Showing 2026Show all
2 papers · 1 filter
cs.CV2026
SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
Chris Choy, Junha Lee, Chunghyun Park +2
Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foun…
cs.RO2026
DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning
Junha Lee, Eunha Park, Minsu Cho
Language-driven dexterous grasp generation requires the models to understand task semantics, 3D geometry, and complex hand-object interactions. While vision-language models have be…