USI-Brain: Enhancing Underwater Spatial Intelligence via Spatial Data-Driven Vision-Language Modeling
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/SKY-Zhu-91/USI-Brain
Terminology
Sources
- Qwen2.5-VL Technical Report
- Qwen3-VL Technical Report
- OceanGPT: A Large Language Model for Ocean Science Tasks
- Underwater Monocular Metric Depth Estimation: Real-World Benchmarks and Synthetic Fine-Tuning with Vision Foundation Models
- Scaling Spatial Intelligence with Multimodal Foundation Models
- SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
- InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
- SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
- USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots
- CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
- TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning
- OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
- SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
- NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
- EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery
- OceanGym: A Benchmark Environment for Underwater Embodied Agents
- Visual Spatial Tuning
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