Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.02888 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917209013485568 |
|---|---|
| author | Wang, Xuanyu Su, Haisen Zhang, Jingtao Wang, Xiangxiang Yu, Yongbin Fan, Manping Xiao, Jialing Gong, Bo Chen, Siqi Cao, Mingsheng Ren, Liyong Yang, Zhenglin |
| author_facet | Wang, Xuanyu Su, Haisen Zhang, Jingtao Wang, Xiangxiang Yu, Yongbin Fan, Manping Xiao, Jialing Gong, Bo Chen, Siqi Cao, Mingsheng Ren, Liyong Yang, Zhenglin |
| contents | Visually impaired users face significant challenges in daily information access and real-time environmental perception, and there is an urgent need for intelligent assistive systems with accurate recognition capabilities. Although large-scale models provide effective solutions for perception and reasoning, their practical deployment on assistive devices is severely constrained by excessive memory consumption and high inference costs. Moreover, existing quantization strategies often ignore inter-block error accumulation, leading to degraded model stability. To address these challenges, this study proposes a novel quantization framework -- Residual-Projected Multi-Collaboration Closed-Loop and Single Instance Quantization(RPIQ), whose quantization process adopts a multi-collaborative closed-loop compensation scheme based on Single Instance Calibration and Gauss-Seidel Iterative Quantization. Experiments on various types of large-scale models, including language models such as OPT, Qwen, and LLaMA, as well as vision-language models such as CogVLM2, demonstrate that RPIQ can compress models to 4-bit representation while significantly reducing peak memory consumption (approximately 60%-75% reduction compared to original full-precision models). The method maintains performance highly close to full-precision models across multiple language and visual tasks, and exhibits excellent recognition and reasoning capabilities in key applications such as text understanding and visual question answering in complex scenarios. While verifying the effectiveness of RPIQ for deployment in real assistive systems, this study also advances the computational efficiency and reliability of large models, enabling them to provide visually impaired users with the required information accurately and rapidly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02888 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RPIQ: Residual-Projected Multi-Collaboration Closed-Loop and Single Instance Quantization for Visually Impaired Assistance Wang, Xuanyu Su, Haisen Zhang, Jingtao Wang, Xiangxiang Yu, Yongbin Fan, Manping Xiao, Jialing Gong, Bo Chen, Siqi Cao, Mingsheng Ren, Liyong Yang, Zhenglin Machine Learning Visually impaired users face significant challenges in daily information access and real-time environmental perception, and there is an urgent need for intelligent assistive systems with accurate recognition capabilities. Although large-scale models provide effective solutions for perception and reasoning, their practical deployment on assistive devices is severely constrained by excessive memory consumption and high inference costs. Moreover, existing quantization strategies often ignore inter-block error accumulation, leading to degraded model stability. To address these challenges, this study proposes a novel quantization framework -- Residual-Projected Multi-Collaboration Closed-Loop and Single Instance Quantization(RPIQ), whose quantization process adopts a multi-collaborative closed-loop compensation scheme based on Single Instance Calibration and Gauss-Seidel Iterative Quantization. Experiments on various types of large-scale models, including language models such as OPT, Qwen, and LLaMA, as well as vision-language models such as CogVLM2, demonstrate that RPIQ can compress models to 4-bit representation while significantly reducing peak memory consumption (approximately 60%-75% reduction compared to original full-precision models). The method maintains performance highly close to full-precision models across multiple language and visual tasks, and exhibits excellent recognition and reasoning capabilities in key applications such as text understanding and visual question answering in complex scenarios. While verifying the effectiveness of RPIQ for deployment in real assistive systems, this study also advances the computational efficiency and reliability of large models, enabling them to provide visually impaired users with the required information accurately and rapidly. |
| title | RPIQ: Residual-Projected Multi-Collaboration Closed-Loop and Single Instance Quantization for Visually Impaired Assistance |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.02888 |