# WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP

arXiv: https://arxiv.org/abs/2509.21153 · HTML: https://mlsanity.com/paper/2509.21153/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://mlsanity.com/paper/2311.17049/) (2023)
- [TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance](https://mlsanity.com/paper/2309.12314/) (2023)
- [MobileCLIP2: Improving Multi-Modal Reinforced Training](https://mlsanity.com/paper/2508.20691/) (2025)
- [TULIP: Towards Unified Language-Image Pretraining](https://mlsanity.com/paper/2503.15485/) (2025)
- [Wavelet-Based Image Tokenizer for Vision Transformers](https://mlsanity.com/paper/2405.18616/) (2024)
- [Semi-Supervised Semantic Segmentation via Marginal Contextual Information](https://mlsanity.com/paper/2308.13900/) (2023)
- [Robot Instance Segmentation with Few Annotations for Grasping](https://mlsanity.com/paper/2407.01302/) (2024)

## Built on by (most cited first, 3 of 3)

- [CARES: Context-Aware Resolution Selector for VLMs](https://mlsanity.com/paper/2510.19496/) (2025)
- [Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs](https://mlsanity.com/paper/2603.16932/) (2026)
- [R3: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain](https://mlsanity.com/paper/2509.24022/) (2025)

## Abstract (arXiv)

We introduce WAVECLIP, a single unified model for adaptive resolution inference in CLIP, enabled by wavelet-based tokenization. WAVECLIP replaces standard patch embeddings with a multi-level wavelet decomposition, enabling the model to process images coarse to fine while naturally supporting multiple resolutions within the same model. At inference time, the model begins with low resolution tokens and refines only when needed, using key-value caching and causal cross-level attention to reuse computation, effectively introducing to the model only new information when needed. We evaluate WAVECLIP in zero-shot classification, demonstrating that a simple confidence-based gating mechanism enables adaptive early exits. This allows users to dynamically choose a compute-accuracy trade-off using a single deployed model. Our approach requires only lightweight distillation from a frozen CLIP teacher and achieves competitive accuracy with significant computational savings.