I am a Ph.D. student at The University of Hong Kong (HKU), advised by Prof. Shenghua Gao. I am currently a research intern at Tencent Hunyuan 3D, advised by Zhuo Chen and Chunchao Guo. Before that, I earned my bachelor’s and master’s degrees from Tianjin University.
My research is driven by curiosity, and I enjoy exploring different fields. My current research focuses on 3D generation. Before that, I worked closely with Prof. Hao Wang at HKUST(GZ) on 3D reconstruction and SfM/SLAM, and with Prof. Ying He at NTU on computer graphics.
Outside of research, I love playing 2D metroidvania and platformer games (e.g., I have unlocked all achievements in Celeste), as well as 3D souls-like games (e.g., I have spent 1,500+ hours in Elden Ring: Nightreign).
* Equal contribution
NeurIPS 2026
Advances in Neural Information Processing Systems (NeurIPS), 2026 Spotlight
@inproceedings{song2026meshbdf,
title = {Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation},
author = {Song, Gaochao and Weng, Haohan and Zhang, Luo and Zhao, Zibo and Gao, Shenghua},
booktitle = {Advances in Neural Information Processing Systems},
year = {2026}
}
ICLR 2026
International Conference on Learning Representations (ICLR), 2026
@inproceedings{song2026meshsilksong,
title = {Topology-Preserved Auto-Regressive Mesh Generation in the Manner of Weaving Silk},
author = {Song, Gaochao and Zhao, Zibo and Weng, Haohan and Zeng, Jingbo and Jia, Rongfei and Gao, Shenghua},
booktitle = {International Conference on Learning Representations},
year = {2026}
}
Computer-Aided Design, 2026
@article{zhang2026text2csg,
title = {Text2CSG: Generating CAD Models from Natural Language via Constructive Solid Geometry},
author = {Zhang, Luo and Song, Gaochao and Rao, Haocong and Wen, Zhengyu and Hu, Jiangbei and He, Ying},
journal = {Computer-Aided Design},
pages = {104127},
year = {2026}
}
ICLR 2025
International Conference on Learning Representations (ICLR), 2025
@inproceedings{cheng2025graphgs,
title = {Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting},
author = {Cheng, Chong and Song, Gaochao and Yao, Yiyang and Zhou, Qinzheng and Zhang, Gangjian and Wang, Hao},
booktitle = {International Conference on Learning Representations},
year = {2025}
}
Remote Sensing, 17(8): 1458, 2025
@article{zang2025dbmfenet,
title = {DB-MFENet: A Dual-Branch Multi-Frequency Feature Enhancement Network for Hyperspectral Image Classification},
author = {Zang, Chen and Song, Gaochao and Li, Lei and Zhao, Guangrui and Lu, Wanxuan and Jiang, Guiyuan and Sun, Qian},
journal = {Remote Sensing},
volume = {17},
number = {8},
pages = {1458},
year = {2025}
}
NeurIPS 2024
Advances in Neural Information Processing Systems (NeurIPS), 2024
@inproceedings{song2024gvkf,
title = {GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes},
author = {Song, Gaochao and Cheng, Chong and Wang, Hao},
booktitle = {Advances in Neural Information Processing Systems},
volume = {37},
pages = {104792--104815},
year = {2024}
}
Computer Aided Geometric Design, 111: 102322, 2024
@article{li2024realtime,
title = {Real-Time Volume Rendering with Octree-Based Implicit Surface Representation},
author = {Li, Jiaze and Zhang, Luo and Hu, Jiangbei and Zhang, Zhebin and Sun, Hongyu and Song, Gaochao and He, Ying},
journal = {Computer Aided Geometric Design},
volume = {111},
pages = {102322},
year = {2024}
}
CVPR 2023
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
@inproceedings{song2023opesr,
title = {OPE-SR: Orthogonal Position Encoding for Designing a Parameter-Free Upsampling Module in Arbitrary-Scale Image Super-Resolution},
author = {Song, Gaochao and Sun, Qian and Zhang, Luo and Su, Ran and Shi, Jianfeng and He, Ying},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {10009--10020},
year = {2023}
}
I'm always happy to discuss research ideas and potential collaborations. The best way to reach me is via email.