Alert button
Picture for Kyunghyun Cho

Kyunghyun Cho

Alert button

Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks

Feb 10, 2022
Nan Wu, Stanisław Jastrzębski, Kyunghyun Cho, Krzysztof J. Geras

Figure 1 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Figure 2 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Figure 3 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Figure 4 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Viaarxiv icon

Generative multitask learning mitigates target-causing confounding

Feb 08, 2022
Taro Makino, Krzysztof Geras, Kyunghyun Cho

Figure 1 for Generative multitask learning mitigates target-causing confounding
Figure 2 for Generative multitask learning mitigates target-causing confounding
Figure 3 for Generative multitask learning mitigates target-causing confounding
Figure 4 for Generative multitask learning mitigates target-causing confounding
Viaarxiv icon

Causal Scene BERT: Improving object detection by searching for challenging groups of data

Feb 08, 2022
Cinjon Resnick, Or Litany, Amlan Kar, Karsten Kreis, James Lucas, Kyunghyun Cho, Sanja Fidler

Figure 1 for Causal Scene BERT: Improving object detection by searching for challenging groups of data
Figure 2 for Causal Scene BERT: Improving object detection by searching for challenging groups of data
Figure 3 for Causal Scene BERT: Improving object detection by searching for challenging groups of data
Figure 4 for Causal Scene BERT: Improving object detection by searching for challenging groups of data
Viaarxiv icon

LINDA: Unsupervised Learning to Interpolate in Natural Language Processing

Dec 28, 2021
Yekyung Kim, Seohyeong Jeong, Kyunghyun Cho

Figure 1 for LINDA: Unsupervised Learning to Interpolate in Natural Language Processing
Figure 2 for LINDA: Unsupervised Learning to Interpolate in Natural Language Processing
Figure 3 for LINDA: Unsupervised Learning to Interpolate in Natural Language Processing
Figure 4 for LINDA: Unsupervised Learning to Interpolate in Natural Language Processing
Viaarxiv icon

Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling

Dec 22, 2021
Ilia Kulikov, Maksim Eremeev, Kyunghyun Cho

Figure 1 for Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
Figure 2 for Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
Figure 3 for Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
Figure 4 for Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
Viaarxiv icon

Amortized Noisy Channel Neural Machine Translation

Dec 16, 2021
Richard Yuanzhe Pang, He He, Kyunghyun Cho

Figure 1 for Amortized Noisy Channel Neural Machine Translation
Figure 2 for Amortized Noisy Channel Neural Machine Translation
Figure 3 for Amortized Noisy Channel Neural Machine Translation
Figure 4 for Amortized Noisy Channel Neural Machine Translation
Viaarxiv icon

Causal Effect Variational Autoencoder with Uniform Treatment

Nov 16, 2021
Daniel Jiwoong Im, Kyunghyun Cho, Narges Razavian

Figure 1 for Causal Effect Variational Autoencoder with Uniform Treatment
Figure 2 for Causal Effect Variational Autoencoder with Uniform Treatment
Figure 3 for Causal Effect Variational Autoencoder with Uniform Treatment
Figure 4 for Causal Effect Variational Autoencoder with Uniform Treatment
Viaarxiv icon

DEEP: DEnoising Entity Pre-training for Neural Machine Translation

Nov 14, 2021
Junjie Hu, Hiroaki Hayashi, Kyunghyun Cho, Graham Neubig

Figure 1 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Figure 2 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Figure 3 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Figure 4 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Viaarxiv icon

AlphaD3M: Machine Learning Pipeline Synthesis

Nov 03, 2021
Iddo Drori, Yamuna Krishnamurthy, Remi Rampin, Raoni de Paula Lourenco, Jorge Piazentin Ono, Kyunghyun Cho, Claudio Silva, Juliana Freire

Figure 1 for AlphaD3M: Machine Learning Pipeline Synthesis
Figure 2 for AlphaD3M: Machine Learning Pipeline Synthesis
Figure 3 for AlphaD3M: Machine Learning Pipeline Synthesis
Figure 4 for AlphaD3M: Machine Learning Pipeline Synthesis
Viaarxiv icon

Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement

Oct 18, 2021
HyoJung Han, Seokchan Ahn, Yoonjung Choi, Insoo Chung, Sangha Kim, Kyunghyun Cho

Figure 1 for Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
Figure 2 for Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
Figure 3 for Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
Figure 4 for Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
Viaarxiv icon