Aurojit Panda — accepted AI-conference papers

2025

On Scaling Up 3D Gaussian Splatting Training

Hexu Zhao, Haoyang Weng, Daohan Lu, Ang Li, Jinyang Li, Aurojit Panda +1

ICLR 2025oral

3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and large-scale 3D reconstruction tasks due to memory constraints…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2022

Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

Jinkun Lin, Anqi Zhang, Mathias Lécuyer, Jinyang Li, Aurojit Panda, Siddhartha Sen

ICML 2022spotlight

We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to…

Cited by 72 Source ↗PDF ↗code ↗Scholar ↗