Hi, I’m Chenxi Song, currently a postdoctoral researcher at AGI Lab, Westlake University, supervised by Prof. Chi Zhang. I received my Ph.D. degree in Engineering from Jilin University in 2024, where I focused on 3D Computer Vision and Computer Graphics under the supervision of Prof. Shigang Wang, with co-supervision from Prof. Jian Wei and Prof. Yan Zhao.

My current research interests lie in 3D & 4D scene and object controllable generation. I am actively engaged in the academic community, serving as a reviewer for top-tier AI conferences and journals including NeurIPS, CVPR, AAAI, ACM MM, and T-CSVT.

I recently launched a lightweight world model project called WorldForge, which will be open-sourced soon. Stay tuned!

News

• September 2025: 🔥🔥🔥Released WorldForge, a training-free world model project, and will be open-sourced soon.
• January 2025: Joined Westlake University School of Engineering as a postdoctoral researcher.
• September 2024: Graduated from Jilin University with Ph.D. degree.
• May 2024: Our work FewarNet on sparse-view multi-view synthesis was published in T-CSVT.

Publications

You can also find my articles on my Google Scholar profile.

WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance (2025)
C Song, Y Yang, T Zhao, R Li, C Zhang
arXiv preprint arXiv:2509.15130

FewarNet: An efficient few-shot view synthesis network based on trend regularization (2024)
C Song, S Wang, J Wei, Y Zhao
IEEE Transactions on Circuits and Systems for Video Technology 34 (10), 9264-9278

FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing (2025)
G Li, Y Yang, C Song, C Zhang
arXiv preprint arXiv:2506.05046

Appagentx: Evolving gui agents as proficient smartphone users (2025)
W Jiang, Y Zhuang, C Song, X Yang, JT Zhou, C Zhang
arXiv preprint arXiv:2503.02268

Wide-baseline view synthesis for light-field display based on plane-depth-fused sweep volume (2023)
C Song, S Wang, J Wei, Y Zhao, R Zhang
Displays 79, 102503

Elemental image array generation based on BVH structure combined with spatial partition and display optimization (2024)
T Li, S Wang, J Wei, Y Zhao, C Song, R Zhang
Displays 84, 102784