arxiv:2601.23159
Seungjun Lee
onandon
AI & ML interests
3D Computer Vision, Scene Understanding, Open-Vocabulary, Multi-Modality, LLM and etc.
Recent Activity
commented on
a paper
about 24 hours ago
Segment Any 3D Object with Language
commented on
a paper
about 24 hours ago
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language
Navigation
commented on
a paper
about 24 hours ago
Segment Any Events with Language
Organizations
None yet
