Chenxi Song

Chenxi Song

Postdoc Researcher at AGI Lab, Westlake University. Research interests: 3D&4D scene generation, controllable video generation, and world models.

– visits

WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models

Published in arXiv preprint, 2026

WorldForge V2 combines training-free camera-trajectory guidance with efficient refinement and lightweight adaptation to control camera motion in pretrained video diffusion models.

arXiv | Code

Recommended citation: C Song, Y Yang, T Zhao, R Li, JT Zhou, C Zhang. (2026). "WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models." arXiv preprint arXiv:2610.31640.
Download Paper