Junru Wu

6

Papers

2

Total Citations

Papers (6)

Principled Architecture-aware Scaling of Hyperparameters

Gaze Prediction in Dynamic 360° Immersive Videos

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

Stronger NAS with Weaker Predictors

Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization

Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions