Haoming Liu is a Ph.D. student in Computer Science, advised by Professor Hongyi Wen in the MAPS Research Group. Prior to that, he earned his B.S. degree in Computer Science from NYU Shanghai and graduated with the the Dean’s Award in Computer Science, Data Science, and Engineering. Currently, his research interest lies in investigating and uncovering the hidden dynamics in deep generative models, such as Diffusion and LLMs, thereby achieving better cross-modality alignment and personalized services.
Publications
- Liu, Haoming, Guo, Yuanhe, Wang, Shengjie, and Wen, Hongyi, “Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations,” arXiv preprint arXiv:2312.08873, 2023.
- Guo, Yuanhe, Liu, Haoming, and Wen, Hongyi, “GEMRec: Towards Generative Model Recommendation,” in Proceedings of the 17th ACM International Conference on Web Search and Data Mining, 2024.
- Liu, Haoming, Guo, Li, Zhou, Zhongwen, and Zhang, Hanyuan, “Pyramid-Context Guided Feature Fusion for RGB-D Semantic Segmentation,” in Proceedings of the 2022 IEEE International Conference on Multimedia and Expo Workshops, 2022.
Research Interests
- Deep Generative Models
- Cross-Modality Alignment
- Controllable Image Generation