500 citations · 1.3k across the 23 of their papers we have counts for
8 papers · 1 filter
Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
Guangyi Liu, Yu Wang, Zeyu Feng +9
The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations --…
Connecting the Dots Between MLE and RL for Sequence Prediction
Bowen Tan, Zhiting Hu, Zichao Yang +2
Sequence prediction models can be learned from example sequences with a variety of training algorithms. Maximum likelihood learning is simple and efficient, yet can suffer from com…
Deep Generative Models with Learnable Knowledge Constraints
Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov +4
The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end…
On Unifying Deep Generative Models
Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov +1
Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for genera…
Toward Controlled Generation of Text
Zhiting Hu, Zichao Yang, Xiaodan Liang +2
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plaus…
Stacked Attention Networks for Image Question Answering
Zichao Yang, Xiaodong He, Jianfeng Gao +2
This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query to search…
A la Carte - Learning Fast Kernels
Zichao Yang, Alexander J. Smola, Le Song +1
Kernel methods have great promise for learning rich statistical representations of large modern datasets. However, compared to neural networks, kernel methods have been perceived a…
Deep Fried Convnets
Zichao Yang, Marcin Moczulski, Misha Denil +4
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the…