This work presents a synchronization-aware acceleration framework for efficient audio-visual generation by explicitly accounting for cross-modal dependence during acceleration, and improves inference efficiency while keeping video quality, audio quality, and audio-video synchronization.
Sheng-Chuan Gao, Teng Hu, Bohao Feng et al.· 0 citations
This paper proposes PhysAgent, a reflective agentic framework that closes the loop among physical program generation, physics simulation, stage-specific verification, and targeted program repair, and design a set of physics-control APIs to support more stable and complex motion behaviors.
This work proposes Cycle-World, a novel framework designed for stable and temporally consistent long-video generation that tackles error drift by enforcing strict temporal reversibility across both the training and inference phases, and demonstrates that forward generative drift can be strictly bottlenecked by a cycle-consistency objective.
Zihan Su, Teng Hu, Jiangning Zhang et al.· 1 citation