Chenxi Song
Scholar

Chenxi Song

Google Scholar ID: rytyb7QAAAAJ
Westlake University & Jilin University
3DVIsion3D&4D Generation&Reconstruction
Citations & Impact
All-time
Citations
31
 
H-index
2
 
i10-index
1
 
Publications
7
 
Co-authors
5
list available
Resume (English only)
Academic Achievements
  • Publications: - WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance (2025) - FewarNet: An efficient few-shot view synthesis network based on trend regularization (2024) - FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing (2025) - Appagentx: Evolving gui agents as proficient smartphone users (2025) - Wide-baseline view synthesis for light-field display based on plane-depth-fused sweep volume (2023) - Elemental image array generation based on BVH structure combined with spatial partition and display optimization (2024)
Research Experience
  • Currently a postdoctoral researcher at AGI Lab, Westlake University, involved in multiple research projects such as WorldForge, and serving as a reviewer for top-tier AI conferences and journals.
Education
  • Ph.D. degree: Jilin University, 2024, Major: Engineering, Supervisors: Prof. Shigang Wang, Prof. Jian Wei, Prof. Yan Zhao.
Background
  • Research interests: 3D & 4D scene and object controllable generation. Brief introduction: Currently a postdoctoral researcher at AGI Lab, Westlake University.
Miscellany
  • Personal interests: Recently launched a lightweight world model project called WorldForge, which will be open-sourced soon.