Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking
TravPro, which converts standard annotations into ordered region pairs and fits a small readout on frozen vision--language model (VLM) patch tokens to these pairs, producing an ordering sensitive to surface condition that a per-class value cannot represent.
Ji-Hoon Hwang, Jisung Bae, E-In Son et al.
· 0 citations