Liuyin Yang
LY

PhD Researcher · Computational Neuroscience · KU Leuven

Liuyin Yang

I build brain foundation models spanning ECoG, EEG, sEEG and MEG for brain–computer interfaces — teaching large models pretrained on scalp EEG to transfer into intracranial recordings, and turning neural signals into real-time control, auditory, and motor decoding.

  • Brain Foundation Models
  • Brain–Computer Interfaces
  • Scalp → Intracranial Transfer
  • Auditory & Motor Decoding
  • Real-time BCI

Background

Curriculum Vitae

Education

  1. 2021 — now
    PhD, Biomedical Sciences (Medicine)
    KU Leuven · Leuven, Belgium
    Topic: EEG-based brain–computer interfaces. Advisor: Prof. Marc M. Van Hulle.
  2. 2020 — 21
    Advanced Master, Artificial Intelligence
    KU Leuven · Big Data Analytics
    Cum laude
  3. 2019 — 20
    MSc, Electronics & ICT Engineering
    KU Leuven · Engineering Technology
    Cum laude
  4. 2017 — 19
    BSc, Electronics Engineering
    KU Leuven
    Cum laude
  5. 2015 — 17
    BEng, Electrical Engineering & Automation
    Chongqing University · China

Research Experience

  1. 2021 — now
    PhD Researcher
    Computational Neuroscience Group, KU Leuven
    EEG foundation models for BCI; cross-modality scalp-to-intracranial transfer (CORTEG, NeurIPS 2026); auditory decoding (ICASSP 2023 — 2nd place); winner of the EEG Foundation Challenge at NeurIPS 2025; online motor-imagery BCI systems.
  2. 2019 — 20
    Master's Thesis Researcher
    KU Leuven · Engineering Technology
    Real-time adaptive-filter speech enhancement on a DSP board, deployed in an IoT communication system.

Skills

Deep Learning
PyTorchDistributed Training (DDP)TransformersSelf-supervised Learning
EEG & Lab
EEG ExperimentationSignal ProcessingUnity (VR — Meta Quest Pro)Android Studio
Programming
PythonMATLABOctaveJavaC / C++ / C#Assembler
Embedded & Hardware
Vivado (FPGA)DSP Board (C5515 eZdsp)ArduinoEagle (PCB)Microcontrollers
Languages
English — proficient中文 — proficientFrançais — intermediate (B1)
Download CV (PDF)

15 papers · 138 citations

Publications

138 Citations
7 h-index
6 i10-index
15 Publications

As of November 2026 · Source: Google Scholar

  1. 2026

    NeurIPS 2026 · Poster

    CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings

    L Yang*, Q Sun*, B Van Dyck, EC Merino, MM Van Hulle · *equal contribution

    Can a large model pretrained on scalp EEG be adapted to intracranial (ECoG) recordings? CORTEG bridges the two with an electrode-aware spatial adapter and a dual-stream tokenizer for low-frequency and high-gamma activity, then calibrates to a held-out patient in minutes — matching or beating task-specific baselines on finger-trajectory and audio-envelope regression.

    Conference on Neural Information Processing Systems (NeurIPS) · Poster · arXiv:2605.10337

    1 citation arXiv Code
    Conference
  2. 2026

    ICLR 2026 · Poster

    Are EEG Foundation Models Worth It? Comparative Evaluation with Traditional Decoders in Diverse BCI Tasks

    L Yang, Q Sun, A Li, MM Van Hulle

    Do EEG foundation models actually beat traditional decoders? A statistically rigorous benchmark of state-of-the-art EEG foundation models across diverse datasets, decoding tasks and six evaluation protocols, alongside ST-EEGFormer, a simple ViT baseline pretrained with masked autoencoding on over 8M EEG segments. Fine-tuned foundation models do well in data-rich, population-level settings, but often fail to significantly outperform compact networks or even classical non-neural decoders when data are scarce.

    International Conference on Learning Representations (ICLR) · Poster

    33 citations Scholar
    Conference
  3. 2026

    arXiv 2026 · Preprint

    Characterization of Speech Imagery in Scalp EEG and Comparison with Motor Imagery

    B Van Dyck, L Yang, Q Sun, A Li, MM Van Hulle

    Does imagined speech look like motor imagery in scalp EEG? In 34 participants, finger motor imagery showed the expected contralateral mu/alpha and beta desynchronization, whereas speech imagery showed a weaker, more distributed increase in alpha power relative to no-task trials, and was harder to decode (balanced accuracy 0.56 vs. 0.72 for motor imagery).

    arXiv preprint · arXiv:2606.12223

    Preprint
  4. 2026

    ICLR 2026 · TSALM Workshop · Poster

    Large EEG Foundation Model Learns Informative Low-Frequency Representations from Intracranial Brain Signals

    Q Sun, L Yang, EC Merino, MM Van Hulle

    Can a scalp-EEG foundation model transfer to invasive recordings? An ECoG-to-EEG channel-projection module and a lightweight adaptation strategy let the pretrained backbone decode ECoG, and the adapted model outperforms conventional ECoG decoders at extracting finger-movement information from low-frequency (128 Hz) signals.

    1st ICLR Workshop on Time Series in the Age of Large Models (TSALM) · Poster

    1 citation Scholar
    Workshop
  5. 2026

    ICLR 2026 · TSALM Workshop · Poster

    Do We Need Domain-Specific Time-Series Models? Insights from EEG Classification Benchmarks

    L Yang, Q Sun, MM Van Hulle

    Does the broad pre-training of generic time-series foundation models pay off in a specialized domain? Benchmarking Mantis (~8M parameters) and MOMENT (~300M) on four public EEG datasets against EEG foundation models and classic baselines: fine-tuning often matches EEG-specific models while linear probing transfers poorly, and a randomly initialized Mantis performs comparably to the pretrained one.

    1st ICLR Workshop on Time Series in the Age of Large Models (TSALM) · Poster

    Workshop
  6. 2026

    ICLR 2026 · TSALM Workshop

    Learning Robust EEG Representations with a Large Spatiotemporal Transformer as a Foundation Model

    L Yang, MM Van Hulle

    Introduces ST-EEGFormer, a simple spatiotemporal EEG transformer that projects patches of raw EEG into an embedding space enriched with spatial and temporal embeddings, so that one model can handle recordings with different channel setups, and evaluates how well it adapts across diverse BCI control paradigms.

    1st ICLR Workshop on Time Series in the Age of Large Models (TSALM)

    1 citation OpenReview
    Workshop
  7. 2026

    KU Leuven RDR 2026 · Open dataset

    A Multi-Paradigm EEG Dataset for Multi-Task BCI Applications

    L Yang, B Van Dyck, Q Sun, A Li, MM Van Hulle

    EEG from 34 healthy participants, each recorded in a single session covering SSVEP, motor imagery and imagined speech, plus structured artifact recordings (eye blinks, jaw clenching, breath holding, hand clenching), resting state and questionnaires. Randomly interleaved test blocks enable realistic asynchronous decoding, and standardized preprocessing pipelines support benchmarking and cross-paradigm transfer learning.

    KU Leuven Research Data Repository · doi:10.48804/3EUSTS

    Dataset
  8. 2025

    arXiv 2025 · Preprint

    CoMET: A Contrastive-Masked Brain Foundation Model for Universal EEG Representation

    A Li, Z Wang, L Yang, Z Wang, T Xu, H Hu, MM Van Hulle

    Masked reconstruction alone over-focuses on local similarity between highly correlated neighboring channels. CoMET pairs an EEG masked autoencoder with a contrastive framework using mirror-scale augmentation to learn global discriminative patterns; pretrained on over one million samples from more than 3,000 subjects, it reaches state-of-the-art results on ten downstream datasets.

    arXiv preprint · arXiv:2509.00314

    11 citations arXiv
    Preprint
  9. 2025

    ICORR 2025

    On the Impact of Proprioception in EEG Representations and Decoding during Human-Hand Exoskeleton Interaction

    Q Sun, EC Merino, L Yang, A Faes, MM Van Hulle

    How does the proprioceptive feedback of a hand exoskeleton shape EEG? In 25 participants performing imagined, passive and combined imagined-plus-passive finger flexion with a cable-driven exoskeleton, exoskeleton-driven movement evoked significantly stronger sensorimotor alpha/beta desynchronization than imagery alone and was readily decoded against rest, but separating motor intention from the exoskeleton’s own feedback remained hard.

    International Conference on Rehabilitation Robotics (ICORR) · pp. 186–192

    1 citation DOI
    Conference
  10. 2024

    JNER 2024

    Unraveling EEG Correlates of Unimanual Finger Movements: Insights from Non-Repetitive Flexion and Extension Tasks

    Q Sun, EC Merino, L Yang, MM Van Hulle

    Do individual finger movements have distinct, decodable EEG correlates? Sixteen participants performed five individual and four coordinated finger flexions and extensions during high-density EEG and finger tracking. Movement versus rest was detected with over 80% accuracy, but telling fingers apart was hard because their neural correlates overlap, with the thumb standing out as the most distinctive.

    Journal of NeuroEngineering and Rehabilitation · vol. 21, art. 228

    23 citations DOI
    Journal
  11. 2024

    J. Neural Eng. 2024

    Binocularly Incongruent, Multifrequency-Coded SSVEP in VR: Feasibility and Characteristics

    L Yang, Q Sun, MM Van Hulle

    A systematic study of binocularly incongruent SSVEP in virtual reality, where each eye sees a stimulus flickering at a different frequency, covering dual-, triple- and quadruple-frequency codes (several of them new) and comparing them with congruent stimulation. The results show binocular summation and suppression effects, and underline how paradigm choice and decoder design shape performance and user comfort.

    Journal of Neural Engineering · vol. 21(5), 056013

    9 citations DOI
    Journal
  12. 2024

    IEEE OJSP 2024

    Sea-Wave: Speech Envelope Reconstruction from Auditory EEG with an Adapted WaveNet

    L Yang, B Van Dyck, MM Van Hulle

    Extends our ICASSP 2023 challenge entry into Sea-Wave, a WaveNet-based model that reconstructs the speech envelope from EEG and outperforms the previous state of the art. Ablations and a hyperparameter search give a subject-independent Pearson correlation of 0.226 on seen and 0.116 on unseen subjects, and subject-specific fine-tuning adds a further 30% average relative gain on seen subjects.

    IEEE Open Journal of Signal Processing · vol. 5, pp. 686–699

    6 citations DOI
    Journal
  13. 2023

    ICASSP 2023 · 2nd place

    Decoding Auditory EEG Responses Using an Adapted WaveNet

    B Van Dyck, L Yang, MM Van Hulle

    A WaveNet-based model that reconstructs the speech envelope from auditory EEG. It placed second in the regression subtask of the ICASSP 2023 Auditory EEG Challenge and achieved the highest score on held-out subjects, with only 341k trainable parameters.

    IEEE ICASSP 2023 — 2nd place, Auditory EEG Grand Challenge · pp. 1–2

    19 citations DOI
    Conference
  14. 2023

    Sensors 2023

    Real-Time Navigation in Google Street View Using a Motor Imagery-Based BCI

    L Yang, MM Van Hulle

    A motor-imagery BCI for navigating Google Street View with only eight dry EEG electrodes. A middle-level control scheme keeps the number of commands small and eye blinks act as an extra control signal to avoid decoder mistakes; offline and online experiments with 20 participants showed acceptable performance despite the minimal setup.

    Sensors · vol. 23(3), 1704

    18 citations DOI
    Journal
  15. 2021

    Biosensors 2021

    Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach

    L Yang, A Libert, MM Van Hulle

    Can brainwaves authenticate users outside the lab? Using a commercial dry-electrode headset and chronic recordings from 15 people performing and imagining motor tasks, an LSTM with bootstrap aggregating (bagging) reached 93.0% authentication accuracy with a 1.9% false-acceptance rate on the combined tasks.

    Biosensors · vol. 11(10), 404

    15 citations DOI
    Journal

Invited · teaching · service

Talks, Teaching & Service

Invited & Selected Talks

  1. Dec 2025
    Spotlight Talk — EEG Foundation Challenge 2025
    NeurIPS 2025 Competition Track · San Diego
  2. 2025
    EEG Foundation Models
    IEEE NER 2025 Workshop
  3. 2025
    Scaling EEG Foundation Model Pretraining
    KU Leuven / UHasselt Tier-2 HPC User Day

Teaching & Supervision

  1. recurring
    Teaching Assistant
    Brain-Computer Interfaces (MSc course) · KU Leuven
  2. 2024 — 25
    Master's Thesis Daily Supervisor
    KU Leuven
    VR-based imagined-speech speller
    Brain connectivity with a brain foundation model
  3. 2023 — 24
    Master's Thesis Daily Supervisor
    KU Leuven
    VR-based binocular SSVEP system

Peer Review

  1. journals
    Journal Reviewer
    Journal of Neural Engineering (JNE) · IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  2. 2026
    Conference Reviewer
    ICLR 2027 · ICML 2026 Workshop FMSD

Funding · 72,119 GPU hours on VSC

Grants & Fellowships

  1. 2026
    VSC Compute Project 2026_064
    Flemish Supercomputer Center (VSC) · HPC GPU allocation for intracranial (ECoG) foundation-model training
    39,961 GPU hours
  2. 2025
    VSC Compute Project 2025_500
    Flemish Supercomputer Center (VSC) · Special competition grant for the EEG Foundation Challenge (NeurIPS 2025)
    7,497 GPU hours
  3. 2025
    VSC Compute Project 2025_038
    Flemish Supercomputer Center (VSC) · HPC GPU allocation · vscentrum.be
    24,661 GPU hours
  4. 2021 — 25
    FWO PhD Fellowship Strategic Basic Research (SB)
    Research Foundation – Flanders (FWO) · fwo.be

Recognition

Awards & Honors

  1. 2025
    1st Place — EEG Foundation Challenge 2025
    From Cross-Task to Cross-Subject EEG Decoding · NeurIPS 2025 Competition Track · eeg2025.github.io
  2. 2023
    2nd Place — ICASSP 2023 Grand Challenge
    Auditory EEG Decoding Challenge · WaveNet regression model
  3. 2019 — 21
    Cum laude — three consecutive KU Leuven degrees
    Advanced Master AI (2021) · MSc Electronics & ICT (2020) · BSc Electronics (2019)

Let's talk

Contact

Email

liuyin.yang@kuleuven.be

Computational Neuroscience Group
KU Leuven · Leuven, Belgium

Elsewhere