Zhen-Yu Wang

ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections

While existing camera-controllable video generation models can produce visually compelling sequences, preserving intrinsic 4D spatiotemporal coherence remains challenging. To address this limitation, we propose ChronoWorld, an"Observation--State--Reflection"framework that leverages spatiotemporal causal cues and recons...