【详细信息】

高俊龙，博士，现为yl8cc永利官网计算机科学与技术系助理教授，硕士生导师。2024年7月于北京大学获得计算机应用技术理学博士学位，2024年8月于商汤科技研究院担任算法研究员，从事多模态大模型相关研究，2025年3月加入yl8cc永利官网。目前主要研究方向包括多模态大模型、图像视频编码、图像视频生成、计算机视觉等机器学习前沿领域。迄今共发表多篇顶级国际期刊会议论文，包括CVPR、TMM、TCSVT、DCC等；在国内视频压缩标准AVS接收技术提案多项。

招收硕士生和对科研感兴趣的本科生，欢迎对深度学习以及相关领域有兴趣的同学联系我。

【代表性论文】

[1] Junlong Gao; Shiqi Wang; Shanshe Wang; Siwei Ma; Wen Gao; Self-critical N-step Training for Image Captioning, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019: 6300-6308.

[2] Junlong Gao; Jiguo Li; Chuanmin Jia; Shanshe Wang; Siwei Ma; Wen Gao; Cross Modal Compression with Variable Rate Prompt, IEEE Transactions on Multimedia (TMM), 2023, 26: 3444-3456.

[3] Junlong Gao; Chuanmin Jia; Zhimeng Huang; Shanshe Wang; Siwei Ma; Wen Gao; Ratedistortion Optimized Cross Modal Compression with Multiple Domains, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024, 34(8): 6978-6992.

[4] Junlong Gao; Chuanmin Jia; Shanshe Wang; Siwei Ma; Wen Gao; Rate-distortion Optimization for Cross Modal Compression, Data Compression Conference (DCC), 2023: 218-227.

[5] Zhimeng Huang; Junlong Gao; Jiaqi Zhang; Shanshe Wang; Siwei Ma; Chuanmin Jia; Image Coding for Machine with Visual-Language Mimic Feature Learning, Data Compression Conference (DCC), 2025.

[6] Siwei Ma; Junlong Gao; Ruofan Wang; Jianhui Chang; Qi Mao; Zhimeng Huang; Chuanmin Jia; Overview of Intelligent Video Coding: from Model-based to Learning-based Approaches, Visual Intelligence, 2023, 1: 15-34.