training-free methods
- Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
- Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
- DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
- ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
- Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models
- VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree