cv
This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.
Contact Information
| Name | Hao-Chun (Chad) Yang |
| Professional Title | Senior AI/ML Engineer · Aptiv · Germany |
| chadyang.hc@gmail.com |
Professional Summary
Senior AI/ML Engineer at Aptiv leading end-to-end multimodal sensor-fusion perception for Level 4 autonomous driving — Transformer-based 3D perception with TensorRT and ONNX for edge deployment (>8% over production benchmarks), Airflow and MLflow pipelines with MLOps/data/KPI teams. Previously postdoctoral researcher at University of Tübingen / Donders Institute on self-supervised masked mesh vision transformers for long-tailed neuroimaging (+6.7% AUROC psychosis) and vision-language foundation-model fine-tuning for neurodegeneration.
Experience
-
2024 - present Germany
Senior Machine Learning Engineer
Aptiv
- Led a five-engineer team developing an end-to-end multimodal sensor-fusion perception system for Level 4 autonomous driving.
- Architected and optimized Transformer-based 3D perception modules with TensorRT and ONNX for edge deployment, improving performance by more than 8% over production benchmarks.
- Partnered with MLOps, data, and KPI teams to integrate Airflow and MLflow pipelines supporting robust data quality and efficient model training.
-
2023 - 2024 Germany/Netherlands
Postdoctoral Researcher, Machine Learning
University of Tübingen / Donders Institute
- Researched self-supervised and unsupervised representation learning for long-tailed neuroimaging disease detection.
- Improved psychosis detection by 6.7% AUROC using a self-supervised masked mesh vision transformer.
- Investigated vision-language foundation-model fine-tuning for large-scale neurodegenerative disease detection.
-
2020 - 2022 Taiwan
Senior Machine Learning Scientist, Domain Transfer and Privacy
National Health Research Institutes
- Introduced a privacy-aware federated learning approach (FedCM) to improve Alzheimer disease detection across multiple sources.
- Identified and differentiated key regions of interest related to normal brain degeneration and Alzheimer disease.
- Mentored students on robust multi-site ADHD detection using a conditional-adversarial domain adaptation network (CDAN).
-
2018 - 2022 Taiwan
Doctoral Researcher, Affective Electrophysiology Responses under Audio / Visual Stimuli
Behavioral Informatics & Interaction Computation Lab (BIIC)
- Enhanced physiological emotion recognition by 3.5% UAR through Transformer-based personalized modeling.
- Achieved an 8% UAR increase in personality recognition using a multi-head attention graph convolutional network.
- Studied subjective and intended emotion responses from ECG, EDA, and EEG signals with Shapley analysis.
-
2021 - 2021 Taiwan
Machine Learning Scientist, Cardiovascular Disease Detection
Inventec AI Center
- Led development of an end-to-end heart-disease anomaly detection system using time-series, multi-lead ECG.
- Proposed Mixed-Domain Self-Attention ResNet (MDARsn) to handle missing and anomalous ECG data for robust multilabel detection.
- Received the Best Challenge Poster Award in the PhysioNet/CinC Challenge 2021 and secured US patent US20230153575A1.
-
2020 - 2021 Taipei, Taiwan
Senior Machine Learning Scientist
C-Media Electronics, Inc.
- Led a team of five developing a real-time fully convolutional speech dereverberation engine, achieving an SRMR score of 4.774.
- Oversaw the full R&D pipeline, including data collection and synthesis, model and metric design, error analysis, and model compression.
- Pioneered speech cloning from previously unseen sources using generative adversarial networks.
-
2020 - 2020 Taipei, Taiwan
Lead ML Consultant
Institute for Information Industry (III)
- Led a team of five developing a deep video-retrieval system to accelerate fake-news screening.
- Proposed a video-retrieval system with 95.1% retrieval precision and orchestrated its deployment with Docker.
- Enabled deployment at Taiwan FactCheck Center and MyGoPen, two leading nonprofit fact-checking organizations.
-
2018 - 2020 Taiwan
Machine Learning Scientist, Neurocognitive Assessment using Brain MRI
National Health Research Institutes
- Spearheaded an MRI research pipeline spanning preprocessing with FreeSurfer and SPM, modeling, and explainable AI with GradCAM++.
- Increased three-class Alzheimer disease detection by 8.98% UAR using a 3D autoencoder with multi-view contrastive loss (BSEN).
- Achieved state-of-the-art 80.2% UAR in binary face-processing ability classification using event-contrastive Node2Vec embeddings.
Education
-
2016 - 2022 Hsinchu, Taiwan
PhD
National Tsing Hua University (NTHU)
Electrical Engineering
- Got President Scholarship which is given to promising students in EE Dept.
-
2012 - 2016 Hsinchu, Taiwan
B.S.
National Tsing Hua University (NTHU)
Electrical Engineering
Projects
-
2016 - 2018 Gamania Digital Entertainment Co., Ltd.
Machine Learning Engineer
- Developed Multi-modal behavior profiling system utilizing Speech, Face, and Gesture for AI-driven hiring recommendations.
- Designed and implemented a real-time, Multi-person Multi-modal data collection system to complement the profiling system.
Awards
-
2022 Program Committee Member
IEEE ICKII, IEEE ICEIB, IARIA CENTRIC
Served on the program committee for IEEE ICKII, IEEE ICEIB, and IARIA CENTRIC.
-
2021 Best Challenge Poster
PhysioNet/CinC Challenge, Computing in Cardiology Society
Awarded the Best Challenge Poster in the PhysioNet/CinC Challenge 2021.
-
2019 Travel Grants
IEEE Signal Processing Society
Received travel grants for ICASSP 2019.
-
2018 Paper Presentation Scholarship
ACLCLP, Taiwan
Scholarship for presenting research at ACLCLP.
-
2018 AI Scholarship
Adbertech Inc., Taiwan
-
2018 President Scholarship
National Tsing Hua University
Scholarship given to promising new PhD students in the EE Department.
-
2015 Summer Academic Exchange Program
Fudan University, China
Skills
Languages
Publications
-
2024 Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping
2024 IEEE International Symposium on Biomedical Imaging (ISBI)
Self-supervised masked mesh vision transformer for cortical anomaly and unsupervised heterogeneity mapping.
-
2021 A Media-Guided Attentive Graphical Network for Personality Recognition Using Physiology
IEEE Transactions on Affective Computing
Journal paper on personality recognition from physiological signals.
-
2021 A Mixed-Domain Self-Attention Network for Multilabel Cardiac Irregularity Classification Using Reduced-Lead Electrocardiogram
Computing in Cardiology (CinC) 2021, Brno, Czech Republic
-
2021 Federated Learning via Conditioned Mutual Learning for Alzheimer Disease Classification on T1w MRI
43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2021
-
2020 Cross Corpus Physiological-based Emotion Recognition Using a Learnable Visual Semantic Graph Convolutional Network
MM'20: The 28th ACM International Conference on Multimedia (ACMMM) 2020
-
2020 Conditional Domain Adversarial Transfer for Robust Cross-Site ADHD Classification Using Functional MRI
ICASSP 2020, Barcelona, Spain
-
2020 A Siamese Content-Attentive Graph Convolutional Network for Personality Recognition Using Physiology
ICASSP 2020, Barcelona, Spain
-
2020 Behavior Score-Embedded Brain Encoder Network for Improved Classification of Alzheimer Disease Using Resting State fMRI
EMBC 2020, Montreal, QC, Canada
-
2019 An Attribute-invariant Variational Learning for Emotion Recognition Using Physiology
ICASSP 2019, Brighton, United Kingdom
-
2019 An Event-contrastive Connectome Network for Automatic Assessment of Individual Face Processing and Memory Ability
ICASSP 2019, Brighton, United Kingdom
-
2019 Annotation Matters: A Comprehensive Study on Recognizing Intended, Self-reported, and Observed Emotion Labels using Physiology
8th International Conference on Affective Computing and Intelligent Interaction (ACII) 2019, Cambridge, United Kingdom
-
2018 Integrating Perceivers Neural-Perceptual Responses Using a Deep Voting Fusion Network for Automatic Vocal Emotion Decoding
ICASSP 2018, Calgary, AB, Canada
-
2018 A Triplet-Loss Embedded Deep Regressor Network for Estimating Blood Pressure Changes Using Prosodic Features
ICASSP 2018, Calgary, AB, Canada