| PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models | | 71.52 | PETR | 2026-09-20 |
| SemPT: Semantic Prompt Tuning for Vision-Language Models | | 70.83 | PromptKD w/ SemPT | 2025-08-14 |
| Decouple before Align: Visual Disentanglement Enhances Prompt Tuning | ✓ Link | 69.73 | DAPT + PromptKD | 2025-08-01 |
| Variational Adapter for Cross-modal Similarity Representation | | 52.4 | VACSR | 2026-05-29 |
| AttriPrompt: Dynamic Prompt Composition Learning for CLIP | | 52.07 | AttriPrompt | 2025-09-07 |
| VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models | | 51.97 | VaMP | 2025-11-27 |
| Prompt Tuning for CLIP on the Pretrained Manifold | | 51.97 | ManiPT | 2026-02-22 |
| DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles | ✓ Link | 51.80 | DeAR | 2026-03-01 |
| MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning | | 51.64 | MMRL++ + MQAdapter | 2026-07-14 |
| Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition | ✓ Link | 51.6 | POMP | 2023-04-10 |
| MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning | | 51.41 | MaPLe + MQAdapter | 2026-07-14 |
| HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models | ✓ Link | 51.36 | HeBA | 2026-03-17 |
| Decouple before Align: Visual Disentanglement Enhances Prompt Tuning | ✓ Link | 51.32 | DAPT + PromptSRC | 2025-08-01 |
| Guided Prompt Evolution for Vision-Language Models Adaptation | | 51.30 | EvoPrompt | 2026-03-10 |
| DiscoVL: Unveiling Disentangled C ross-Modal Representation Learning via Orthogonal Adversarial Regularization for V ision-Language Models | | 51.30 | DiscoVL | 2026-10-08 |
| RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models | | 51.21 | RMAdapter | 2025-12-07 |
| MMRL: Multi-Modal Representation Learning for Vision-Language Models | ✓ Link | 51.20 | MMRL | 2025-03-11 |
| HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling | ✓ Link | 51.18 | HPT++ | 2024-08-27 |
| MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning | | 51.15 | PromptSRC + MQAdapter | 2026-07-14 |
| MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models | | 51.10 | MAIL++ | 2026-05-25 |
| GLAD: Generalizable Tuning for Vision-Language Models | | 51.03 | GLAD | 2025-07-17 |
| MaPLe: Multi-modal Prompt Learning | ✓ Link | 50.90 | MaPLe | 2022-10-06 |
| Self-regulating Prompts: Foundational Model Adaptation without Forgetting | ✓ Link | 50.90 | PromptSRC | 2023-07-13 |
| Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models | ✓ Link | 50.85 | HPT | 2023-12-11 |
| MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation | ✓ Link | 50.83 | MMLoP | 2026-02-24 |
| ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models | ✓ Link | 50.83 | ProCAP | 2026-09-24 |
| Hierarchical Cross-modal Prompt Learning for Vision-Language Models | ✓ Link | 50.79 | HiCroPL | 2025-07-20 |
| Conditional Prompt Learning for Vision-Language Models | ✓ Link | 50.63 | CoCoOp | 2022-03-10 |
| Consistency-guided Prompt Learning for Vision-Language Models | ✓ Link | 50.50 | CoPrompt | 2023-06-01 |
| Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics | | 50.43 | GAPL | 2026-04-05 |
| From Points to Clouds: Learning Robust Semantic Distributions for Multi-modal Prompts | | 50.4 | P2C | 2025-11-28 |
| Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise | | 50.37 | ANPrompt | 2025-08-06 |
| Integrated Structural Prompt Learning for Vision-Language Models | | 49.90 | ISP | 2025-07-08 |
| Decouple before Align: Visual Disentanglement Enhances Prompt Tuning | ✓ Link | 49.41 | DAPT-S | 2025-08-01 |
| AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning | ✓ Link | 48.93 | MaPLe + AmPLe | 2025-12-20 |
| AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning | ✓ Link | 48.67 | MMRL + AmPLe | 2025-12-20 |
| Decouple before Align: Visual Disentanglement Enhances Prompt Tuning | ✓ Link | 47.97 | DAPT-G | 2025-08-01 |
| Learning Transferable Visual Models From Natural Language Supervision | ✓ Link | 47.77 | CLIP | 2021-02-26 |
| AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning | ✓ Link | 47.77 | MMA + AmPLe | 2025-12-20 |