| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Task-Aware Clustering for Prompting Vision-Language Models | ✓ Link | 50.3 | TAC | 2025-06-11 |
| HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models | ✓ Link | 49.57 | HeBA | 2026-03-17 |
| Prompt Learning via Meta-Regularization | ✓ Link | 49.55 | ProMetaR | 2024-04-01 |
| SDSA: Shallow-Deep Squeezing Adapter for Vision-Language Models | 49.37 | SDSA (ViT-B/16) | 2026-09-08 | |
| MMA: Multi-Modal Adapter for Vision-Language Models | ✓ Link | 49.13 | MMA | 2024-06-17 |
| MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation | ✓ Link | 49.07 | MMLoP | 2026-02-24 |