{"total":89,"rows":[{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51,"area":null},{"id":"2507.09477","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","created":"2025-07-13","cited_by_count":42,"area":"lr"},{"id":"2104.03090","title":"HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks","created":"2021-04-07","cited_by_count":39,"area":null},{"id":"2504.12330","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","created":"2025-04-13","cited_by_count":31,"area":"rag"},{"id":"2403.03077","title":"MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding","created":"2024-03-05","cited_by_count":29,"area":null},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"id":"2406.15477","title":"CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2402.16832","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space","created":"2024-02-26","cited_by_count":22,"area":"mllm"},{"id":"2108.12828","title":"MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification","created":"2021-08-29","cited_by_count":20,"area":null},{"id":"2501.06932","title":"Harnessing Large Language Models for Disaster Management: A Survey","created":"2025-01-12","cited_by_count":20,"area":null},{"id":"2503.12972","title":"Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning","created":"2025-03-17","cited_by_count":19,"area":"lr"},{"id":"2410.08814","title":"A social context-aware graph-based multimodal attentive learning framework for disaster content classification during emergencies: a benchmark dataset and method","created":"2024-10-11","cited_by_count":12,"area":null},{"id":"2312.01882","title":"Unleashing the Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenario","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2205.09744","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2210.14190","title":"CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2309.05494","title":"CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts","created":"2023-09-11","cited_by_count":7,"area":null},{"id":"2411.14717","title":"FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data","created":"2024-11-22","cited_by_count":7,"area":"mllm"},{"id":"2401.06194","title":"CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classification","created":"2024-01-11","cited_by_count":6,"area":null},{"id":"2211.00543","title":"Geo-Information Harvesting from Social Media Data","created":"2022-11-01","cited_by_count":5,"area":null},{"id":"2401.02838","title":"CrisisViT: A Robust Vision Transformer for Crisis Image Classification","created":"2024-01-05","cited_by_count":5,"area":null},{"id":"2507.07015","title":"MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation","created":"2025-07-09","cited_by_count":5,"area":"distill"},{"id":"2509.14030","title":"CrowdAgent: Multi-Agent Managed Multi-Source Annotation System","created":"2025-09-17","cited_by_count":5,"area":"agents"},{"id":"2511.19887","title":"Distilling Cross-Modal Knowledge via Feature Disentanglement","created":"2025-11-25","cited_by_count":5,"area":"distill"},{"id":"2104.04184","title":"Robust Training of Social Media Image Classification Models for Rapid Disaster Response","created":"2021-04-09","cited_by_count":4,"area":null},{"id":"2205.11454","title":"What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability","created":"2022-05-23","cited_by_count":4,"area":null},{"id":"2211.02646","title":"Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2212.10735","title":"NADBenchmarks -- a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2402.09036","title":"Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2202.00050","title":"Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data","created":"2022-01-31","cited_by_count":3,"area":"distill"},{"id":"2209.02139","title":"Cross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios","created":"2022-09-05","cited_by_count":3,"area":null},{"id":"2211.11468","title":"Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2301.00321","title":"Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2305.11536","title":"PORTRAIT: a hybrid aPproach tO cReate extractive ground-TRuth summAry for dIsaster evenT","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2111.07815","title":"Sentiment Analysis of Fashion Related Posts in Social Media","created":"2021-11-15","cited_by_count":2,"area":null},{"id":"2301.00320","title":"Relevance Classification of Flood-related Twitter Posts via Multiple Transformers","created":"2023-01-01","cited_by_count":2,"area":null},{"id":"2305.02932","title":"Image Captioners Sometimes Tell More Than Images They See","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2307.02712","title":"Multi-Similarity Contrastive Learning","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2403.16614","title":"Semantically Enriched Cross-Lingual Sentence Embeddings for Crisis-related Social Media Texts","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2410.00182","title":"Zero-Shot Classification of Crisis Tweets Using Instruction-Finetuned Large Language Models","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2505.19699","title":"Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments","created":"2025-05-26","cited_by_count":2,"area":"moe"},{"id":"2601.18493","title":"DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2111.06334","title":"Identification of Fine-Grained Location Mentions in Crisis Tweets","created":"2021-11-11","cited_by_count":1,"area":null},{"id":"2401.00894","title":"Balanced Multi-modal Federated Learning via Cross-Modal Infiltration","created":"2023-12-31","cited_by_count":1,"area":null},{"id":"2405.06541","title":"ATSumm: Auxiliary information enhanced approach for abstractive disaster Tweet Summarization with sparse training data","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2410.06370","title":"HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2506.04672","title":"FedAPM: Federated Learning via ADMM with Partial Model Personalization","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2506.22036","title":"Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion","created":"2025-06-27","cited_by_count":1,"area":"lr"},{"id":"2507.02781","title":"From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2509.11634","title":"Assessing On-the-Ground Disaster Impact Using Online Data Sources","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2512.08071","title":"CAMO: Causality-Guided Adversarial Multimodal Domain Generalization for Crisis Classification","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2601.13839","title":"DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes","created":"2026-01-20","cited_by_count":1,"area":"mllm"},{"id":"2604.04969","title":"MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation","created":"2026-04-04","cited_by_count":1,"area":"mllm"},{"id":"2604.26597","title":"Translating Under Pressure: Domain-Aware LLMs for Crisis Communication","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2101.05656","title":"On Informative Tweet Identification For Tracking Mass Events","created":"2021-01-14","cited_by_count":0,"area":null},{"id":"2206.03248","title":"Rites de Passage: Elucidating Displacement to Emplacement of Refugees on Twitter","created":"2022-05-30","cited_by_count":0,"area":null},{"id":"2302.13403","title":"Tweets Under the Rubble: Detection of Messages Calling for Help in Earthquake Disaster","created":"2023-02-26","cited_by_count":0,"area":null},{"id":"2312.11020","title":"Information Type Classification with Contrastive Task-Specialized Sentence Encoders","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2405.06551","title":"ADSumm: Annotated Ground-truth Summary Datasets for Disaster Tweet Summarization","created":"2024-05-10","cited_by_count":0,"area":null},{"id":"2406.15816","title":"Reading Is Believing: Revisiting Language Bottleneck Models for Image Classification","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2407.05219","title":"Flood of Techniques and Drought of Theories: Emotion Mining in Disasters","created":"2024-07-07","cited_by_count":0,"area":null},{"id":"2410.05359","title":"Interactive Event Sifting using Bayesian Graph Neural Networks","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2504.09941","title":"FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environments","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2504.13231","title":"WildFireCan-MMD: A Multimodal Dataset for Classification of User-Generated Content During Wildfires in Canada","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2507.05165","title":"Differential Attention for Multimodal Crisis Event Analysis","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2509.01576","title":"Structured AI Decision-Making in Disaster Management","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2511.00004","title":"Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2512.01896","title":"OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2512.09092","title":"Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2602.00030","title":"RAPTOR-AI for Disaster OODA Loop: Hierarchical Multimodal RAG with Experience-Driven Agentic Decision-Making","created":"2026-01-18","cited_by_count":0,"area":"agents"},{"id":"2603.05957","title":"Domain-Adaptive Model Merging Across Disconnected Modes","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.18611","title":"Cross-Modal Rationale Transfer for Explainable Humanitarian Classification on Social Media","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.08196","title":"Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.08448","title":"LLM-guided Semi-Supervised Approaches for Social Media Crisis Data Classification","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.11348","title":"Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.18554","title":"Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusion","created":"2026-06-17","cited_by_count":0,"area":"diffusion"},{"id":"2606.26654","title":"SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.12111","title":"PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.12112","title":"Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning","created":"2026-07-13","cited_by_count":0,"area":"mllm"},{"id":"2607.13192","title":"Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.28269","title":"Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.00012","title":"Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.23525","title":"EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.00879","title":"Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.04281","title":"When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.16964","title":"HUMAID-NER: A Disaster Tweet Dataset for Joint Named Entity Recognition and Event Classification via Uncertainty-Weighted Multitask Learning","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.35821","title":"CrisisFake: Benchmark Validity of AI-Generated Text Detection for Disaster Social Sensing","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.37243","title":"Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2610.15403","title":"A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning","created":"2026-10-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}