HJ

Leave HJ’s trace, All-In

[Articles] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Introducint BERT, bidirectional pre=training with Transformer

[Articles] Attention is All You Need

The foundational paper for modern NLP models, replacing RNNs with a self-attention mechanism.

[Articles] Denoising Diffusion Probabilistic Models

Diffusion Model

[Articles] Generative Adversarial Nets

GAN

[Articles] Deep Residual Learning for Image Recognition

ResNet