2 papers
cs.CV2026
Apollo: Unified Multi-Task Audio-Video Joint Generation
Jun Wang, Chunyu Qiang, Yuxin Guo +3
Audio-video joint generation has progressed rapidly, yet substantial challenges still remain. Non-commercial approaches still suffer audio-visual asynchrony, poor lip-speech alignm…
cs.SD2026
MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning
Chunyu Qiang, Jun Wang, Xiaopeng Wang +2
Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity…