Generalizable-Prompt-Learning-for-VLMs

June 5, 2026 · View on GitHub

A curated list of prompt learning methods for vision-language models which can be used for base-to-novel generalizaiton.

Tips:

  • All the papers included in this list contain base-to-novel generalization experiments. In other words, methods that do not demonstrate generalization capabilities are not listed here.
  • The layout of this list is inspired by this repository, which is initiated and maintained by Zheng Li. He is currently a third-year Ph.D. student at Nankai University, with one more CCF A-level paper to be published before graduation. I wish him success in his further research and happy trail running.
  • I was saddened to unexpectedly find that Yaohui Li (1997-2024), the second author of Conditional Prototype Rectification Prompt Learning (CPR, TCSVT 2025), tragically passed away in an accident after completing this work. In his homepage, his education timeline noted his PhD as expected to span from 2023 to 2027, but sadly, his 2027 will never come. Although I did not know him personally, I extend my heartfelt gratitude for his contributions to the field of prompt learning, and I hope that his legacy will inspire others to build upon his vision. May you rest in peace.

Table of Contents

Keywords

Use text-based parameter-efficient fine-tuning.

Use image-based parameter-efficient fine-tuning.

Use text- and image-based parameter-efficient fine-tuning

Published in 2026

  • ProLoG ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization AAAI 2026.
    [Paper LinK] [Code Link(Empty)]
  • RMAdapter RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models AAAI 2026.
    [Paper LinK] [No code available]
  • LOREAL LOREAL: Mitigating Low-Resolution Challenges in Vision-Language Models with Attribute-driven Prompt Self-Distillation CVPR 2026.
    [Paper LinK] [Code Link]
  • CPT Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models CVPR 2026.
    [No paper available] [No code available]
  • ReBaPL ReBaPL: Repulsive Bayesian Prompt Learning CVPR 2026.
    [Paper LinK] [Code Link]
  • Promise PROMISE: Prompt-Robust Vision-Language Models Via Meta-Finetuning ICLR 2026.
    [Paper LinK] [No code available]
  • NeRP NeRP: Neutral-Reference Prompting for Vision–Language Models ICML 2026.
    [Paper LinK] [Code Link]
  • SpecPL SpecPL: Disentangling Spectral Granularity for Prompt Learning ICML 2026.
    [Paper LinK] [Code Link]
  • LightRA LightRA: Lightweight Residual Attention for Adaptation of Vision-Language Models TMM 2026.
    [Paper LinK] [Code Link]

Published in 2025

  • Beyond the Seen Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning NIPS 2025.
    [Paper LinK] [Code Link]
  • TextRefiner TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning AAAI 2025.
    [Paper LinK] [Code Link]
  • ProText Learning to Prompt with Text Only Supervision for Vision-Language Models AAAI 2025.
    [Paper Link] [Code Link]
  • SPTR A Similarity Paradigm Through Textual Regularization Without Forgetting AAAI 2025.
    [Paper Link] [No code available]
  • FATE FATE: Feature-Adapted Parameter Tuning for Vision-Language Models AAAI 2025.
    [Paper Link] [No code available]
  • PTinCAS Prompt Tuning In a Compact Attribute Space AAAI 2025.
    [Paper Link] [No code available]
  • DsRA Exploring the Better Multimodal Synergy Strategy for Vision-Language Models AAAI 2025.
    [Paper Link] [No code available]
  • KAID KAID: Knowledge-Aware Interactive Distillation for Vision-Language Models ACM MM 2025.
    [No paper available] [No code available]
  • CLIP-AST Adaptive Parameter Selection for Tuning Vision-Language Models CVPR 2025.
    [Paper Link] [No code available]
  • MMRL MMRL: Multi-Modal Representation Learning for Vision-Language Models CVPR 2025.
    [Paper Link] [Code Link]
  • DPC DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models CVPR 2025.
    [Paper Link] [Code Link]
  • 2SFS Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages CVPR 2025.
    [Paper Link] [Code Link]
  • SkipT Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves CVPR 2025.
    [Paper Link] [Code Link]
  • TAC Task-Aware Clustering for Prompting Vision-Language Models CVPR 2025.
    [Paper Link] [Code Link]
  • ATPrompt Advancing Textual Prompt Learning with Anchored Attributes ICCV 2025.
    [Paper Link] [Code Link]
  • CaPL Causality-guided Prompt Learning for Vision-language Models via Visual Granulation ICCV 2025.
    [No paper available] [Code Link]
  • HicroPL Hierarchical Cross-modal Prompt Learning for Vision-Language Models ICCV 2025.
    [Paper Link] [Code Link]
  • FM Enhancing Target-unspecific Tasks through a Features Matrix ICML 2025.
    [Paper Link] [No code available]
  • SurPL Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models ICML 2025.
    [Paper Link] [Code Link]
  • TAP Tree of Attributes Prompt Learning For Vision Language Models ICLR 2025.
    [Paper Link] [Code Link]
  • DeKg Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning ICLR 2025.
    [Paper Link] [Code Link]
  • DiSa DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models KDD 2025.
    [Paper Link] [No code available]
  • BIP Bi-modality Individual-aware Prompt tuning for Visual-Language Model TPAMI 2025.
    [Paper Link] [Code Link]
  • CPR Conditional Prototype Rectification Prompt Learning TCSVT 2025.
    [Paper Link] [Code Link]
  • LwEIB Learning with Enriched Inductive Biases for Vision-Language Models IJCV 2025.
    [Paper Link] [Code Link]
  • FCPrompt Frequency-based Comprehensive Prompt Learning for Vision-Language Models TPAMI 2025.
    [Paper Link] [Code Link]