杨育彬教授领衔的VCU (Visual/Volume Computing & Understanding，视觉/大数据计算及理解)研究组隶属于南京大学计算机软件新技术国家重点实验室和南京大学计算机科学与技术系。
研究成果已发表于CVPR、NeurIPS、ICLR、AAAI、IEEE TMM、ACM MM、ICDM、ECAI、ICASSP、ICMR、ICME、Machine Learning、Pattern Recognition等CCF A/B类会议和期刊, 获国家发明专利授权 30余项，软件著作权6项，并在国家电网、华为等大型企业应用实施。
欢迎各位有能力&有兴趣的同学加入VCU的大家庭！
Vision-Oriented Lightweight Neural Architecture Search with Budget-Adaptive Evaluation
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026)
Test-time Domain Generalization for Image Super-resolution
The Fourteenth International Conference on Learning Representations (ICLR 2026)
LDT: Layer-Decomposition Training Makes Networks More Generalizable
The Fourteenth International Conference on Learning Representations (ICLR 2026)
Hyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook Strategy
Forty-Third International Conference on Machine Learning (ICML 2026)
课程讲义与课后作业。
课程简介、计算机视觉简介与图像生成/早期视觉专题。