Minjae Lee

NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks

2022 · arXiv (Cornell University)

We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine learning. Our novel hybrid data structure can reduce …

GenOL: Generating Diverse Examples for Name-only Online Learning

2024 · arXiv (Cornell University)

Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate new concepts (e.g., classes), real-time manual annotation is impractical …

Privacy-Preserving Argumentative Explanations (Student Abstract)

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

We propose a framework for privacy-preserving argumentative explanations using homomorphic encryption. This method applies the Cheon-Kim-Kim-Song scheme, along with a soft k-means adapted for encrypted computation, to generate explanations without exposing sensitive data. By leveraging …