Skip to content
View ChiaWei0804's full-sized avatar

Highlights

  • Pro

Block or report ChiaWei0804

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.

Content in all repositories owned by your account will be closed.
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
ChiaWei0804/README.md

Hi, I'm Andy 👋

M.S. student in Artificial Intelligence at Yuan Ze University (expected Jul 2027), working on deep learning for image and audio data with PyTorch. I like finding out how much performance survives when you take the compute away.

Eligible for Taiwan R&D Substitute Service (RDSS), available Jul 2027 · 研發替代役資格

Focus — deep learning · computer vision · object detection · speech separation Also build — Java / Spring Boot backends, containerised deployments


Projects

dinov3_detr — Resource-efficient object detection on a frozen ViT. A DETR-style head with 8.5M trainable parameters on a frozen DINOv3 ViT-B/16, trained end-to-end on COCO 2017. Reaches 43.1 mAP on val2017 — 65% of the official DINOv3 detector's accuracy using 1.4% of its parameters, on a single consumer GPU. PyTorch DETR Vision Transformer COCO MLflow

Denoiser — Two-speaker speech separation. Conv-TasNet with a dual-path encoder and an input-adaptive slice-fusion mechanism (under 3K extra parameters). Reaches 14.29 ± 2.79 dB SI-SNR over 1,440 held-out utterances. PyTorch Conv-TasNet Gumbel-Softmax SI-SNR

SyncSpace — Notion-style collaborative workspace. Nested page trees, a block editor with drag-and-drop reordering, and 18 REST endpoints. Runs from a single docker compose up. Java 17 Spring Boot JPA / Hibernate MySQL Docker


Currently

Training multi-label classification models on chest X-rays (RANZCR CLiP), and deepening the MLOps side of my work — model monitoring and CI/CD for training pipelines.

📫 aicpqp@gmail.com · LinkedIn

Pinned Loading

  1. Denoiser Denoiser Public

    Two-speaker speech separation, 14.29 dB SI-SNR. Conv-TasNet + SC-CHM with input-adaptive slice fusion (<3K extra params).

    Python

  2. SyncSpace SyncSpace Public

    Notion-style workspace: nested page trees, block editor with drag-and-drop. Spring Boot + JPA/MySQL + Docker Compose.

    JavaScript

  3. dinov3_detr dinov3_detr Public

    DETR-style detection head on a frozen DINOv3 ViT-B/16 backbone, trained end-to-end on COCO 2017. Mixed Query Selection, aspect-ratio bucketing, Hungarian matching with L1 + CIoU. 8.5M trainable par…

    Python