112 citations · 301 across the 9 of their papers we have counts for
9 papers
Principled Architecture-aware Scaling of Hyperparameters
Wuyang Chen, Junru Wu, Zhangyang Wang +1
Training a high-quality deep neural network requires choosing suitable hyperparameters, which is a non-trivial and expensive process. Current works try to automatically optimize or…
Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization
Junru Wu, Yi Liang, Feng Han +3
Self-supervised pre-training recently demonstrates success on large-scale multimodal data, and state-of-the-art contrastive learning methods often enforce the feature consistency f…
Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN
Qiucheng Wu, Yifan Jiang, Junru Wu +5
The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only t…
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
Yifan Jiang, Xinyu Gong, Junru Wu +3
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often co…
Stronger NAS with Weaker Predictors
Junru Wu, Xiyang Dai, Dongdong Chen +7
Neural Architecture Search (NAS) often trains and evaluates a large number of architectures. Recent predictor-based NAS approaches attempt to alleviate such heavy computation costs…
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Orest Kupyn, Tetiana Martyniuk, Junru Wu +1
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring effic…