UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios Paper • 2511.18050 • Published Nov 22, 2025 • 38
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story Paper • 2511.15210 • Published Nov 19, 2025 • 90
Depth Anything 3: Recovering the Visual Space from Any Views Paper • 2511.10647 • Published Nov 13, 2025 • 99
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published Nov 19, 2025 • 231