Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published Jul 21 • 78
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published Jul 21 • 78
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence Paper • 2602.08683 • Published Feb 9 • 52
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18, 2025 • 16
Boosting Neural Representations for Videos with a Conditional Decoder Paper • 2402.18152 • Published Feb 28, 2024
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting Paper • 2403.08551 • Published Mar 13, 2024 • 11