Thanh Tin Nguyen's repositories
owlvit_segment_anything
Combining OwlViT with Segment Anything - Open-vocabulary Detection and Segmentation (Text-conditioned, and Image-conditioned)
Line_Segmentation
Line Segmentation Based on Bi-variate Gauss Statistic and Distance Metric; and Handwritten Recognition
VLSP_ImageCaptioning
VLSP2021 vieCap4H Challenge: Automatic image caption generation for healthcare domains in Vietnamese
Deforestation_Segmentation
Deforestation Segmentation
Coarse-To-Fine-Fusion-for-Language-Grounding-in-3D-Navigation
Auto Encoder Enhanced Vision Language Navigation in Vizdoom, KBS 2023
Multigoal_VLN_Vizdoom
Fourier Transform Enhanced Vision Language Multi-goal Navigation
Automate_Research
Try to automate everything for research
blogs
Jupyter notebooks that support my graph data science blog posts at https://bratanic-tomaz.medium.com/
CLIPQ
A simple implementation of a CLIP that splits up an image into quandrants and then gets the embeddings for each quandrant
DocumentGPT
DocumentGPT is a web application that allows you to chat over your research document using OpenAI's chat API and perform semantic search using vector databases. This tool provides a seamless interface for interacting with your research document, exploring search results, and engaging in a conversation with an AI chatbot.
Elementary-Math-Solving-Zalo-AI-2023
Baseline for ZaloAI Challenge 2023 Elementary Math Solving
Everything-about-LLMs
A work in progress. Trying to write about all interesting or necessary pieces in the current development of LLMs and generative AI. Gradually adding more topics.
ivadomed
Repository on the collaborative IVADO medical imaging project between the Mila and NeuroPoly labs.
kaggle_benetech
Solution for the Benetech - Making Graphs Accessible Kaggle Competition
LaVy
Pioneering in Vietnamese Multimodal Large Language Model
LLaMA2
This repository contains an implementation of the LLaMA 2 (Large Language Model Meta AI) model, a Generative Pretrained Transformer (GPT) variant. The implementation focuses on the model architecture and the inference process. The code is restructured and heavily commented to facilitate easy understanding of the key parts of the architecture.
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
llm-claude-3
LLM plugin for interacting with the Claude 3 family of models
llm-course
Course with a roadmap and notebooks to get into Large Language Models (LLMs).
llm4regression
Examining how large language models (LLMs) perform across various synthetic regression tasks when given (input, output) examples in their context, without any parameter update
MambaRobustness
Towards Evaluating the Robustness of Visual State Space Models
multi-token-pred
Train toy models using multi-token prediction objective
sg2im
Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018
Transformer-Distribution-Visualizer
A Research Toolkit that allows users to select a transformer model, specify a decoding strategy to generate text, which are then displayed in an interactive fashion to understand model probabilities.