SemanticGen: Video Generation in Semantic Space Paper β’ 2512.20619 β’ Published 27 days ago β’ 91
MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives Paper β’ 2512.14699 β’ Published Dec 16, 2025 β’ 27
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling Paper β’ 2512.12675 β’ Published Dec 14, 2025 β’ 40
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length Paper β’ 2512.04677 β’ Published Dec 4, 2025 β’ 168
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation Paper β’ 2512.05106 β’ Published Dec 4, 2025 β’ 16
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper β’ 2511.14993 β’ Published Nov 19, 2025 β’ 229
view article Article Weβre open-sourcing our text-to-image model and the process behind it Nov 12, 2025 β’ 76