OpenCodePapers

prompt-engineering-on-imagenet-v2

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.
PaperCodeTop-1 accuracy %ModelNameReleaseDate
SemPT: Semantic Prompt Tuning for Vision-Language Models70.46PromptKD w/ SemPT2025-08-14
PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models70.39PETR2026-09-20
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning✓ Link70.11DAPT + PromptKD2025-08-01
Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter68.60VRGAdapter2025-07-14
Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics66.43GAPL2026-04-05
AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning✓ Link65.73MMA + AmPLe2025-12-20
Variational Adapter for Cross-modal Similarity Representation65.7VACSR2026-05-29
AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning✓ Link65.53MMRL + AmPLe2025-12-20
HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling✓ Link65.31HPT++2024-08-27
Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models✓ Link65.25HPT2023-12-11
AttriPrompt: Dynamic Prompt Composition Learning for CLIP65.07AttriPrompt2025-09-07
MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models65.03MAIL++2026-05-25
VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models64.96VaMP2025-11-27
GLAD: Generalizable Tuning for Vision-Language Models64.93GLAD2025-07-17
DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles✓ Link64.87DeAR2026-03-01
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning✓ Link64.81DAPT + PromptSRC2025-08-01
MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning64.77MMRL++ + MQAdapter2026-07-14
Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise64.63ANPrompt2025-08-06
ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models✓ Link64.60ProCAP2026-09-24
DiscoVL: Unveiling Disentangled C ross-Modal Representation Learning via Orthogonal Adversarial Regularization for V ision-Language Models64.60DiscoVL2026-10-08
MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning64.53PromptSRC + MQAdapter2026-07-14
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning✓ Link64.51DAPT-G2025-08-01
Integrated Structural Prompt Learning for Vision-Language Models64.50ISP2025-07-08
MMRL: Multi-Modal Representation Learning for Vision-Language Models✓ Link64.47MMRL2025-03-11
RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models64.45RMAdapter2025-12-07
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning✓ Link64.43DAPT-S2025-08-01
AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning✓ Link64.43MaPLe + AmPLe2025-12-20
Guided Prompt Evolution for Vision-Language Models Adaptation64.40EvoPrompt2026-03-10
Self-regulating Prompts: Foundational Model Adaptation without Forgetting✓ Link64.35PromptSRC2023-07-13
MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation✓ Link64.30MMLoP2026-02-24
MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning64.24MaPLe + MQAdapter2026-07-14
Conditional Prompt Learning for Vision-Language Models✓ Link64.07CoCoOp2022-03-10
MaPLe: Multi-modal Prompt Learning✓ Link64.07MaPLe2022-10-06
63.8POMP
HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models✓ Link63.55HeBA2026-03-17
Learning Transferable Visual Models From Natural Language Supervision✓ Link60.83CLIP2021-02-26
Check out how to contribute new results. Then edit this file on GitLab or GitHub.