Publications
2025
-
ORIC: Benchmarking Object Recognition in Incongruous Context for Large Vision-Language ModelsIn preprint, arXiv, 2025 -
Point-SAM: Promptable 3D Segmentation Model for Point CloudsIn The Thirteenth International Conference on Learning Representations (ICLR), 2025 -
PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood EstimationIn ICCV 2025 Workshop on Wild 3D: 3D Modeling, Reconstruction, and Generation in the Wild, 2025