胡心亭
邮 件：xinting@ustc.edu.cn
所属单位：人工智能与数据科学学院
个人主页： https://joyhuyy1412.github.io/
主要研究方向：生成式人工智能、多模态推理与学习、持续学习与弱监督学习
2018年获得中国科学技术大学信息科学与技术专业学士学位，2023年获得新加坡南洋理工大学计算机专业博士学位。2022年6月至2025年7月在德国马克思·普朗克信息研究所从事博士后研究，2025年7月至2026年2月在香港大学从事博士后研究。2026年3月起任中国科学技术大学人工智能与数据科学学院教授。长期从事人工智能、计算机视觉与多模态学习研究，在生成式人工智能、多模态推理、持续学习、半监督学习等方向取得了一系列代表性成果。相关成果发表于CVPR、ICLR等国际高水平会议，获德国马克思·普朗克学会 Lise Meitner 奖学金。
近几年代表论著：
[1] Xinting Hu, Haoran Wang, Jan Eric Lenssen, Bernt Schiele. PersonaHOI: Effortlessly Improving Face Personalization in Human-Object Interaction Generation, 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
[2] Yongliang Wu, Xinting Hu, Yuyang Sun, Yizhou Zhou, Wenbo Zhu, Fengyun Rao, Bernt Schiele, Xu Yang. Number it: Temporal Grounding Videos like Flipping Manga, 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
[3] Junchao Huang, Xinting Hu, Shaoshuai Shi, Zhuotao Tian, Li Jiang. Edit360: 2D Image Edits to 3D Assets from Any Angle, 2025 IEEE/CVF International Conference on Computer Vision (ICCV)
[4] Xinyuan Zhu, Jiadong Lu, Xinting Hu, Tengchuan Jin, Shan Lu, Fuli Feng. Hierarchical Progressive Learning for Zero-Shot Peptide-HLA Binding Prediction and Automated Antigenic Peptide Design, Cell Reports, Volume 44, Issue 6, 2025.
[5] Xinting Hu, Li Jiang, Bernt Schiele. Training Vision Transformers for Semi-Supervised Semantic Segmentation, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
[6] Anurag Das, Xinting Hu, Li Jiang, Bernt Schiele. MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment, European Conference on Computer Vision (ECCV)
[7] Yingzhe Peng, Chenduo Hao, Xinting Hu, Jiawei Peng, Xin Geng, Xu Yang. LIVE: Learnable In-Context Vector for Visual Question Answering, Advances in Neural Information Processing Systems, 2024.
[8] Xinting Hu, Yulei Niu, Chunyan Miao, Xian-Sheng Hua, Hanwang Zhang. On Non-Random Missing Labels in Semi-Supervised Learning, 10th International Conference on Learning Representations, 2022