霍赋硕 (Fushuo Huo)研究员
电话：18751795276
办公室：李文正图书馆4楼
个人主页：https://huofushuo.github.io/
邮箱：fushuohuo@seu.edu.cn
教育背景
学术兼职
研究领域
人工智能安全；AI4CyberSecurity;
(多模态)大模型；具身智能；
招生计划:
如果您对上述方向感兴趣(本科生/硕士生/博士生/博士后)，对科研有热情，欢迎邮件联系 :)
研究概况
每周和每位学生线上交流一次，氛围轻松；
同时和港科/港理工、上交/华科、南洋理工、华为相关课题组线上定期交流。
研究课题
主持项目
隐私保护的个性化多模态主动式智能体 —— 国家自然科学基金优秀青年科学基金项目(海外)
扩散先验约束的多模态大模型隐式推理技术研究 —— 国家自然科学基金青年科学基金项目（C类）
Towards Personalized Multimodal Proactive Agent —— 香港科技大学博士后配套资金
参与项目
Editable Learning with Fast Adaptation over Evolutionary Edges —— 香港研究资助局基金
Collaborative Training in Resource‑constrained Edge Networks via Generative Mutual Knowledge Transfer —— 香港研究资助局基金
面向人机协同的边缘计算开放系统研发及应用 —— 广东省重点研发“新一代人工智能”专项
奖励与荣誉
东南大学青年首席教授、博士生导师，入选国家高层次青年人才计划。
课程信息
学术成果
Selected Publications
*: students mentored by me
Y. Shi* (SEU Undergraduate), K. Wei, F. Huo, S. Wu, and C. Ma, “One Trap to Block Them All: Defending Encoder Stealing via Isotropic Uniformity,”European Conference on Computer Vision (ECCV), 2026.[News]
H. Peng* , H. Li, J. Chen, Y. Pan, R. Yao, Y. Dai, F. Huo, F. Hong, Z. Chen, H. Wang, D. Zhang, Z. Liu, W. Xu, “SpatialBench: Is Your Spatial Foundation Model an All-Round Player,”Neural Information Processing System (NeurIPS), 2026.[Project]
Y. Pan*, H. Peng, Z. Zhang, Z. Yan, Y. Dai, F. Huo, C. Wang, T. Qi, X. Wang, N. Cheng, W. Xu, “World‑to‑Wrist: Task‑Conditioned Future Wrist Modeling for Fine‑Grained Robot Manipulation,”arXiv:2608.05369, 2026.[Project]
Y. Pan*, X. Wang, F. Huo, N. Cheng, and W. Xu, “Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training,”IEEE Transactions on Cognitive Communications and Networking (TCCN), 2026.
Q. Nguyen*, S. Liang, Y. Li, F. Huo, D. Tao, “TimeGuard: Channel‑wise Pool Training for Backdoor Defense in Time Series Forecasting,”International Conference on Machine Learning (ICML), 2026.
Y. Cui*, P. Qi, F. Huo, H. Du, W. Shi, J. Dai, Z. Zhu, S. Han, Y. Guo, “Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection,”Annual Meeting of the Association for Computational Linguistics (ACL) main track, 2026.
F. Huo, W. Xu, Z. Zhang, H. Wang, Z. Chen, P. Zhao, “Self‑Introspective Decoding: Alleviating Hallucinations for Large Vision‑Language Models,”International Conference on Learning Representations (ICLR), 2025.150+ Citation.
Y. Fan, W. Xu, H. Wang, F. Huo, J. Chen, and S. Guo, “Overcome Modal Bias in Multi‑modal Federated Learning via Balanced Modality Selection,”European Conference on Computer Vision (ECCV), 2024.
F. Huo, W. Xu, J. Guo, H. Wang, and S. Guo, “C2KD: Bridging the Modality Gap for Cross‑Modal Knowledge Distillation,”Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024,Highlight.150+ Citation.
F. Huo, W. Xu, S. Guo, J. Guo, H. Wang, and Z. Liu, “PROCC: Progressive cross‑primitive consistency for open‑world compositional zero‑shot learning,”Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024.
F. Huo, W. Xu, J. Guo, H. Wang, Y. Fan, and S. Guo, “Non‑Exemplar Online Class‑incremental Continual Learning via Dual‑prototype Self‑augment and Refinement,”Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024.
F. Huo, X. Zhu, L. Zhang, Q. Liu, and Y. Shu, “Efficient Context‑Guided Stacked Refinement Network for RGB‑T Salient Object Detection,”IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022.200+ Citation.
其他
最近动态
