Deep Learning

Non-sequential Autoregressive Shape Priors for 3D Completion, Reconstruction and Generation
Capstone project on exploring autoregressive shape priors for 3D objects and developing a unified framework for shape completion, single-view reconstruction and language guided generation
Video Capstone Page code (Coming Soon)
Non-sequential Autoregressive Shape Priors for 3D Completion, Reconstruction and Generation
Multi-Modal Multi-Hop Source Retrieval using Graph Convolutions
A graph convolution based approach to select multiple relevant sources (text or images) of information for multi-hop question answering.
Poster Project Report code (Coming soon)
Multi-Modal Multi-Hop Source Retrieval using Graph Convolutions
Inverting 3D Deep Learning Architectures
Project on inverting models of 3D object recognition and classification in order to analyze interpretability
Project Report Code (Coming Soon)
Inverting 3D Deep Learning Architectures