Skip to content
View juliairsalina's full-sized avatar
💬
working on something..
💬
working on something..

Block or report juliairsalina

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
juliairsalina/README.md

hi, i'm julia !

i'm a data science undergraduate student at korea university.

i like working on projects around machine learning, deep learning, data-driven systems, ui/ux, and agentic ai.

🌷 about me

i love working on ml/ai-related research and development, and most of my projects involve building, improving, or experimenting with machine learning models.

i also enjoy learning independently and exploring new tools based on my interests. since i like design too, i started learning frontend development to build projects that feel more interactive and visually polished.

recently, i've been exploring azure services, cloud technologies, llm-based applications, and agentic ai workflows.

outside of tech, i love playing roblox, reading japanese-translated books, and watching movies.

💻 featured projects

  • yapping study buddy
    an agentic ai learning platform using azure openai, microsoft foundry, azure speech services, fastapi, and a 3-agent workflow for flashcard generation, spoken answer evaluation, and adaptive feedback.

  • hierarchical product classification
    a machine learning project using bert-based text embeddings and graph attention networks for large-scale hierarchical product classification.

  • crowd density estimation with csrnet-cbam
    a deep learning project for crowd density estimation using convolutional neural networks and attention-based improvements.

  • stress detection with dual-branch vae-lstm
    a physiological signal learning project using vae-lstm and attention mechanisms for stress detection.

  • interactive yearbook platform
    a creative web-based platform combining frontend development, interaction design, and user-centered ui/ux.

🌙 little note

if you're working on data or ai projects and would like to connect, feel free to reach out on linkedin.
thanks for visiting my profile ♡

Pinned Loading

  1. crowd-density-estimation-csrnet-cbam crowd-density-estimation-csrnet-cbam Public

    Forked from whitepieridae/20251R0136COSE47400-CSRNet-CBAM-for-Crowd-Density-Estimation

    Fork of a team deep learning project on crowd density estimation. We explored multiple pipelines to address challenges such as occlusion and perspective distortion, and our best-performing model wa…

    Jupyter Notebook

  2. dual-branch-vae-lstm-stress-detection dual-branch-vae-lstm-stress-detection Public

    Forked from peunsu/wesad-stress-detection

    Fork of a team project on stress detection using a dual-branch VAE-LSTM with multi-head attention, developed on WESAD physiological signals for robust and efficient sequence modeling.

    Jupyter Notebook

  3. hierarchical-multi-label-text-classification hierarchical-multi-label-text-classification Public

    Hierarchical multi-label text classification pipeline with silver label generation, core-aware teacher training, soft self-training, and confidence-aware student learning. Combines hierarchy-aware …

    Jupyter Notebook

  4. interactive-yearbook-project interactive-yearbook-project Public

    Interactive Yearbook project goes beyond simply digitizing a book. It aims to recreate the feeling of being there again, surrounded by familiar faces, voices, and emotions through a carefully craft…

    TypeScript