Autonomous Driving with Vision-Language Models

8 repos

Multimodal AI systems that combine vision and language models for autonomous vehicle perception and decision-making. The cluster centers on LMDrive, a framework integrating large language models with visual encoders for end-to-end driving tasks, along with model variants (Vicuna, LLaVA, Llama) and supporting components. Projects here explore how conversational AI and image-text understanding can be applied to autonomous driving scenarios.

Related clusters