Profile image
Pin-Ying Wu
Machine Learning Engineer
TSMC, San Jose, CA

About Me

I am a machine learning engineer at TSMC, focusing on LLM-based solutions for data-driven business decisions that enhance decision-making efficiency. Specifically, I developed an interactive chatbot for internal pricing decisions, leveraging cutting-edge information retrieval and summarization techniques, which achieves 92.1% average recall on the internal data. Prior to that, I received my M.S. degree from the Department of ECE at University of California San Diego (UCSD). I am an AI enthusiast and my interests and domain knowledge span across Generative AI, Computer Vision, and Deep Learning. Aside from industrial experience, I had rich research experience at research labs. I was a research intern investigating the reliability of LLMs in the context of 3D Visual Question Answering (3D-VQA) in Statistical Visual Computing Lab at UCSD, advised by Prof. Nuno Vasconcelos. Before joining UCSD, I received my B.S. degree from the EE department at National Taiwan University (NTU), where I was fortunate to work with Prof. Yu-Chiang Frank Wang at Vision and Learning Lab on Audio-Visual Learning for Sounding Source Localization.

Experience


Machine Learning Engineer

TSMC, San Jose, CA, USA
Apr. 2024 - Present

  • Developing LLM-based solutions for data-driven business decisions that enhance decision-making efficiency.

  • Leading an interactive chatbot project for internal pricing decisions, leveraging cutting-edge information retrieval and summarization techniques, which achieves 92.1% average recall on the internal data.

  • Coordinating across teams to refine project requirements, address challenges, and ensure continuous alignment between technical deliverables and strategic business goals.


    • Graduate Research Intern

    Statistical Visual Computing Lab, University of Californnia San Diego, USA
    Apr. 2023 - Mar. 2024

    Advised by Prof. Nuno Vasconcelos

  • Addressed the reliability of LLMs in the context of 3D visual question answering and curated 100,000 questions regarding the potential risks in the given scenes that require high-level reasoning.


    • Computer Vision Undergraduate Researcher

    Vision and Learning Lab, National Taiwan University, Taiwan
    Sep. 2020 - Jun. 2022

    Advised by Prof. Yu-Chiang Frank Wang

  • Developed an Audio-Visual Transformers model to learn cross-modal contextual features for locating sounding sources in an image, and conducted thorough experimental studies with the MUSIC dataset.

  • Addressed the challenge of the fully unsupervised scenario by leveraging self-supervised training of CNNs, along with short-time Fourier transform (STFT) for extracting serial features for audio signals.

    • Selected Projects

    Unsupervised PCB Anomaly Segmentation with Foundational Models Python
    Chih-Hui Ho, SungBal Seo, NaYeon Kim, Pin-Ying Wu, YouSuk Bae, Nuno Vasconcelos
    Electronic Imaging (EI), Intelligent Robotics and Industrial Applications using Computer Vision, Oral, 2024
    Conference paper
    Unveiling the Efficacy of Foundation Models for Depth Estimation Python
    Pin-Ying Wu, Zih-Hao Fu, 2023

    • Formulating depth estimation as a distance classification task and conducting thorough experiments and ablation studies using large foundation models, including CLIP and SAM, under self-supervised and supervised settings with the NYU-Depth v2 Dataset.

    • Leveraging CLIP's semantic language tokens for initial depth prediction and incorporating adapter networks to study whether these refinement modules can further improve the CLIP predictions, including CLIP-Adapter, Coarse/Refined Adapter, and the proposed Multi-Scale Adapter.

      • [code][pdf]
    Shallow-PPGNet: A Simple yet Effective Network for Hypertension Detection Python
    Pin-Ying Wu, Ye Sel Lee, Yin Lei, 2023

    • Proposed Shallow-PPGNet, a CNN for detecting hypertension with PPG signals, and achieved over 10% improvement on PPG-BP and MIMIC-II datasets than state-of-the-art approaches.

    • Enhanced the diabetes prediction by transferring the knowledge learned from the hypertension prediction and conducted comprehensive ablations on different prediction models and with various metrics.

      • [pdf]
    An Effective Approach for Arrhythmia Classification using ECG Signals Python
    Pin-Ying Wu, 2023

    • Developed Simple-ECGNet, a light CNN for detecting arrhythmia with ECG signals, and achieved over 10% improvement in sensitivity and precision on MIT-BIH dataset than state-of-the-art approaches.

    • Conducted comprehensive ablations on different prediction models and loss functions with various metrics.

    Face Anti-Spoofing Python
    Pin-Ying Wu, Pei-Ying Lin, Zi-Ting Chou, Chun-Tin Wu, 2020

    • Utilized feature pretraining and sequential modeling techniques to address the face anti-spoofing challenge, resulting in an impressive recognition accuracy of 99.3% on the Oulu-NPU and SiW datasets.

    • Dedicated to brainstorming ideas for model development, encouraging group discussions, setting the project milestones and summarizing the outcomes as a project leader with 3 group members.

      • [code][pdf]
    Visual Domain Adaptation with Adversarial Training Python
    Pin-Ying Wu, 2020

    • Investigated the literature of visual domain adaptation and implemented two popular algorithms, DAAN and ADDA, that adopt adversarial training to align features in different domains.

    • Conducted several domain adaptation experiments with USPS, MNIST-M, and SVHN datasets.

      • [code]
    Face Generation with VAE and GAN Python
    Pin-Ying Wu, 2020

    • Explored and compared the classic generative models, including VAE and GAN.

    • Analyzed the effect of different loss functions and studied the influence of hyper-parameter choices.

      • [code]
    Few-shot Image Classification Python
    Pin-Ying Wu, 2020

    • Implemented Prototypical Network and hallucinated data to classify image with limited training data.

    • Studied different distance metrics and their performance under different settings (i.e. different ways/shots).

      • [code]
    Single-Cycle CPU Implementation Verilog
    Pin-Ying Wu, Si-Ying Chen, 2021

    • A course project collaborating with a teammate in Computer Architecture class using Verilog.

    • Implemented the architecture and functions of single-cycle CPU, supporting RISC-V instructions.

    Controlling DC Motor Position with PID control, lead-lag compensator MATLAB
    Pin-Ying Wu, Hsin-Tzu Sung, 2021

    • A Matlab project collaborating with a teammate in Control System class.

    • Leveraged PID control, lead compensator and lead-lag compensator to implement the desired system and analyzed the property of the system with root locus and Bode plot.

    Source Coding: Turning Signals into Bits MATLAB
    Pin-Ying Wu, 2021

    • Implemented the Huffman tree and the corresponding encoder and decoder, and applied it to convert the resampled and quantized audio waveforms.

    • Analyzed the transmitted and received signals with different noise levels in the communication channel.

    Education

    M.S. in Electrical and Computer Engineering, University of Californnia San Diego, USA
    Sep. 2022 - Mar. 2024
    B.S. in Electrical Engineering, National Taiwan University, Taiwan
    Sep. 2018 - Jun. 2022

    Copyright © Pin-Ying Wu 巫品瑩 2025

    Template from Jason Lai