Can Text-to-Image Models Draw from the Right Frame of Reference? Paper • 2608.03357 • Published 7 days ago • 23
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing Paper • 2602.12205 • Published Feb 13 • 83
Optimizing Visual Generative Models via Distribution-wise Rewards Paper • 2607.02291 • Published Jul 2 • 18
Optimizing Visual Generative Models via Distribution-wise Rewards Paper • 2607.02291 • Published Jul 2 • 18
Optimizing Visual Generative Models via Distribution-wise Rewards Paper • 2607.02291 • Published Jul 2 • 18
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning Paper • 2604.05404 • Published Apr 7 • 46