{"ID":2875111,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.03494","arxiv_id":"2509.03494","title":"Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA","abstract":"In this paper, we propose a novel parameter-efficient adaptation method for No- Reference Image Quality Assessment (NR-IQA) using visual prompts optimized in pixel-space. Unlike full fine-tuning of Multimodal Large Language Models (MLLMs), our approach trains only 600K parameters at most (\u003c 0.01% of the base model), while keeping the underlying model fully frozen. During inference, these visual prompts are combined with images via addition and processed by mPLUG-Owl2 with the textual query \"Rate the technical quality of the image.\" Evaluations across distortion types (synthetic, realistic, AI-generated) on KADID- 10k, KonIQ-10k, and AGIQA-3k demonstrate competitive performance against full finetuned methods and specialized NR-IQA models, achieving 0.93 SRCC on KADID-10k. To our knowledge, this is the first work to leverage pixel-space visual prompts for NR-IQA, enabling efficient MLLM adaptation for low-level vision tasks. The source code is publicly available at https: // github. com/ yahya-ben/ mplug2-vp-for-nriqa.","short_abstract":"In this paper, we propose a novel parameter-efficient adaptation method for No- Reference Image Quality Assessment (NR-IQA) using visual prompts optimized in pixel-space. Unlike full fine-tuning of Multimodal Large Language Models (MLLMs), our approach trains only 600K parameters at most (\u003c 0.01% of the base model), wh...","url_abs":"https://arxiv.org/abs/2509.03494","url_pdf":"https://arxiv.org/pdf/2509.03494v2","authors":"[\"Yahya Benmahane\",\"Mohammed El Hassouni\"]","published":"2025-09-03T17:23:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}