Research map / Vision-language and multimodal / CLIP and zero-shot
Do-Prompt: Causal Interventions Meet Variational Prompt Bottlenecks
Xueting Chen, Jun-Jie Huang, Yan Yan, Long Lan, Yuhua Tang, Wenjing Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add variational prompt bottleneck (ablation) | MaPLe* · Base-to-novel average | HM: 78.37 -> 78.93 | Improved |
| add do-intervention consistency (ablation) | MaPLe* · Base-to-novel average | HM: 78.37 -> 79.02 | Improved |
| add both bottleneck and intervention to MaPLe (ablation) | MaPLe* · Base-to-novel average | HM: 78.37 -> 80.12 | Improved |
| add variational prompt bottleneck (ablation) | MMRL* · Base-to-novel average | HM: 80.59 -> 81.32 | Improved |
| add do-intervention consistency (ablation) | MMRL* · Base-to-novel average | HM: 80.59 -> 81.43 | Improved |
| add both components to MMRL (ablation) | MMRL* · Base-to-novel average | HM: 80.59 -> 82.56 | Improved |
| use all three intervention operators instead of mask only (ablation) | MaPLe* + Do-Prompt · Base-to-novel average | HM: 79.01 -> 80.12 | Improved |
| use all three operators instead of swap only (ablation) | MaPLe* + Do-Prompt · Base-to-novel average | HM: 78.94 -> 80.12 | Improved |
| core-environment split 2:3 instead of 3:2 (ablation) | MMRL + Do-Prompt · Base-to-novel average | HM: 82.56 -> 81.27 | Hurt |
| core-environment split 4:1 instead of 3:2 (ablation) | MaPLe + Do-Prompt · Base-to-novel average | HM: 80.12 -> 79.31 | Hurt |
| add Do-Prompt to MMRL | MMRL* · EuroSAT base-to-novel | HM: 85.50 -> 91.28 | Improved |
| add Do-Prompt to MMRL | MMRL* · StanfordCars base-to-novel | HM: 77.99 -> 78.17 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MMRL* — MMRL: Multi-Modal Representation Learning for Vision-Language Models (CVPR 2025) · better on 8 of 8 shared results
- MaPLe* — MaPLe: Multi-Modal Prompt Learning (CVPR 2023) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models (NeurIPS 2025 · similarity 0.91)
- Learning to Learn Better Visual Prompts (AAAI 2024 · similarity 0.90)
- Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models (ICML 2024 · similarity 0.90)
- IPO: Interpretable Prompt Optimization for Vision-Language Models (NeurIPS 2024 · similarity 0.90)
- VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion (NeurIPS 2025 · similarity 0.90)
- Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
