Junwei Liang

4

Papers

35

Total Citations

Papers (4)

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding