Duc Nguyen Phan Tri's Projects
Use R for analyzing factors affecting the profits of start-ups
Create API endpoints to perform Create, Retrieve, Update and Delete operations on transient data with an Express server. Implement authentication at the session level using JSON Web Tokens (JWT) for authorized access.
:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
Blank Language Models study for the Vietnamese input method
Or called lecture helper
Play Thirteen(Vietnamese Tien Len) and Blackjack(also Vietnamese rules)
A CLI program built in c++ to manage university students
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具,使用你的音色或任意声音来录制音频
a state-of-the-art-level open visual language model | 多模态预训练模型
Using YOLOv8 to count a batch of materials.
Bầu Cua - Hoo Hey How - Gourd Crab Fish Tiger - Crabling(Crab+Gambling): A traditional gambling game at Vietnam and China.
Data Science Roadmap from A to Z
DSA make a cache
Config files for my GitHub profile.
Front-end development of a budget managing web application.
An AI-based web application, using IBM Watson to perform sentiment analysis on the input text.
A server-side online book review application and integrate it with a secure REST API server which will use authentication at session level using JWT.
MIPS four in a row game
Final project of working on git CLI and UI
Use IBM Watson services to find sentiments and emotions in text. The application was built using Express.js in the backend and React.js in the frontend application with Watson API.
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
Change from infix to prefix (and post-fix)
Introduction to Git and GitHub
shopping-app
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD)
A maze structure, with maze creating algorithm