{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"id":"2309.16020","title":"GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization","created":"2023-09-27","cited_by_count":187},{"id":"1510.03743","title":"Wide-Area Image Geolocalization with Aerial Reference Imagery","created":"2015-10-13","cited_by_count":186},{"id":"1903.12351","title":"Lending Orientation to Neural Networks for Cross-view Geo-localization","created":"2019-03-29","cited_by_count":180},{"id":"2204.00097","title":"TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization","created":"2022-03-31","cited_by_count":168},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2005.03860","title":"Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching","created":"2020-05-08","cited_by_count":126},{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119},{"id":"1602.05314","title":"PlaNet - Photo Geolocation with Convolutional Neural Networks","created":"2016-02-17","cited_by_count":115},{"id":"1811.11597","title":"Automated Algorithm Selection: Survey and Perspectives","created":"2018-11-28","cited_by_count":114},{"id":"2304.03410","title":"$R^{2}$Former: Unified $R$etrieval and $R$eranking Transformer for Place Recognition","created":"2023-04-06","cited_by_count":102},{"id":"1705.04838","title":"Revisiting IM2GPS in the Deep Learning Era","created":"2017-05-13","cited_by_count":80},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80},{"id":"2212.04074","title":"Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence","created":"2022-12-08","cited_by_count":70},{"id":"1703.07815","title":"Cross-View Image Matching for Geo-localization in Urban Environments","created":"2017-03-22","cited_by_count":69},{"id":"1808.02130","title":"CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps","created":"2018-08-06","cited_by_count":68},{"id":"2103.12236","title":"Instance-level Image Retrieval using Reranking Transformers","created":"2021-03-22","cited_by_count":63},{"id":"2204.13861","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","created":"2022-04-29","cited_by_count":58},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56},{"id":"2303.04249","title":"Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes","created":"2023-03-07","cited_by_count":55},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48},{"id":"2204.01458","title":"Correlation Verification for Image Retrieval","created":"2022-04-04","cited_by_count":47},{"id":"2302.00275","title":"Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization","created":"2023-02-01","cited_by_count":41},{"id":"2308.06954","title":"Global Features are All You Need for Image Retrieval and Reranking","created":"2023-08-14","cited_by_count":41},{"id":"2404.18873","title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","created":"2024-04-29","cited_by_count":38},{"id":"2412.17007","title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","created":"2024-12-22","cited_by_count":38},{"id":"2405.14702","title":"G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models","created":"2024-05-23","cited_by_count":34},{"id":"2403.19584","title":"Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation","created":"2024-03-28","cited_by_count":32},{"id":"2506.14674","title":"Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models","created":"2025-06-17","cited_by_count":28},{"id":"2406.18572","title":"GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model","created":"2024-06-03","cited_by_count":27},{"id":"2408.06761","title":"Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IAN","created":"2024-08-13","cited_by_count":23},{"id":"2412.06781","title":"Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation","created":"2024-12-09","cited_by_count":23},{"id":"2405.20363","title":"LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild","created":"2024-05-30","cited_by_count":21},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20},{"id":"2505.13731","title":"GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization","created":"2025-05-19","cited_by_count":19},{"id":"2408.09474","title":"Image-Based Geolocation Using Large Vision-Language Models","created":"2024-08-18","cited_by_count":17},{"id":"2506.00785","title":"GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning","created":"2025-06-01","cited_by_count":16},{"id":"2505.18700","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","created":"2025-05-24","cited_by_count":14},{"id":"2112.15202","title":"Visual and Object Geo-localization: A Comprehensive Survey","created":"2021-12-30","cited_by_count":13},{"id":"2412.12170","title":"PickLLM: Context-Aware RL-Assisted Large Language Model Routing","created":"2024-12-12","cited_by_count":13},{"id":"2502.14412","title":"Evaluating Precise Geolocation Inference Capabilities of Vision Language Models","created":"2025-02-20","cited_by_count":12},{"id":"2508.01608","title":"From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models","created":"2025-08-03","cited_by_count":12},{"id":"2406.01917","title":"GOMAA-Geo: GOal Modality Agnostic Active Geo-localization","created":"2024-06-04","cited_by_count":11},{"id":"2412.08907","title":"Towards Interactive Global Geolocation Assistant","created":"2024-12-12","cited_by_count":11},{"id":"2601.05432","title":"Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization","created":"2026-01-08","cited_by_count":9},{"id":"2511.01082","title":"GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction","created":"2025-11-02","cited_by_count":7},{"id":"2602.09463","title":"SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning","created":"2026-02-10","cited_by_count":7},{"id":"2503.18142","title":"LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space","created":"2025-03-23","cited_by_count":6},{"id":"2601.00388","title":"Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach","created":"2026-01-01","cited_by_count":6},{"id":"2509.04334","title":"GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models","created":"2025-09-04","cited_by_count":5},{"id":"2602.12617","title":"GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics","created":"2026-02-13","cited_by_count":5},{"id":"2601.21278","title":"GeoRC: A Benchmark for Geolocation Reasoning Chains","created":"2026-01-29","cited_by_count":4},{"id":"2603.10463","title":"Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning","created":"2026-03-11","cited_by_count":3},{"id":"2603.13628","title":"Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models","created":"2026-03-13","cited_by_count":2},{"id":"2603.05708","title":"Interpretable Perception and Reasoning for Audiovisual Geolocation","created":"2026-03-05","cited_by_count":1}],"next_cursor":null}