paper-with-me

홈 › Papers

ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Models

2025-10-31 · Xin Tang, Youfang Han, Fangfei Gou, Wei Zhao, Xin Meng, Yang Yu, Jinguo Zhang, Yuanchun Shi, Yuntao Wang, Tengxiang Zhang arxiv

Vision-Language Models (VLMs) excel in diverse multimodal tasks. However, user requirements vary across scenarios, which can be categorized into fast response, high-quality output, and low energy consumption. Relying solely on large models deployed in the cloud for all queries often leads to high latency and energy cost, while small models deployed on edge devices are capable of handling simpler tasks with low latency and energy cost. To fully leverage the strengths of both large and small models, we propose ECVL-ROUTER, the first scenario-aware routing framework for VLMs. Our approach introduces a new routing strategy and evaluation metrics that dynamically select the appropriate model for each query based on user requirements, maximizing overall utility. We also construct a multimodal response-quality dataset tailored for router training and validate the approach through extensive experiments. Results show that our approach successfully routes over 80\% of queries to the small model while incurring less than 10\% drop in problem solving probability.

📄 PDF Abstract BibTeX arXiv:2510.27256

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios

2026-04-10 · Hui Liu, Bin Zou, Kecheng Chen, Jie Liu 외 arxiv

Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet user-specific cost-performance trade-offs…

DiSRouter: Distributed Self-Routing for LLM Selections

2025-10-22 · Hang Zheng, Hongshen Xu, Yongkai Lin, Shuai Fan 외 arxiv

The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current rou…

SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks

2026-08-12 · Tao Yu, Yifei Qu, Zhiqing Cui, Pengfei Zhou 외 arxiv

Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA evaluation, lacks systematic calibration …

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project

2026-03-22 · Huamin Chen, Xunzhuo Liu, Bowei He, Fuyuan Lyu 외 arxiv

Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, router performance engineering, policy confl…

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization

2026-04-16 · Haochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu 외 arxiv

Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the routing strategy introduces a new security concern that adversaries may manip…