{"total":78,"rows":[{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96,"area":null},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2412.11936","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","created":"2024-12-16","cited_by_count":55,"area":"lr"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33,"area":"lr"},{"id":"2502.12520","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","created":"2025-02-18","cited_by_count":32,"area":"mllm"},{"id":"2502.12532","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","created":"2025-02-18","cited_by_count":32,"area":"agents"},{"id":"2407.02157","title":"FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs","created":"2024-07-02","cited_by_count":30,"area":null},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"id":"2502.11051","title":"MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models","created":"2025-02-16","cited_by_count":30,"area":"mllm"},{"id":"2408.17267","title":"UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios","created":"2024-08-30","cited_by_count":28,"area":"mllm"},{"id":"2506.14674","title":"Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models","created":"2025-06-17","cited_by_count":28,"area":"wm"},{"id":"2406.13945","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","created":"2024-06-20","cited_by_count":27,"area":"wm"},{"id":"2503.13502","title":"Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2503.18132","title":"MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection","created":"2025-03-23","cited_by_count":24,"area":"lr"},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2503.11835","title":"How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook","created":"2025-03-14","cited_by_count":20,"area":null},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2402.16142","title":"From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility","created":"2024-02-25","cited_by_count":19,"area":null},{"id":"2403.16831","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17,"area":"alignment"},{"id":"2412.00953","title":"BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis","created":"2024-12-01","cited_by_count":16,"area":null},{"id":"2312.17016","title":"On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications","created":"2023-12-23","cited_by_count":15,"area":null},{"id":"2503.09128","title":"FlexiReg: Flexible Urban Region Representation Learning","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2410.18032","title":"GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration","created":"2024-10-23","cited_by_count":12,"area":"agents"},{"id":"2504.09848","title":"A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science","created":"2025-04-14","cited_by_count":12,"area":"wm"},{"id":"2408.11366","title":"GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding","created":"2024-08-21","cited_by_count":10,"area":"lr"},{"id":"2502.10038","title":"POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning","created":"2025-02-14","cited_by_count":10,"area":null},{"id":"2503.15417","title":"Temporal Regularization Makes Your Video Generator Stronger","created":"2025-03-19","cited_by_count":10,"area":null},{"id":"2506.01364","title":"Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review","created":"2025-06-02","cited_by_count":10,"area":null},{"id":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2404.07919","title":"ST-LoRA: Low-rank Adaptation for Spatio-Temporal Forecasting","created":"2024-04-11","cited_by_count":9,"area":null},{"id":"2408.12133","title":"Self-Supervised Representation Learning for Geospatial Objects: A Survey","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2408.05920","title":"Urban Region Pre-training and Prompting: A Graph-based Approach","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2311.11319","title":"GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation","created":"2023-11-19","cited_by_count":7,"area":null},{"id":"2410.04819","title":"MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models","created":"2024-10-07","cited_by_count":7,"area":"mllm"},{"id":"2502.11916","title":"EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models","created":"2025-02-17","cited_by_count":7,"area":"mllm"},{"id":"2505.13965","title":"CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring","created":"2025-05-20","cited_by_count":7,"area":"agents"},{"id":"2506.00530","title":"CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing","created":"2025-05-31","cited_by_count":7,"area":"mllm"},{"id":"2509.22228","title":"UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2506.02744","title":"Enriching Location Representation with Detailed Semantic Information","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2405.14135","title":"Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2506.01297","title":"MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2507.00914","title":"Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications","created":"2025-07-01","cited_by_count":4,"area":"agents"},{"id":"2504.12345","title":"Reimagining Urban Science: Scaling Causal Inference with Large Language Models","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2505.14406","title":"Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.14570","title":"From Points to Places: Towards Human Mobility-Driven Spatiotemporal Foundation Models via Understanding Places","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.19586","title":"Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2510.16555","title":"Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2412.02114","title":"Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2503.07991","title":"Boundary Prompting: Elastic Urban Region Representation via Graph-based Spatial Tokenization","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.02009","title":"Urban Computing in the Era of Large Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2505.15870","title":"Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2508.16623","title":"RAST: A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2510.09894","title":"Beyond AlphaEarth: Toward Human-Centered Geospatial Foundation Models via POI-Guided Contrastive Learning","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2511.07062","title":"Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2601.22746","title":"UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling","created":"2026-01-30","cited_by_count":2,"area":"moe"},{"id":"2603.02435","title":"VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings","created":"2026-03-02","cited_by_count":2,"area":"mllm"},{"id":"2507.13323","title":"GeoReg: Weight-Constrained Few-Shot Regression for Socio-Economic Estimation using LLM","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2507.17795","title":"LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic Prediction","created":"2025-07-23","cited_by_count":1,"area":"diffusion"},{"id":"2511.06269","title":"LLM$^3$-DTI: A Large Language Model and Multi-modal data co-powered framework for Drug-Target Interaction prediction","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2512.03558","title":"CartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2602.15750","title":"UrbanVerse: Learning Urban Region Representation Across Cities and Tasks","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2602.19442","title":"UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment","created":"2026-02-23","cited_by_count":1,"area":"mllm"},{"id":"2606.00871","title":"Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2607.13558","title":"Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.21041","title":"CoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2507.11558","title":"Reprogramming Vision Foundation Models for Spatio-Temporal Forecasting","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.19499","title":"Sat2Flow: A Structure-Aware Diffusion Framework for Human Flow Generation from Satellite Imagery","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.23772","title":"A Modality-Tailored Graph Modeling Framework for Urban Region Representation via Contrastive Learning","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2602.01610","title":"ToPT: Task-Oriented Prompt Tuning for Urban Region Representation Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2606.08046","title":"OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.15890","title":"UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics","created":"2026-06-14","cited_by_count":0,"area":"mllm"},{"id":"2607.07292","title":"CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.01753","title":"Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit","created":"2026-08-03","cited_by_count":0,"area":"mllm"},{"id":"2608.17848","title":"MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18546","title":"MARCUS: Missing-Aware Region Representation with Contextual Urban Signals for Rent Prediction","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2610.13390","title":"PlacePulse: Learning Transferable Place Representations from Structural Geographic Data","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}