| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Adaptive Parameter Selection for Tuning Vision-Language Models | 78.6 | CLIP-AST (ViT-L/14) | 2025-06-11 | |
| ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning | ✓ Link | 78 | ImagineFSL LoRA (16-shot) | 2025-06-11 |
| Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP | 77.42 | CDPS (OpenCLIP ViT-B/16, 16-shot) | 2026-09-08 | |
| LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP | ✓ Link | 66.4 | LP++ (16-shot) | 2024-04-02 |
| BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming | 66.0 | BioMedVR | 2026-06-23 | |
| AdaBoosting Text Prompts for Vision-Language Models | ✓ Link | 62.8 | TPB (16-shot, OpenAI CLIP RN50) | 2026-07-01 |