SonarLLM: A Native Sonar--Optical Multimodal Large Language Model for Underwater Perception
cs.AI
Submitted: 2026-08-25
Updated: 2026-08-25
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis
- Qwen3-VL Technical Report
- A Sonar-Visual Dataset for Cross-Modal Underwater Robot Perception
- LoRA: Low-Rank Adaptation of Large Language Models
- Kimi K3: Open Frontier Intelligence
- Improved Baselines with Visual Instruction Tuning
- DINOv2: Learning Robust Visual Features without Supervision
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- OceanGym: A Benchmark Environment for Underwater Embodied Agents
- OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
- MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
- UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding
- MarineGPT: Unlocking Secrets of Ocean to the Public
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