김승일
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
이혜민
Big Transfer (BiT): General Visual Representation Learning
이동훈
Non-Attentive Tacotron: Robust and Controllable Neural TTS systhesis Including Unsupervised Duration Modeling
최태균
MINILM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
황인중
https://openaccess.thecvf.com/content_CVPR_2020/papers/Nie_Total3DUnderstanding_Joint_Layout_Object_Pose_and_Mesh_Reconstruction_for_Indoor_CVPR_2020_paper.pdf
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
김연태
Training Generative Adversarial Networks with Limited Data
이상헌
Simulation-based Lidar Super-resolution for Ground Vehicles
김정석
Adaptive Ultrasound Beamforming using Deep Learning
윤석채→까방권
mixup: Beyond Emperical Risk Minimzation
박정은
D2RL: Deep Dense Architectures in Reinforcement Learning
김승일
Learning to Cartoonize Using White-box Representations
김태훈→윤석채
Extractive Summarization as Text Matching.pdf
Extractive Summarization as Text Matching
남성욱
BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals
김승일
An Intriguing failing of convolutional neural networks and the CoordConv solution
이혜민
Resource Elasticity in Distributed Deep Learning
최태균
Feedback-based Self-learning in Large-scale Conversational AI Agents
김연태
Image Generation from Scene Graphs