mlsanityData to 7 Oct 2026

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

arXiv 2604.05375 ↗First posted 7 Apr 2026cs.MMcited by 0

On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 16 of its 50 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

16 of 50 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection8 Jan
  2. 2025Adaptive Guidance Semantically Enhanced via Multimodal LLM for Edge-Cloud Object Detection24 Sep

Other references · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  6. 2020Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analyticscited by 80
  7. 2018JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Executioncited by 38
  8. 2016BOLA: Near-Optimal Bitrate Adaptation for Online Videoscited by 26
  9. 2021AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inferencecited by 16
  10. 2025Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversationscited by 13
  11. 2025Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestrationcited by 11
  12. 2025From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devicescited by 4
2 more
  1. 2025MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inferencecited by 4
  2. 2025SAEC: Scene-Aware Enhanced Edge-Cloud Collaborative Industrial Vision Inspection with Multimodal LLMcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models
  2. 2026INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference
  3. 2026Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
  4. 2026Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs
  5. 2024CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration
  6. 2026POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
  7. 2025Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing
  8. 2025DeltaLLM: A Training-Free Framework Exploiting Temporal Sparsity for Efficient Edge LLM Inference