Akarsh

latr. Implementation of LaTr: Layout-aware transformer for scene-text VQA,a novel multimodal architecture for Scene Text Visual Question Answering (STVQA)

docformer. Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)

TiLT-Implementation. Implementation of the paper: Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer.

docformerv2. This repo consists of my implementation of DocFormerV2

med-vqa. An approach for solving the problem of medical visual question answering

Eit-Enhanced-Interactive-Transformer. Implementation of EIT: ENHANCED INTERACTIVE TRANSFORMER

LiLT. My Implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

all_my_work. This repo consits of all my work done till now in the field of DL/ML

transformers_paper_implementation.

vision-transformer. An Implementation of the Paper: AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE

movie_recommendation_from_scratch. Python

LayoutLMv3-DocVQA. Example codebase for fine-tuning layoutLMv3 on DocVQA

customer-segmentation. Repository for Customer segmentation

instructor-embedding. [ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

brain-segmentation. This repository contains the code for the model and the deployment for the same in Flask

SSM-s-on-Document-AI-Task. This repository contains my experiments of SSM (State Space Models) on various Document AI Task