2 papers
cs.CV2026
GeoThinker-: Endogenous Predictive World Representations for Fast Spatial Intelligence
Haoyuan Li, Qihang Cao, Huanyuan Zhou +10
Existing geometry-aware Multimodal Large Language Models (MLLMs) increasingly rely on external 3D encoders to provide structural priors, but executing these additional encoder path…
cs.RO2026
CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image
Dongwon Son, Junhyek Han, Yoontae Cho +5
Robots operating safely in cluttered everyday environments often need to infer scene geometry from partial observations. Methods that detect objects in 2D and reconstruct them inde…