DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915919833333760 |
|---|---|
| author | Guo, Qi Yang, Zheming Hu, Yunqing Zhao, Chang Ji, Wen |
| author_facet | Guo, Qi Yang, Zheming Hu, Yunqing Zhao, Chang Ji, Wen |
| contents | Multimodal large language models (MLLMs) have shown strong capability in semantic understanding and visual reasoning, yet their use on continuous video streams in bandwidth-constrained edge-cloud systems incurs prohibitive computation and communication overhead and hinders low-latency alerting and effective visual evidence delivery. To address this challenge, we propose DAT to achieve high-quality semantic generation, low-latency event alerting, and effective visual evidence supplementation. To reduce unnecessary deep reasoning costs, we propose a collaborative small-large model cascade. A lightweight edge-side small model acts as a gating module to filter non-target-event frames and perform object detection, triggering MLLM inference only for suspicious frames. Building on this, we introduce an efficient fine-tuning strategy with visual guidance and semantic prompting, which improves structured event understanding, object detection, and output consistency. To ensure low-latency semantic alerting and effective visual evidence supplementation under bandwidth constraints, we further devise a semantics and bandwidth-aware multi-stream adaptive transmission optimization method. Experimental results show that DAT achieves 98.83% recognition accuracy and 100% output consistency. Under severe congestion, it reduces weighted semantic alert delay by up to 77.5% and delivers 98.33% of visual evidence within 0.5 s, demonstrating the effectiveness of jointly optimizing cascade inference and elastic transmission. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05375 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems Guo, Qi Yang, Zheming Hu, Yunqing Zhao, Chang Ji, Wen Multimedia Multimodal large language models (MLLMs) have shown strong capability in semantic understanding and visual reasoning, yet their use on continuous video streams in bandwidth-constrained edge-cloud systems incurs prohibitive computation and communication overhead and hinders low-latency alerting and effective visual evidence delivery. To address this challenge, we propose DAT to achieve high-quality semantic generation, low-latency event alerting, and effective visual evidence supplementation. To reduce unnecessary deep reasoning costs, we propose a collaborative small-large model cascade. A lightweight edge-side small model acts as a gating module to filter non-target-event frames and perform object detection, triggering MLLM inference only for suspicious frames. Building on this, we introduce an efficient fine-tuning strategy with visual guidance and semantic prompting, which improves structured event understanding, object detection, and output consistency. To ensure low-latency semantic alerting and effective visual evidence supplementation under bandwidth constraints, we further devise a semantics and bandwidth-aware multi-stream adaptive transmission optimization method. Experimental results show that DAT achieves 98.83% recognition accuracy and 100% output consistency. Under severe congestion, it reduces weighted semantic alert delay by up to 77.5% and delivers 98.33% of visual evidence within 0.5 s, demonstrating the effectiveness of jointly optimizing cascade inference and elastic transmission. |
| title | DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems |
| topic | Multimedia |
| url | https://arxiv.org/abs/2604.05375 |