RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization Paper • 2507.12142 • Published 15 days ago • 35
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models Paper • 2506.19103 • Published Jun 23 • 42
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback Paper • 2507.02321 • Published 28 days ago • 38
T-LoRA: Single Image Diffusion Model Customization Without Overfitting Paper • 2507.05964 • Published 23 days ago • 113
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback Paper • 2507.02321 • Published 28 days ago • 38
T-LoRA: Single Image Diffusion Model Customization Without Overfitting Paper • 2507.05964 • Published 23 days ago • 113
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models Paper • 2506.19103 • Published Jun 23 • 42
FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention Paper • 2505.21144 • Published May 27 • 2
MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing Paper • 2502.15381 • Published Feb 21
ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models Paper • 2505.22569 • Published May 28 • 55
FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention Paper • 2505.21144 • Published May 27 • 2
DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization Paper • 2505.20975 • Published May 27 • 36
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models Paper • 2506.06395 • Published Jun 5 • 128
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models Paper • 2506.06395 • Published Jun 5 • 128
Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards Paper • 2503.19948 • Published Mar 25