ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement Paper • 2605.25569 • Published 2 days ago • 15
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models Paper • 2605.21573 • Published 7 days ago • 94
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 326
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models Paper • 2603.25502 • Published Mar 26 • 57
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation Paper • 2511.20635 • Published Nov 25, 2025 • 32