FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing Paper • 2509.22244 • Published Sep 26, 2025 • 5
CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition Paper • 2509.19768 • Published Sep 24, 2025 • 7
LongLive: Real-time Interactive Long Video Generation Paper • 2509.22622 • Published Sep 26, 2025 • 188
