, Xihui Liu
    • WACV 2024 [paper]
  • Fit: Flexible vision transformer for diffusion model
    • Zeyu Lu, Zidong Wang, Di Huang, Chengyue Wu, Xihui Liu, Wanli Ouyang, Lei Bai
    • ICML 2024, spotlight [paper] [project page]
  • Seeing is not always believing: benchmarking human and model perception of AI-generated images
    • Zeyu Lu, Di Huang, Lei Bai, Jingjing Qu, Chengyue Wu, Xihui Liu, Wanli Ouyang
    • Neurips 2023 [paper] [project page]
  • Generative data augmentation for non-iid problem in decentralized clinical machine learning
    • Zirui Wang, Shaoming Duan, Chengyue Wu, Wenhao Lin, Xinyu Zha, Peiyi Han, Chuanyi Liu
    • ICDIS 2022 [paper]
  • Automatic time series forecasting model design based on pruning
    • Chunnan Wang, Xingyu Chen, Chengyue Wu, Hongzhi Wang
    • Applied Soft Computing [paper]
  • Adapting LLaMA Decoder to Vision Transformer
    • Jiahao Wang, Wenqi Shao, Mengzhao Chen, Chengyue Wu, Yong Liu, Kaipeng Zhang, Songyang Zhang, Kai Chen, Ping Luo
    • Arxiv 2024.04 [paper] [project page]

Honors & Awards

  • Hong Kong PhD Fellowship Scheme (HKPFS), 2023
  • HKU Presidential PhD Scholarship (HKU-PS), 2023
  • Outstanding Graduate of Heilongjiang Province, 2023
  • National Scholarship, 2020