500 citations · 1.3k across the 23 of their papers we have counts for
23 papers
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 --…
Language Models Meet World Models: Embodied Experiences Enhance Language Models
Jiannan Xiang, Tianhua Tao, Yi Gu +4
While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as…
FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement
Xiaonan Nie, Xupeng Miao, Zilong Wang +5
With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these…
Composable Text Controls in Latent Space with ODEs
Guangyi Liu, Zeyu Feng, Yuan Gao +7
Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and…
TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding
Le Zhang, Zichao Yang, Diyi Yang
Data augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word…
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Guangyi Liu, Zichao Yang, Tianhua Tao +6
Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a…
Local Additivity Based Data Augmentation for Semi-supervised NER
Jiaao Chen, Zhenghui Wang, Ran Tian +2
Named Entity Recognition (NER) is one of the first stages in deep language understanding yet current NER models heavily rely on human-annotated data. In this work, to alleviate the…
Progressive Generation of Long Text with Pretrained Language Models
Bowen Tan, Zichao Yang, Maruan AI-Shedivat +2
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it…
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
Jiaao Chen, Zichao Yang, Diyi Yang
This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amo…
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
Chao Zhang, Zichao Yang, Xiaodong He +1
Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their…
Data-to-Text Generation with Style Imitation
Shuai Lin, Wentao Wang, Zichao Yang +4
Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, senten…
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…
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
Zhiting Hu, Haoran Shi, Bowen Tan +12
We introduce Texar, an open-source toolkit aiming to support the broad set of text generation tasks that transform any inputs into natural language, such as machine translation, su…
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…
Unsupervised Text Style Transfer using Language Models as Discriminators
Zichao Yang, Zhiting Hu, Chris Dyer +2
Binary classifiers are often employed as discriminators in GAN-based unsupervised style transfer systems to ensure that transferred sentences are similar to sentences in the target…
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…
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
Zichao Yang, Zhiting Hu, Ruslan Salakhutdinov +1
Recent work on generative modeling of text has found that variational auto-encoders (VAE) incorporating LSTM decoders perform worse than simpler LSTM language models (Bowman et al.…
Reference-Aware Language Models
Zichao Yang, Phil Blunsom, Chris Dyer +1
We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to create mentions of entities and the…
Neural Machine Translation with Recurrent Attention Modeling
Zichao Yang, Zhiting Hu, Yuntian Deng +2
Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the…
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…