WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling Paper • 2512.14614 • Published 10 days ago • 64
Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation Paper • 2512.13495 • Published 11 days ago • 11
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models Paper • 2512.02014 • Published 25 days ago • 68
Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy Paper • 2511.21579 • Published 30 days ago • 23
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation Paper • 2505.20292 • Published May 26 • 52