Postdoctoral researcher at POSTECH Institute of AI, working with Prof. Minsu Cho.

I work on 3D visual perception for systems that act in the physical world: efficient architectures (Fast Point Transformer, PointMixer), geometric deep learning (CHOIR, RIST), open-vocabulary perception (Mosaic3D, SpaCeFormer), and active perception (Affostruction). I am now bringing these together into 3D world action models for robot manipulation.