OpenCodePapers

prompt-engineering-on-eurosat

Transfer LearningPrompt Engineering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeHarmonic meanModelNameReleaseDate
DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles✓ Link92.22DeAR2026-03-01
MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models✓ Link91.94MMRL++2025-05-15
Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise91.21ANPrompt2025-08-06
ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models✓ Link90.98ProCAP2026-09-24
Causality-guided Prompt Learning for Vision-language Models via Visual Granulation90.69CaPL2025-09-04
MERGETUNE: Continued Fine-Tuning of Vision-Language Models✓ Link90.28PromptKD + MergeTune2026-01-15
One Last Attention for Your Vision-Language Model✓ Link89.22RAda + Prompt2025-07-21
PromptKD: Unsupervised Prompt Distillation for Vision-Language Models✓ Link89.14PromptKD2024-03-05
HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models✓ Link88.16HeBA2026-03-17
SpecPL: Disentangling Spectral Granularity for Prompt Learning✓ Link87.87MMRL + SpecPL2026-05-06
HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling✓ Link87.36HPT++2024-08-27
MMRL: Multi-Modal Representation Learning for Vision-Language Models✓ Link87.21MMRL2025-03-11
AttriPrompt: Dynamic Prompt Composition Learning for CLIP87.12AttriPrompt2025-09-07
Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics87.05GAPL2026-04-05
SpecPL: Disentangling Spectral Granularity for Prompt Learning✓ Link86.12MaPLe + SpecPL2026-05-06
Consistency-guided Prompt Learning for Vision-Language Models✓ Link85.84CoPrompt2023-06-01
MERGETUNE: Continued Fine-Tuning of Vision-Language Models✓ Link85.81MMA + MergeTune2026-01-15
Prompt Learning via Meta-Regularization✓ Link85.30ProMetaR2024-04-01
DePT: Decoupled Prompt Tuning✓ Link84.88DePT2023-09-14
Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models✓ Link84.82HPT2023-12-11
RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models84.69RMAdapter2025-12-07
GLAD: Generalizable Tuning for Vision-Language Models84.22GLAD2025-07-17
One Last Attention for Your Vision-Language Model✓ Link84.20RAda + Adapter2025-07-21
Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning84.18PromptSRC + IPL2026-05-06
Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning84.01MaPLe + IPL2026-05-06
Learning Domain Invariant Prompt for Vision-Language Models✓ Link83.38MetaPrompt2022-12-08
MaPLe: Multi-modal Prompt Learning✓ Link82.35MaPLe2022-10-06
Self-regulating Prompts: Foundational Model Adaptation without Forgetting✓ Link82.32PromptSRC2023-07-13
SpecPL: Disentangling Spectral Granularity for Prompt Learning✓ Link82.09CoCoOp + SpecPL2026-05-06
One Last Attention for Your Vision-Language Model✓ Link81.82RAda2025-07-21
MERGETUNE: Continued Fine-Tuning of Vision-Language Models✓ Link77.22KgCoOp + MergeTune2026-01-15
Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning77.10CoOp + IPL2026-05-06
Read-only Prompt Optimization for Vision-Language Few-shot Learning✓ Link76.79RPO2023-08-29
Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning74.77KgCoOp + IPL2026-05-06
Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning74.59CoCoOp + IPL2026-05-06
SpecPL: Disentangling Spectral Granularity for Prompt Learning✓ Link73.83CoOp + SpecPL2026-05-06
MERGETUNE: Continued Fine-Tuning of Vision-Language Models✓ Link73.40CoOp + MergeTune2026-01-15
Conditional Prompt Learning for Vision-Language Models✓ Link71.21CoCoOp2022-03-10
Learning Transferable Visual Models From Natural Language Supervision✓ Link60.03CLIP2021-02-26
Check out how to contribute new results. Then edit this file on GitLab or GitHub.