paper

Study / paper

• Sampling Generative Networks
• mixup: Beyond Empirical Risk Minimization
• Efficient Training of Visual Transformers with Small Datasets
• Box It to Bind It: Unified Layout Control and Attribute Binding in T2I Diffusion Models
• Deep Learning and the Information Bottleneck Principle
• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
• Neural Network Diffusion
• Learning Transferable Visual Models From Natural Language Supervision
• YOLO-World: Real-Time Open-Vocabulary Object Detection
• DoRA: Weight-Decomposed Low-Rank Adaptation
• You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
• Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
• SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions