Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.12638 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914160802004992 |
|---|---|
| author | Qian, Chen Yu, Xinran Huang, Zewen Li, Danyang Ma, Qiang Dang, Fan Ding, Xuan Shang, Guangyong Yang, Zheng |
| author_facet | Qian, Chen Yu, Xinran Huang, Zewen Li, Danyang Ma, Qiang Dang, Fan Ding, Xuan Shang, Guangyong Yang, Zheng |
| contents | Vision-Language Models (VLMs) are increasingly deployed in real-time applications such as autonomous driving and human-computer interaction, which demand fast and reliable responses based on accurate perception. To meet these requirements, existing systems commonly employ cloud-edge collaborative architectures, such as partitioned Large Vision-Language Models (LVLMs) or task offloading strategies between Large and Small Vision-Language Models (SVLMs). However, these methods fail to accommodate cloud latency fluctuations and overlook the full potential of delayed but accurate LVLM responses. In this work, we propose a novel cloud-edge collaborative paradigm for VLMs, termed Context Transfer, which treats the delayed outputs of LVLMs as historical context to provide real-time guidance for SVLMs inference. Based on this paradigm, we design edgeVLM, which incorporates both context replacement and visual focus modules to refine historical textual input and enhance visual grounding consistency. Extensive experiments on three real-time vision-lanuage reasoning tasks across four datasets demonstrate the effectiveness of the proposed framework. The new paradigm lays the groundwork for more effective and latency-aware collaboration strategies in future VLM systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12638 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer Qian, Chen Yu, Xinran Huang, Zewen Li, Danyang Ma, Qiang Dang, Fan Ding, Xuan Shang, Guangyong Yang, Zheng Computer Vision and Pattern Recognition Artificial Intelligence Vision-Language Models (VLMs) are increasingly deployed in real-time applications such as autonomous driving and human-computer interaction, which demand fast and reliable responses based on accurate perception. To meet these requirements, existing systems commonly employ cloud-edge collaborative architectures, such as partitioned Large Vision-Language Models (LVLMs) or task offloading strategies between Large and Small Vision-Language Models (SVLMs). However, these methods fail to accommodate cloud latency fluctuations and overlook the full potential of delayed but accurate LVLM responses. In this work, we propose a novel cloud-edge collaborative paradigm for VLMs, termed Context Transfer, which treats the delayed outputs of LVLMs as historical context to provide real-time guidance for SVLMs inference. Based on this paradigm, we design edgeVLM, which incorporates both context replacement and visual focus modules to refine historical textual input and enhance visual grounding consistency. Extensive experiments on three real-time vision-lanuage reasoning tasks across four datasets demonstrate the effectiveness of the proposed framework. The new paradigm lays the groundwork for more effective and latency-aware collaboration strategies in future VLM systems. |
| title | edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.12638 |