# DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems

Source: [DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems](<https://www.sota2.com/research/paper/69d5e0eb7d0172140ec758fa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-09T05:00:04.534Z

Authors: Qi Guo, Zheming Yang, Yunqing Hu, Chang Zhao, Wen Ji

Published: 2026-04-07T03:21:17.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.05375>)

[PDF](<https://arxiv.org/pdf/2604.05375.pdf>)
