MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing Paper • 2509.22186 • Published Sep 26, 2025 • 181
LongLive: Real-time Interactive Long Video Generation Paper • 2509.22622 • Published Sep 26, 2025 • 192
Seedream 4.0: Toward Next-generation Multimodal Image Generation Paper • 2509.20427 • Published Sep 24, 2025 • 91
Video models are zero-shot learners and reasoners Paper • 2509.20328 • Published Sep 24, 2025 • 101