Popular repositories Loading

1. drivefusion drivefusion Public

   DriveFusion is an open-source multimodal Vision–Language–Action model for autonomous driving that fuses visual perception, language understanding, and driving context (GPS and speed) to describe dr…

   Python 2

2. carla-data-collection carla-data-collection Public

   Autonomous-driving data pipeline for DriveFusion project built on the CARLA Simulator, generating cleaned multi-modal sensor data and VQA annotations for training vision-language action models.

   Python 1

3. data-preprocessing data-preprocessing Public

   Data preprocessing pipeline for the DriveFusionQA. It converts multiple autonomous-driving QA datasets into unified LLaMA and LLaVA-style instruction formats, with modular dataset preprocessors, JS…

   Python

4. Evaluate-Models Evaluate-Models Public

   Evaluation framework for the DriveFusion DriveFusionQA vision-language model, benchmarking Q&A performance on driving datasets using metrics like Lingo-Judge, BLEU, and BERTScore.

   Python

5. drivefusion-train drivefusion-train Public

   Training framework for the DriveFusion project that fine-tunes and train LLMs and multimodal vision-language models for driving tasks. Built on LLaMAFactory, it adds dataset processing, distributed…

   Python

6. car-deployment car-deployment Public

   Autonomous vehicle deployment system for DriveFusion combining ROS-based control with AI vision powered by the Qwen 2.5 vision-language model, enabling real-time driving, single-shot decisions, and…

   Python