Triplet Incremental Training Adapts General VLMs for Autonomous Driving
Researchers introduce a Triplet Incremental Training framework that instills 3D geometric awareness into general vision-language model backbones for autonomous driving without architectural overhauls. The method uses automatically constructed image-depth-QA triplets in a tri-stream pipeline: an unfrozen primary VLM for driving tasks, an auxiliary depth stream for implicit geometry learning, and a frozen twin VLM with logit-level KL distillation to prevent semantic drift. The depth branch is discarded at deployment, so the added geometric awareness incurs no inference overhead. Across four benchmarks, the approach reportedly outperforms state-of-the-art driving VLMs, rivals domain-specific experts in 3D perception, and retains general multimodal reasoning.
It offers a non-intrusive, deployment-ready method for turning general VLMs into capable driving models while preserving open-world reasoning and avoiding inference overhead.
Comments & Questions (0)
No comments yet
Be the first to comment!