EO-Jev: Decision Model for Earth Observation
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/apolinario/decision-index
Terminology
Sources
- CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
- RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification
- reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis
- GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
- TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
- GeoChat: Grounded Large Vision-Language Model for Remote Sensing
- VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
- GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing
- Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
- LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
- Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
- VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
- GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
- EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM
- TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
- RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models
- EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
- GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes
- DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
- DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs