vilt

A modern Laravel Admin Panel built with Vue 3, Inertia.js, and AI capabilities. Inspired by Filament but powered by the frontend.

⚡ Human resource management system built with VueJS, InertiaJS, Laravel 8 and Tailwind CSS

Securade.ai Sentinel - A monitoring and surveillance application that enables visual Q&A and video captioning for existing CCTV cameras.

This repo contains the original implementation of VAuLT, the Vision-and-Augmented-Language Transformer. We provide instructions to download some multimodal social-media datasets, and scripts to experiment with. VAuLT is a stack of Transformers, a LM like BERT that preprocesses the text input of ViLT

Vue.js + Inertia.js + Laravel + Tailwind CSS

Laravel package for handling file uploads with FilePond in the VILT stack (Vue, Inertia, Laravel, Tailwind).

Schema Digram Builder to convert digram to full dashboard and flutter apps CRUDs

Visual Question Answering with ViLT

A CLI and GUI for using the Vision-and-Language Transformer (ViLT) model for visual question answering (answering questions based on an image)

visual question answering in real-time

A Full Products Management With tons of functions and multi variations and prices, stock.

Clean starter template for Laravel 12; bridging Inertia 2.0, TailwindCSS 4.0, Vue3 JS and ZiggyJS or Wayfinder preinstalled. Default Laravel values (PHPUnit and SQLite). No extra bloat.

using ViLT for medical data

A benchmark suite for lightweight generative multimodal Vision-Language Models, comparing ViLT and SmolVLM under resource-constrained inference environments. Demonstrates CPU-only deployment, model evaluation, and multimodal reasoning with images and text, highlighting practical GenAI engineering for real-world applications.

Insurance Broker Software

Implemented Vision and Language Transformer (ViLT) Model with FastApi and Dockers

PyTorch multimodal VQA with ViLT, official-toolkit VQA v2 val 68.42, reproducible training and Gradio demo / 基于 PyTorch 的多模态 VQA，官方工具验证集 68.42，支持可复现训练与 Gradio 演示

Machine Learning project on Natural Language Visual Reasoning using Logistic Regression and ViLT on the NLVR2 dataset.