Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts
cs.CV, cs.AI
Submitted: 2025-12-08
Updated: 2026-11-11
Code: https://github.com/lostwolves/AerialVP
Terminology
Sources
- Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions
- VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous Driving
- Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models
- Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
- A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
- Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
- FG-CLIP: Fine-Grained Visual and Textual Alignment
- FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
- Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- Describe Anything: Detailed Localized Image and Video Captioning
- AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
- GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
- More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- LLaVA-OneVision: Easy Visual Task Transfer
- Where do Large Vision-Language Models Look at when Answering Questions?
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