PanoVLN

PanoVLN is a vision-and-language navigation policy that follows instructions from 360ยฐ RGB observations. It combines a Qwen3.5-4B backbone with PanoVGGT geometry features and predicts 18-action sequences.

Downloads last month
27
Safetensors
Model size
6B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Paper for wangzhen-w/PanoVLN_realworld