Similar Items: Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
- TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
- Linearizing Vision Transformer with Test-Time Training
- Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
- Let ViT Speak: Generative Language-Image Pre-training
- Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
- Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting