# Spotlighter: Revisiting Prompt Tuning from a Representative Mining View

arXiv: https://arxiv.org/abs/2509.00905 · HTML: https://mlsanity.com/paper/2509.00905/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Progressive Visual Prompt Learning with Contrastive Feature Re-formation](https://mlsanity.com/paper/2304.08386/) (2023)
- [LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation](https://mlsanity.com/paper/2401.17244/) (2024)
- [CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination](https://mlsanity.com/paper/2408.09441/) (2024)
- [Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages](https://mlsanity.com/paper/2503.11609/) (2025)
- [GOAL: Global-local Object Alignment Learning](https://mlsanity.com/paper/2503.17782/) (2025)
- [Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification](https://mlsanity.com/paper/2409.16718/) (2024)
- [TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning](https://mlsanity.com/paper/2412.08176/) (2024)
- [Efficient and Versatile Robust Fine-Tuning of Zero-shot Models](https://mlsanity.com/paper/2408.05749/) (2024)

## Built on by (most cited first, 1 of 1)

- [CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment](https://mlsanity.com/paper/2603.02557/) (2026)

## Abstract (arXiv)

CLIP's success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components introduce noise and incur unnecessary computational costs. In this work, we propose Spotlighter, a lightweight token-selection framework that simultaneously enhances accuracy and efficiency in prompt tuning. Spotlighter evaluates each visual token's activation from both sample-wise and semantic-wise perspectives and retains only the top-scoring tokens for downstream prediction. A class-specific semantic memory bank of learned prototypes refines this selection, ensuring semantic representativeness and compensating for discarded features. To further prioritize informative signals, we introduce a two-level ranking mechanism that dynamically weights token--prototype interactions. Across 11 few-shot benchmarks, Spotlighter outperforms CLIP by up to 11.19% in harmonic mean accuracy and achieves up to 0.8K additional FPS, with only 21 extra parameters. These results establish Spotlighter as an effective and scalable baseline for prompt tuning. Code for our method will be available at https://github.com/greatest-gourmet/Spotlighter.