Gravity and Flight: Learning to Navigate Fine-Grained Remote Sensing Scenes
cs.CV
Submitted: 2026-11-12
Updated: 2026-11-13
Code: https://github.com/Z0ngL1ng/Gravity-and-Flight
Terminology
Sources
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding
- Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs
- MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
- GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision
- GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes
- Multimodal Chain-of-Thought Reasoning in Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Proximal Policy Optimization Algorithms
- RSVQA: Visual Question Answering for Remote Sensing Data
- OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks
- VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
- EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework
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