I am a PhD student at MMLab@HKUST, The Hong Kong University of Science and Technology, supervised by Anyi Rao and Hongbo Fu. I am the recipient of IEEE Signal Processing Society (SPS) Scholarship and BSIG Outstanding Thesis Award. I am fortunate to have experiences at NLPR@CASIA, Tencent, MicroSoft Research Lab Asia (MSRA), SenseTime Research, and MMLab@NTU.
🔈JOIN US!
Inspired by Richard Feynman’s “What I cannot create, I do not understand,” I aim to understand and enhance human intelligence through generative AI. My research seeks to advance multimodal AIGC to spark human creativity while prioritizing safety and ethics.
Do not hesitate to drop me an email for any possible collaboration if you are interested in these directions:- Foundation Model: Generation Model, Unified Multimodal Model, and Agentic System
- Creator-Machine Co-Learning: Personalization, Interactivity, and Assessment
- Trustworthy AIGC: Robustness, Privacy, Watermark, and Detection
🔥 News
∙ 2026/01: One paper is accepted by ICLR 2026.
∙ 2025/12: One paper is accepted by Pattern Recognition.
∙ 2025/11: One paper is accepted by AAAI 2026.
∙ 2025/09: I am granted by IEEE Signal Processing Society (SPS) Scholarship!.
∙ 2025/07: One paper is accepted by IEEE TCSVT.
∙ 2025/06: One paper is accepted by ICCV 2025.
∙ 2025/05: One paper is accepted by ICML 2025.
∙ 2025/02: We are organizing the 6th Workshop on AI for Creative Visual Content Generation Editing and Understanding at CVPR 2025.
∙ 2024/07: I am awarded the 2024 Outstanding Thesis Award by BSIG!.
∙ 2024/07: One paper is accepted by ACM TOMM.
∙ 2024/06: I am invited to give a talk about my Master's thesis (slides). ∙ 2024/05: I have successfully defended my Master's thesis.
∙ 2024/03: One paper is accepted by ICME 2024.
∙ 2024/01: I am invited by AI TIME to give a talk (in Chinese) about PlaneDict (AAAI 2024).
∙ 2023/12: One paper is accepted by AAAI 2024.
∙ 2023/10: I am granted by National Scholarship (Graduate)!
∙ 2023/07: One paper is accepted by MM 2023.
👨🎓 Education
-
PhD Student in MMLab@HKUST, The Hong Kong University of Science and Technology
Supervisors: Anyi Rao and Hongbo Fu -
M.S. in New Lab of Pattern Recognition (NLPR), CASIA Institute
Supervisors: Wei Wang and Jing Dong
Thesis: Dynamic Facial Editing based on Neural Radiance Fields (BSIG Outstanding Thesis Award) -
B.E. in Nanjing University of Aeronautics and Astronautics
Thesis: Face De-Identification based on Generative Adversarial Networks (Jiangsu Outstanding Thesis Award)
💻 Work Experience
- Student Researcher, Tencent Video AI Center, PCG, Tencent
- Research Associate, MMLab@NTU, Nanyang Technological University
- Research Intern, Content Generation Group, SenseTime Research
- Research Intern, Machine Learning Group, MicroSoft Research Lab Asia (MSRA)
- Research Intern, Identity Verification Group, SenseTime Research
📝 Selected Publications
Human-Centric Content Generation with Diffusion Models: A Survey
Songlin Yang, Yueming Lyu, Ziyuan Chen, Yang Li, Beibei Dong, Xiaoxuan Han, Pei Yang, Ziye Wang, Anyi Rao, Ziwei Liu, Jing Dong, Hongbo Fu, Caifeng Shan, Xiaoming Liu, Liang Wang, Chenyang Si
Dense Semantic Matching with VGGT Prior
Songlin Yang, Tianyi Wei, Yushi Lan, Zeqi Xiao, Anyi Rao, Xingang Pan
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
Zichuan Wang, Songlin Yang, Bo Peng, Zhenchen Tang, Yang Li, Beibei Dong, Jing Dong
The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
Paper
Alpha-DPO: Robust Preference Alignment for Diffusion Models via Alpha Divergence
Yang Li, Songlin Yang, Wei Wang, Xiaoxuan Han, Jing Dong
The Fourteenth International Conference on Learning Representations, 2026
Paper
Revisiting MLLM Based Image Quality Assessment: Errors and Remedy
Zhenchen Tang, Songlin Yang, Bo Peng, Zichuan Wang, Jing Dong
Proceedings of the AAAI Conference on Artificial Intelligence, 2026
Instant Preference Alignment for Text-to-Image Diffusion Models
Yang Li, Songlin Yang, Xiaoxuan Han, Wei Wang, Jing Dong, Yueming Lyu, Ziyu Xue
Textured 3D Regenerative Morphing with 3D Diffusion Prior
Songlin Yang, Yushi Lan, Honghua Chen, Xingang Pan
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
Paper Project Code
Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time
Xiaoxuan Han, Songlin Yang, Wei Wang, Yang Li, Jing Dong
Forty-Second International Conference on Machine Learning, 2025
Paper
Learning Dense Correspondence for NeRF-Based Face Reenactment
Songlin Yang, Wei Wang, Yushi Lan, Xiangyu Fan, Bo Peng, Lei Yang, Jing Dong
Proceedings of the AAAI Conference on Artificial Intelligence, 2024
Paper Project Code
Exploiting Backdoors of Face Synthesis Detection with Natural Triggers
Xiaoxuan Han, Songlin Yang, Wei Wang, Ziwen He, Jing Dong
ACM Transactions on Multimedia Computing Communications and Applications, 2024
🎖️ Awards
- IEEE Signal Processing Society (SPS) Scholarship (2025).
- BSIG Outstanding Thesis Award (2024).
- National Scholarship - Graduate (2023).
- National Scholarship - Bachelor (2018).
- Provincial Outstanding Graduate (2021).
- Provincial Outstanding Bachelor Thesis Award (2021).
- President Scholarship of Nanjing University of Aeronautics and Astronautics (2020).
- Outstanding Graduate of Nanjing University of Aeronautics and Astronautics (2021).
- Outstanding Student of University of Chinese Academy of Sciences (2022, 2023, 2024).
- Scholarship of Aviation Industry Corporation of China (2019, 2020).
- Outstanding Reviewer for CVPR Workshop (2025).
🕴️ Professional Services
- Organizer for CVEU Workshop at CVPR 2025.
- Publicity Chair for IEEE Beijing Biometrics Council Chapter (2021-2024).
- IEEE Student Member (2021-Now).
- ACM Member (2024-Now).
- Journal Reviewer
- IEEE Transactions on Multimedia (TMM)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
- Pattern Recognition (PR)
- International Journal of Computer Vision (IJCV)
- Conference Reviewer
- AAAI (2023, 2024, 2025, 2026)
- ICCV (2025)
- SIGGRAPH (2025)
- CVPR (2022, 2023, 2024, 2025, 2026)
- ICLR (2026)
- MM (2024)
- ECCV (2022, 2024)
- 3DV (2025)
- BMVC (2026)