2 papers
cs.CV2026
ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration
Taekbeom Lee, Youngseok Jang, Jeonghwa Heo +2
Embodied reasoning and exploration are increasingly considered crucial abilities for robots operating in complex and unfamiliar environments. To accomplish tasks in such settings,…
cs.CV2026
SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis
Jeongjun Choi, Yeonsoo Park, H. Jin Kim
We present SceneNAT, a masked non-autoregressive Transformer for 3D indoor scene synthesis from natural language instructions. It generates complete scenes in a few parallel decodi…