Video Generation

Ziwei Zhou, Zeyuan Lai, Rui Wang et al.

AVGen-Bench finds that today's flashy text-to-audio-video systems are still semantically unreliable, especially for speech, text rendering, physical reasoning, and musical pitch control.

InSpatio Team, Donghui Shen, Guofeng Zhang et al.

A real-time 4D world simulator from a single video that emphasizes spatial consistency and controllable interaction, pointing toward more usable interactive environments for embodied training and evaluation.

Zirui Li, Xinghao Chen, Lingyu Jiang et al.

PVIR introduces the first physics-aware benchmark for video object removal, forcing models to preserve physical consistency like shadows and reflections—critical for realistic video editing in production systems.