Final-year Computer Science PhD Candidate at Johns Hopkins University
AI and computational cognitive researcher bridging cognitive science, machine learning, and computer vision
Current research focuses on 3D analysis by synthesis, 3D part models, interpretability, model merging, and efficient/constrained learning of generative models (2D/3D/4D and LLMs/VLMs)
Past work includes unsupervised learning, 3D generative models, continual learning, domain adaptation, and model robustness
Currently working on part-based 3D object representation and completion, image-to-3D generative modeling, and lifelong learning for internet-scale large vision-language models