237 citations · 1.3k across the 60 of their papers we have counts for
16 papers · 1 filter
Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs
Rachit Bansal, Aston Zhang, Rishabh Tiwari +8
Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can co…
SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing
Chaoyang He, Shuai Zheng, Aston Zhang +4
The mixture of Expert (MoE) parallelism is a recent advancement that scales up the model size with constant computational cost. MoE selects different sets of parameters (i.e., expe…
Learning Multimodal Data Augmentation in Feature Space
Zichang Liu, Zhiqiang Tang, Xingjian Shi +4
The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances…
Removing Batch Normalization Boosts Adversarial Training
Haotao Wang, Aston Zhang, Shuai Zheng +3
Adversarial training (AT) defends deep neural networks against adversarial attacks. One challenge that limits its practical application is the performance degradation on clean samp…
PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions
Eleonora Grassucci, Aston Zhang, Danilo Comminiello
Hypercomplex neural networks have proven to reduce the overall number of parameters while ensuring valuable performance by leveraging the properties of Clifford algebras. Recently,…
Dive into Deep Learning
Aston Zhang, Zachary C. Lipton, Mu Li +1
This open-source book represents our attempt to make deep learning approachable, teaching readers the concepts, the context, and the code. The entire book is drafted in Jupyter not…
Controllable and Diverse Text Generation in E-commerce
Huajie Shao, Jun Wang, Haohong Lin +4
In E-commerce, a key challenge in text generation is to find a good trade-off between word diversity and accuracy (relevance) in order to make generated text appear more natural an…
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with Parameters
Aston Zhang, Yi Tay, Shuai Zhang +4
Recent works have demonstrated reasonable success of representation learning in hypercomplex space. Specifically, "fully-connected layers with Quaternions" (4D hypercomplex numbers…
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Tianlong Chen, Yongduo Sui, Xuxi Chen +2
With graphs rapidly growing in size and deeper graph neural networks (GNNs) emerging, the training and inference of GNNs become increasingly expensive. Existing network weight prun…
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
Huajie Shao, Zhisheng Xiao, Shuochao Yao +3
This paper reviews the novel concept of controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic proper…
ControlVAE: Controllable Variational Autoencoder
Huajie Shao, Shuochao Yao, Dachun Sun +5
Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation le…
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
Jian Guo, He He, Tong He +13
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-…
G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators
Yunhui Long, Boxin Wang, Zhuolin Yang +4
Recent advances in machine learning have largely benefited from the massive accessible training data. However, large-scale data sharing has raised great privacy concerns. In this w…
RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations
Shuochao Yao, Yiran Zhao, Huajie Shao +4
Recent advances in deep learning have led various applications to unprecedented achievements, which could potentially bring higher intelligence to a broad spectrum of mobile and ub…
DeepIoT: Compressing Deep Neural Network Structures for Sensing Systems with a Compressor-Critic Framework
Shuochao Yao, Yiran Zhao, Aston Zhang +2
Recent advances in deep learning motivate the use of deep neutral networks in sensing applications, but their excessive resource needs on constrained embedded devices remain an imp…
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Shuochao Yao, Shaohan Hu, Yiran Zhao +2
Mobile sensing applications usually require time-series inputs from sensors. Some applications, such as tracking, can use sensed acceleration and rate of rotation to calculate disp…