5 papers
Inside-JEPA: From Prediction to Relational Grounding in Latent World Models
Hossein Resani, Javen Qinfeng Shi
Joint-embedding predictive architectures (JEPAs) learn world models in latent space, enabling efficient planning but leaving their states opaque. We introduce Inside-JEPA, which pl…
Do-JEPA: From Masking to Intervention in Latent World Models
Hossein Resani, Javen Qinfeng Shi
Latent world models are trained to predict what happens next, so nothing in their objective separates what an action caused from what merely co-occurred with it. Object-masking mod…
ToosiCubix: Monocular 3D Cuboid Labeling via Vehicle Part Annotations
Behrooz Nasihatkon, Hossein Resani, Amirreza Mehrzadian
Many existing methods for 3D cuboid annotation of vehicles rely on expensive and carefully calibrated camera-LiDAR or stereo setups, limiting their accessibility for large-scale da…
MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction
Hossein Resani, Behrooz Nasihatkon
In this paper, we introduce a novel framework for memory-efficient and privacy-preserving continual learning in 3D object classification. Unlike conventional memory-based approache…
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection
Hossein Resani, Behrooz Nasihatkon, Mohammadreza Alimoradi Jazi
We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral cluste…