Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views
Paper • 2606.29513 • Published • 53
Keummin Ka
KEUMMin
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 year ago
Don't Look Only Once: Towards Multimodal Interactive Reasoning with
Selective Visual RevisitationOrganizations
upvoted a paper 16 days ago
upvoted 3
papers about 1 year ago
Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
Paper • 2506.00958 • Published • 20
Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation
Paper • 2505.18842 • Published • 36
Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance
Paper • 2505.16348 • Published • 52