paper-with-me

홈 › Papers

INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference

2026-05-13 · Ahmed Šabanović, Paul Joe Maliakel, Ivona Brandić arxiv

Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but incurs communication delay and energy cost, while edge-only execution is faster but less accurate due to limited model capacity. This trade-off is further complicated by heterogeneity in image quality and reasoning complexity, making static placement suboptimal. We present INAR-VL, a lightweight edge-cloud routing system for multimodal inference in a two-tier deployment. INAR-VL maintains complementary VLMs across edge and cloud and uses lightweight image and text complexity signals to guide routing and model selection, executing simple queries locally while offloading complex ones when beneficial. Evaluation on visual question answering shows that INAR-VL executes 36% of requests on the edge, reduces latency by 24%, lowers energy by 26%, and preserves 97% of cloud-level accuracy.

📄 PDF Abstract BibTeX arXiv:2605.18853

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question Answering

Similar Papers 제목 키워드 기반

VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening

2026-07-28 · Syed Mhamudul Hasan, Anas AlSobeh, Hussein Zangoti, Abdur R. Shahid arxiv

We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing device and sends captured images, together with optional symptom descrip…

Image Classification

PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration

2025-11-27 · Junfei Zhan, Haoxun Shen, Zheng Lin, Tengjiao He arxiv

Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and me…

Natural Language Understanding

ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models

2026-03-22 · Haoyu Qiao, Hao Zhang, Shanwen Mao, Siyao Cheng 외 arxiv

Large language models (LLMs) deliver impressive capabilities but incur substantial inference latency and cost, which hinders their deployment in latency-sensitive and resource-constrained scenarios. Cloud-edge-device col…

CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference

2026-05-12 · Nan Xue, Shengkang Chen, Zhiyong Chen, Jiangchao Yao 외 arxiv

As large language models (LLMs) move from centralized clouds to mobile edge environments, efficient serving must balance latency, energy consumption, and accuracy under constrained device-edge resources. Query-level rout…

Adaptive Edge-Cloud Inference for Speech-to-Action Systems Using ASR and Large Language Models

2025-12-14 · Mohammad Jalili Torkamani, Israt Zarin arxiv

Voice-based interaction has emerged as a natural and intuitive modality for controlling IoT devices. However, speech-driven edge devices face a fundamental trade-off between cloud-based solutions, which offer stronger la…

Speech Recognition