steventan0110

align-filter

Repository for "Bitext Mining for Low-Resource Languages via Contrastive Learning"

DiffNorm

Official repository for our NeurIPS 2024 paper: DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation

FLRimageProcessing

image processing codes for ECE drone project. 1. Detect three Region of Interests (ROIs). 2. Based on the ROIs, the code calculates mean value of crucial area to determine if the person being scanned is alive.

LegoUltrasound

Summer Research on Ultrasound Image Processing at Hopkins advised by Professor Emad Doctor. Tools used include MATLAB deep learning and image processing toolbox as well as K-wave simulation toolbox

MICaptioning

NMT_RL_Filter

Filter training data for neural machine translation model `on the fly` with reinforcement learning agent. Work based on previous research from Carnegie Mellon University (multi-DDS) and Johns Hopkins University (LASER score for data-sets from WMT-20)

NMTModelAttack

Code repository for the paper "Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation" with instructions to reproduce the results. Paper accepted by the conference of the Association for Machine Translation in the Americas (AMTA 2022)

ObjectDetectionRL

Final Project for Reinforcement Learning

OCT_preprocess

Python implementation of optical coherence tomography(OCT) data pre-process: 1.retina detection 2. OCT normalization 3. retina flatten

STAR

Official Repository for paper "Streaming Sequence Transduction through Dynamic Compression"

steventan0110/OCT_preprocess

Python implementation of optical coherence tomography(OCT) data pre-process: 1.retina detection 2. OCT normalization 3. retina flatten

steventan0110/LegoUltrasound

Summer Research on Ultrasound Image Processing at Hopkins advised by Professor Emad Doctor. Tools used include MATLAB deep learning and image processing toolbox as well as K-wave simulation toolbox

steventan0110/align-filter

Repository for "Bitext Mining for Low-Resource Languages via Contrastive Learning"

steventan0110/NMT_RL_Filter

Filter training data for neural machine translation model `on the fly` with reinforcement learning agent. Work based on previous research from Carnegie Mellon University (multi-DDS) and Johns Hopkins University (LASER score for data-sets from WMT-20)

steventan0110/FLRimageProcessing

image processing codes for ECE drone project. 1. Detect three Region of Interests (ROIs). 2. Based on the ROIs, the code calculates mean value of crucial area to determine if the person being scanned is alive.

steventan0110/NMTModelAttack

Code repository for the paper "Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation" with instructions to reproduce the results. Paper accepted by the conference of the Association for Machine Translation in the Americas (AMTA 2022)

steventan0110/DiffNorm

Official repository for our NeurIPS 2024 paper: DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation

steventan0110/MICaptioning

steventan0110/ObjectDetectionRL

Final Project for Reinforcement Learning

steventan0110/Paper_Reading

Summary of my past readings on ML, CV, NLP-related paper. Currently, the update focuses on machine translation and general model architectures.

steventan0110/STAR

Official Repository for paper "Streaming Sequence Transduction through Dynamic Compression"

steventan0110/JHU_SSO

steventan0110/OOSE

On-Develop web app for Johns Hopkins University's Course Assistant Application at the Computer Science Department. Also a course project for Object-Oriented Software Engineering. Full repo under private mode.

steventan0110/WebSecutity

HW for web security class

steventan0110/ClassroomHelper

An android studio developed image processing application: 1. Convert image into text form and math equations into LaTeX form. 2. App is implemented with Mathpix and Google Computer Vision APIs

steventan0110/DBFinalProject

This project is built on tomcat which supports Java Servlet and Java Database Connector. The project utilizes geohash to locate the user and query the safest/most dangerous street around the user.

steventan0110/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

steventan0110/fairseq2_speech_llm

FAIR Sequence Modeling Toolkit 2

steventan0110/first_flask

steventan0110/Flask_Web

My personal website built on linode server with Flask

steventan0110/mamba-s2s

steventan0110/multiDDS

Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"

steventan0110/ParaCrawl

On-develop Bitext Mining Tool for low resource languages

steventan0110/RaspGPIO

Embedded System development based on GPIO on Raspberrypi 3B+

steventan0110/screeps

steventan0110/steventan0110.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

steventan0110/steventan0110.github.io_old

steventan0110/steventan0110_temp.github.io

steventan0110/TranSpeech

PyTorch Implementation of TranSpeech (ICLR'23): Textless NAR Speech-to-Speech Translation with Bilateral Perturbation

steventan0110/tutorial-template

Template for the Read the Docs tutorial