Locateanything3d
1 mentions across 1 person
All mentions
“We present LocateAnything3D, a VLM-native recipe that casts 3D detection as a next-token prediction problem.”
Chain-of-Sight Enables VLM-Native 3D Detection via Sequential Token Prediction ↗1 mentions across 1 person
“We present LocateAnything3D, a VLM-native recipe that casts 3D detection as a next-token prediction problem.”
Chain-of-Sight Enables VLM-Native 3D Detection via Sequential Token Prediction ↗