85 citations · 226 across the 15 of their papers we have counts for
15 papers
GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
Jing Zhang, Xiaokang Zhang, Daniel Zhang-Li +10
We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet kno…
A 2030 United States Macro Grid Unlocking Geographical Diversity to Accomplish Clean Energy Goals
Yixing Xu, Daniel Olsen, Bainan Xia +4
Some U.S. states have set clean energy goals and targets in an effort to decarbonize their electricity sectors. There are many reasons for such goals and targets, including the inc…
How Much Demand Flexibility Could Have Spared Texas from the 2021 Outage?
Dongqi Wu, Xiangtian Zheng, Ali Menati +5
The February 2021 Texas winter power outage has led to hundreds of deaths and billions of dollars in economic losses, largely due to the generation failure and record-breaking elec…
Manifold Regularized Dynamic Network Pruning
Yehui Tang, Yunhe Wang, Yixing Xu +4
Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices. Compared wit…
Learning Frequency Domain Approximation for Binary Neural Networks
Yixing Xu, Kai Han, Chang Xu +3
Binary neural networks (BNNs) represent original full-precision weights and activations into 1-bit with sign function. Since the gradient of the conventional sign function is almos…
Kernel Based Progressive Distillation for Adder Neural Networks
Yixing Xu, Chang Xu, Xinghao Chen +3
Adder Neural Networks (ANNs) which only contain additions bring us a new way of developing deep neural networks with low energy consumption. Unfortunately, there is an accuracy dro…
Training Binary Neural Networks through Learning with Noisy Supervision
Kai Han, Yunhe Wang, Yixing Xu +3
This paper formalizes the binarization operations over neural networks from a learning perspective. In contrast to classical hand crafted rules (\eg hard thresholding) to binarize…
SCOP: Scientific Control for Reliable Neural Network Pruning
Yehui Tang, Yunhe Wang, Yixing Xu +4
This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the im…
DC-NAS: Divide-and-Conquer Neural Architecture Search
Yunhe Wang, Yixing Xu, Dacheng Tao
Most applications demand high-performance deep neural architectures costing limited resources. Neural architecture searching is a way of automatically exploring optimal deep neural…
A Semi-Supervised Assessor of Neural Architectures
Yehui Tang, Yunhe Wang, Yixing Xu +6
Neural architecture search (NAS) aims to automatically design deep neural networks of satisfactory performance. Wherein, architecture performance predictor is critical to efficient…
Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks
Yehui Tang, Yunhe Wang, Yixing Xu +4
Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. On one hand, massive trainable parameters signifi…
U.S. Test System with High Spatial and Temporal Resolution for Renewable Integration Studies
Yixing Xu, Nathan Myhrvold, Dhileep Sivam +9
Planning for power systems with high penetrations of variable renewable energy requires higher spatial and temporal granularity. However, most publicly available test systems are o…
Positive-Unlabeled Compression on the Cloud
Yixing Xu, Yunhe Wang, Hanting Chen +4
Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providin…
ReNAS:Relativistic Evaluation of Neural Architecture Search
Yixing Xu, Yunhe Wang, Kai Han +4
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing…
Full-Stack Filters to Build Minimum Viable CNNs
Kai Han, Yunhe Wang, Yixing Xu +3
Deep convolutional neural networks (CNNs) are usually over-parameterized, which cannot be easily deployed on edge devices such as mobile phones and smart cameras. Existing works us…