Research map / Vision-language and multimodal / CLIP and zero-shot

Prompt learning for CLIP

Learns soft text prompts for vision-language models, with distillation, regularization and Bayesian modeling.

102 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2022–2026) · an approach in CLIP and zero-shot, keyword cluster “prompt · tuning · pre trained”

State History Benchmarks Tried Baselines Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2022 · Conditional Prompt Learning for Vision-Language Models (CVPR 2022 · 1,735 citations)
• 2023 · MaPLe: Multi-Modal Prompt Learning (CVPR 2023 · 886 citations)
• 2024 · PromptKD: Unsupervised Prompt Distillation for Vision-Language Models (CVPR 2024 · 106 citations)
• 2025 · Learning to Prompt with Text Only Supervision for Vision-Language Models (AAAI 2025 · 26 citations)
• 2026 · SpecPL: Disentangling Spectral Granularity for Prompt Learning (ICML 2026 · 0 citations)

Earliest papers here

• Conditional Prompt Learning for Vision-Language Models (CVPR 2022 · 1,735 citations)
• Prompt Distribution Learning (CVPR 2022 · 245 citations)
• Align and Prompt: Video-and-Language Pre-Training With Entity Prompts (CVPR 2022 · 175 citations)

Benchmark records

The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.

What has been tried

76 papers here report 934 measured changes (a component added, removed or swapped, compared with a baseline): helped 76%, no clear effect 4%, hurt 17%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

Baseline numbers that disagree

The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.

What reviewers will expect

Datasets and baselines named in the 26 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Recent preprints

Who publishes on it

Institutions on the most papers of this approach since 2023 (of 97 papers; from OpenAlex and the papers' affiliations).

• Chinese Academy of Sciences · 7 papers
• Shanghai Jiao Tong University · 6 papers
• Harbin Institute of Technology · 5 papers
• University of Science and Technology of China · 4 papers
• University of Chinese Academy of Sciences · 3 papers
• Peking University · 3 papers
• Australian National University · 3 papers
• Xidian University · 3 papers
• The Chinese University of Hong Kong · 3 papers
• Nanyang Technological University · 2 papers

Use it

Download BibTeX of 30 key papersOpen the topic in the interactive map

Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.

Related approaches

Same keyword cluster

• Test-time adaptation of VLMs (93 papers)
• Feature calibration for unseen-class detection (50 papers)
• Parameter-efficient visual tuning (41 papers)

Elsewhere in the topic

• Open-vocabulary alignment from VLMs (130 papers)
• Attribute-based zero-shot learning (115 papers)
• Adapting VLMs for zero-shot classification (108 papers)
• Recaptioning and text-supervised pretraining (73 papers)
• CLIP training recipes and data curation (72 papers)
• Language models for zero-shot reasoning (64 papers)
• Fine-grained improvements to CLIP (63 papers)
• Self-distillation for vision-language pretraining (48 papers)

Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).