FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining Paper • 2606.20506 • Published 22 days ago • 28
ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement Paper • 2605.25569 • Published May 25 • 21
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models Paper • 2605.21573 • Published May 20 • 111
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 329
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models Paper • 2603.25502 • Published Mar 26 • 58
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation Paper • 2511.20635 • Published Nov 25, 2025 • 32