Chadrick Blog

paper review: "Graph Attention Networks"

paper review: "Graph Attention Networks"

pytorch implementation of sinusoidal position encoding

pytorch implementation of sinusoidal position encoding

relu, gelu , swish, mish activation function comparison

relu, gelu , swish, mish activation function comparison

paper review: "Donut : Document Understanding Transformer without OCR"

paper review: "Donut : Document Understanding Transformer without OCR"

paper review: “BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension”

paper review: “BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension”

paper summary: "DocFormer: End-to-End Transformer for Document Understanding"

paper summary: "DocFormer: End-to-End Transformer for Document Understanding"

paper review: "LayoutLMV2: Multi-Modal Pre-training for Visually-Rich Document Understanding"

paper review: "LayoutLMV2: Multi-Modal Pre-training for Visually-Rich Document Understanding"

paper summary: "BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents"

paper summary: "BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents"

paper summary “Perceiver IO: A General Architecture for Structured Inputs & Outputs”

paper summary “Perceiver IO: A General Architecture for Structured Inputs & Outputs”

paper summary: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

paper summary: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows