# LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge

arXiv: https://arxiv.org/abs/2602.07849 · HTML: https://mlsanity.com/paper/2602.07849/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://mlsanity.com/paper/2311.17049/) (2023)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [WATT: Weight Average Test-Time Adaptation of CLIP](https://mlsanity.com/paper/2406.13875/) (2024)
- [Real-Time Video Inference on Edge Devices via Adaptive Model Streaming](https://mlsanity.com/paper/2006.06628/) (2020)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [Unraveling Batch Normalization for Realistic Test-Time Adaptation](https://mlsanity.com/paper/2312.09486/) (2023)

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

- [Toward Native Multimodal Modeling: A Roadmap](https://mlsanity.com/paper/2605.25343/) (2026)

## Abstract (arXiv)

Deploying Vision-Language Models (VLMs) on edge devices is challenged by resource constraints and performance degradation under distribution shifts. While test-time adaptation (TTA) can counteract such shifts, existing methods are too resource-intensive for on-device deployment. To address this challenge, we propose LQA, a lightweight, quantized-adaptive framework for VLMs that combines a modality-aware quantization strategy with gradient-free test-time adaptation. We introduce Selective Hybrid Quantization (SHQ) and a quantized, gradient-free adaptation mechanism to enable robust and efficient VLM deployment on resource-constrained hardware. Experiments across both synthetic and real-world distribution shifts show that LQA improves overall adaptation performance by 4.5%, uses less memory than full-precision models, and significantly outperforms gradient-based TTA methods, achieving up to 19.9× lower memory usage across seven open-source datasets. These results demonstrate that LQA offers a practical pathway for robust, privacy-preserving, and efficient VLM deployment on edge devices.