Track 1: Driving with Language
-
Updated
Aug 23, 2025 - Python
#
drivelm
Here are 4 public repositories matching this topic...
Fine-tuning Vision-Language Models for autonomous driving VQA: custom i.i.d. DriveLM-nuScenes split, ~132k pseudo-labels generated by Qwen3 from nuScenes sensor priors (3D bounding boxes, LiDAR depth, tracking trajectories), and InternVL2-2B LoRA fine-tuning reaching a DriveLM score of 0.589. Master's thesis, CTU Prague 2026.
-
Updated
Jun 15, 2026 - Python
Reproducible six-camera DriveLM pipeline with Qwen2.5-VL LoRA SFT, evaluation and continuous reasoning demos
-
Updated
Aug 29, 2026 - Python
Distills a 72B driving vision-language model down to 4B, then measures what survives: whether it still looks at the camera feeds, and whether its confidence still means anything once quantized for in-car hardware.
lora model-calibration autonomous-driving quantization knowledge-distillation openvino npu edge-ai nuscenes vision-language-model qwen-vl drivelm
-
Updated
Aug 14, 2026 - Python
Add this topic to your repo
To associate your repository with the drivelm topic, visit your repo's landing page and select "manage topics."