Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning
cs.AI
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/hiyouga/LLaMA-Factory
Terminology
Sources
- Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- WT5?! Training Text-to-Text Models to Explain their Predictions
- e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
- Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages
- A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy
- LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
- Qwen2.5-VL Technical Report
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases
- ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
- GPT-4o System Card
- Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation
- RankME: Reliable Human Ratings for Natural Language Generation
- A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluation
- Harnessing Large Language Models for Disaster Management: A Survey
- Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models
- AI-based Approach in Early Warning Systems: Focus on Emergency Communication Ecosystem and Citizen Participation in Nordic Countries
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection