GAN
DSBA 연구실 사전학습 논문 리뷰 - Generative Adversarial Networks
review of papers
summarization of the content of the paper that I understand
Latent Diffusion
DSBA 연구실 사전학습 논문 리뷰 - High-Resolution Image Synthesis with Latent Diffusion Models
VQ-VAE
DSBA 연구실 사전학습 논문 리뷰 - Neural Discrete Representation Learning
VAE
DSBA 연구실 사전학습 논문 리뷰 - Auto-Encoding Variational Bayes
DDPM
DSBA 연구실 사전학습 논문 리뷰 - Denoising Diffusion Probabilistic Models
CLIP
DSBA 연구실 사전학습 논문 리뷰 - Learning Transferable Visual Models From Natural Language Supervision
최근 읽은 논문들 간단 정리
transformer-xl, wav2letter, wav2vec
ViT and MLP-Mixer
What is inductive bias? Then, what is the key difference between ViT and CNN?
Reading papers
Read papers about MT-DNN, MASS, UNILM, XLNet, RoBERTa, ALBERT.
Attention is all you need
Deep dive into the Transformer architecture, especially the implementation in each layers.
Let's learn seq2seq!
Learn how to use seq2seq models using PyTorch