I am an incoming PhD student. Currently, I work as a research associate at MMLab@NTU, S-Lab, Nanyang Technological University in Singapore, under the supervision of Xingang Pan. I achieved my M.S. from Institute of Automation, Chinese Academy of Sciences and B.E. from Nanjing University of Aeronautics and Astronautics with Honors Distinction. I am the recipient of BSIG Outstanding Thesis Award (Graduate), Jiangsu Outstanding Thesis Award (Bachelor), and China National Scholarship (Bachelor & Graduate). I am fortunate to have internships at several leading research institutions, including MicroSoft Research Asia and SenseTime Research. My research experience focuses on controllable multimodal content generation, with a particular emphasis on implicit 3D representations and diffusion models.

My previous research mainly focused on these aspects:
  • Multi-Modal AIGC: Talking-Head Video, Text-to-Image/3D Generation, and Image-Driven Face Reenactment
  • Trustworthy AIGC: Machine Unlearning, Adversarial Attack, and Backdoor Attack
  • Robust Face Recognition System: De-Identification, Anti-Spoofing, and Deepfake Detection

🔈JOIN US!

I embrace Richard Feynman’s dictum, ‘What I can not create, I do not understand.’ This aligns with my technical roadmap of using generative AI to perceive, understand, and manipulate the 3D world. I will continue conducting research at the intersection of computer vision and graphics, especially in video and 3D generation, to create the 3D world from 2D pixels and realize creative human-centered AIGC.

Do not hesitate to drop me an email for any possible collaboration if you are interested in these directions:
  • Generative Models for 2D (Images/Videos), 3D, and 4D Content
  • Neural Rendering (Quality, Diversity, and Efficiency)
  • 3D Object, Scene, Human, and Human-Object-Scene Interaction
  • AIGC Safety
  • Robotics and Embodied Intelligence

🔥 News

🧑‍🎓 Education

  • M.S. in Pattern Recognition and Intelligent Systems, NLPR Department, CASIA Institute
    Supervisor: Wei Wang (Co-Supervised by Jing Dong and Bo Peng)
    Thesis: Dynamic Facial Editing based on Neural Radiance Fields (BSIG Outstanding Thesis Award)
    GPA: 3.82/4.0 (National Scholarship)

  • B.E. in Automation Engineering, Nanjing University of Aeronautics and Astronautics
    Thesis: Face De-Identification based on Generative Adversarial Networks (Jiangsu Outstanding Thesis Award)
    GPA: 4.4/5.0 (Rank: 1/204, Honors Distinction)

💻 Work Experience

  • Research Associate, MMLab@NTU, S-Lab, Nanyang Technological University
    Supervised by Xingang Pan.

  • Research Intern, Content Generation Group, SenseTime Research
    Supervised by Xiangyu Fan and Lei Yang.

  • Research Intern, Machine Learning Group, MicroSoft Research Asia
    Supervised by Xu Tan and Jun Ling.

  • Research Intern, Identity Verification Group, SenseTime Research
    Supervised by Chenye Xu and Yichao Wu.

📝 Preprint

Under Review
sym

Textured 3D Regenerative Morphing with 3D Diffusion Prior

Songlin Yang, Yushi Lan, Honghua Chen, Xingang Pan

Paper Project

Under Review
sym

Beyond Inserting: Learning Subject Embedding for Semantic-Fidelity Personalized Diffusion Generation

Yang Li*, Songlin Yang*, Wei Wang, Jing Dong
(* Equal Contribution)

Paper Project

Under Review
sym

Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective

Xiaoxuan Han, Songlin Yang, Wei Wang, Yang Li, Jing Dong

Paper Project Survey Code

📖 Selected Publications

AAAI 2024
sym

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

ACM MM 2023
sym
ACM TOMM 2024
sym

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

Paper

ICME 2024
sym

Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts

Yang Li*, Songlin Yang*, Wei Wang, Ziwen He, Bo Peng, Jing Dong
(* Equal Contribution)

IEEE International Conference on Multimedia and Expo (ICME), 2024
Oral Presentation
Paper Code

ICASSP 2023
sym

Designing a 3D-Aware StyleNeRF Encoder for Face Editing

Songlin Yang, Wei Wang, Bo Peng, Jing Dong

IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023

Paper Code

CVPR-W 2023
sym

Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models

Songlin Yang, Wei Wang, Chenye Xu, Ziwen He, Bo Peng, Jing Dong

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2023
Long Oral Presentation
Paper

🎖️ Awards

  • 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
  • First Class Scholarship for Academic Excellence. 2017, 2018, 2019, 2020

🕴️ 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).
  • Conference Reviewer
    • AAAI (2023, 2024, 2025)
    • CVPR (2022, 2023, 2024, 2025)
    • MM (2024)
    • ICCV (2025)
    • ECCV (2022, 2024)
  • 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)