High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation Paper • 2606.12575 • Published 10 days ago • 11
Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions Paper • 2606.09076 • Published 12 days ago • 59
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models Paper • 2605.05204 • Published May 6 • 27
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer Paper • 2511.22699 • Published Nov 27, 2025 • 247
Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield Paper • 2511.22677 • Published Nov 27, 2025 • 35
Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining Paper • 2408.02657 • Published Aug 5, 2024 • 35
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models Paper • 2311.07575 • Published Nov 13, 2023 • 15