view article Article Wan 3.0 Ecosystem Signals: What WanSong, Wan-Dancer, and Wan-Streamer Reveal About Alibaba's Next Video Model ResterChed • 26 days ago • 2
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published Jul 13 • 85
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating Paper • 2606.21661 • Published Jun 19 • 28
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating Paper • 2606.21661 • Published Jun 19 • 28
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating Paper • 2606.21661 • Published Jun 19 • 28
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence Paper • 2606.14777 • Published Jun 10 • 217