paper-with-me

홈 › Papers

GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization

2026-03-25 · Pengyue Jia, Derong Xu, Yingyi Zhang, Xiaopeng Li, Wenlin Zhang, Yi Wen, Yuanshao Zhu, Xiangyu Zhao arxiv

Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity. Recent methods mainly follow two paradigms: retrieval-based approaches that match queries against a reference database, and generation-based approaches that directly predict coordinates using Large Vision-Language Models (LVLMs). However, we observe distinct error profiles between them: retrieval excels at fine-grained instance matching, while generation offers robust semantic reasoning. This complementary heterogeneity suggests that no single paradigm is universally superior. To harness this potential, we propose GeoRouter, a dynamic routing framework that adaptively assigns each query to the optimal paradigm. GeoRouter leverages an LVLM backbone to analyze visual content and provide routing decisions. To optimize GeoRouter, we introduce a distance-aware preference objective that converts the distance gap between paradigms into a continuous supervision signal, explicitly reflecting relative performance differences. Furthermore, we construct GeoRouting, the first large-scale dataset tailored for training routing policies with independent paradigm predictions. Extensive experiments on IM2GPS3k and YFCC4k demonstrate that GeoRouter significantly outperforms state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2603.24376

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey

2026-02-23 · Yasmin Moslem, John D. Kelleher arxiv

The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent model selection at inference time. While smaller models suffice for routine queri…

Reinforcement Learning

Multi-Agent Reinforcement Learning for Markov Routing Games: A New Modeling Paradigm For Dynamic Traffic Assignment

2020-11-22 · Zhenyu Shou, Xu Chen, Yongjie Fu, Xuan Di

This paper aims to develop a paradigm that models the learning behavior of intelligent agents (including but not limited to autonomous vehicles, connected and automated vehicles, or human-driven vehicles with intelligent…

Autonomous VehiclesBilevel OptimizationMulti-agent Reinforcement LearningQ-Learning

Three Pillars Towards Next-Generation Routing System

2024-09-03 · Lei LI, Mengxuan Zhang, Zizhuo Xu, Yehong Xu 외

The routing results are playing an increasingly important role in transportation efficiency, but they could generate traffic congestion unintentionally. This is because the traffic condition and routing system are discon…

Management

Fleet: Few Shots Lead Effective AI-generated Image Detection

2026-06-30 · Jiaan Wang, Sirui Liu, Yu Li, Kaiyuan Yang 외 arxiv

AI-generated image (AIGI) detection is undergoing a critical transition from laboratory benchmarks to open-world adversarial defense. The prevalent paradigm focuses on finding static feature spaces, assuming that some in…

Zero-shot GeneralizationAdversarial Defense

Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer

2025-03-04 · Yujiao Yang, Jing Lian, Linhui Li

Mixture-of-Experts (MoE) enhances model performance while maintaining computational efficiency, making it well-suited for large-scale applications. However, expert in exist MoE paradigm works as an individual, thereby la…

Computational EfficiencyMixture-of-Experts