Zobrazeno 71 - 80
of 580
pro vyhledávání: '"Li, Chunyuan"'
Autor:
Yuan, Siyang, Bai, Ke, Chen, Liqun, Zhang, Yizhe, Tao, Chenyang, Li, Chunyuan, Wang, Guoyin, Henao, Ricardo, Carin, Lawrence
Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural language processing. This paper investigates a novel approach for the ident
Externí odkaz:
http://arxiv.org/abs/2008.06597
Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence. Most existing methods borrow ideas from video generation, which naively treat skeleton nodes/
Externí odkaz:
http://arxiv.org/abs/2007.01971
We present a new method SOLOIST that uses transfer learning and machine teaching to build task bots at scale. We parameterize classical modular task-oriented dialog systems using a Transformer-based auto-regressive language model, which subsumes diff
Externí odkaz:
http://arxiv.org/abs/2005.05298
Large-scale pre-trained language models, such as BERT and GPT-2, have achieved excellent performance in language representation learning and free-form text generation. However, these models cannot be directly employed to generate text under specified
Externí odkaz:
http://arxiv.org/abs/2005.00558
Autor:
Li, Xiujun, Yin, Xi, Li, Chunyuan, Zhang, Pengchuan, Hu, Xiaowei, Zhang, Lei, Wang, Lijuan, Hu, Houdong, Dong, Li, Wei, Furu, Choi, Yejin, Gao, Jianfeng
Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be
Externí odkaz:
http://arxiv.org/abs/2004.06165
When trained effectively, the Variational Autoencoder (VAE) can be both a powerful generative model and an effective representation learning framework for natural language. In this paper, we propose the first large-scale language VAE model, Optimus.
Externí odkaz:
http://arxiv.org/abs/2004.04092
The instability in GAN training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing feature matching with mini-batch statistics, due to a fragile balance betwe
Externí odkaz:
http://arxiv.org/abs/2004.02088
Autor:
Xia, Qiaolin, Li, Xiujun, Li, Chunyuan, Bisk, Yonatan, Sui, Zhifang, Gao, Jianfeng, Choi, Yejin, Smith, Noah A.
Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified. In this paper, we present a novel training paradigm,
Externí odkaz:
http://arxiv.org/abs/2003.00857
Conventional survival analysis approaches estimate risk scores or individualized time-to-event distributions conditioned on covariates. In practice, there is often great population-level phenotypic heterogeneity, resulting from (unknown) subpopulatio
Externí odkaz:
http://arxiv.org/abs/2003.00355
Autor:
Peng, Baolin, Zhu, Chenguang, Li, Chunyuan, Li, Xiujun, Li, Jinchao, Zeng, Michael, Gao, Jianfeng
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical mo
Externí odkaz:
http://arxiv.org/abs/2002.12328