Chunyan Lan

McGovern Institute for Brain Research

Unclaimed · AI-structured profileOpenAlex

Dual-field researcher bridging EEG visual decoding, brain-computer interfaces, and brain-inspired continual learning

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

—

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.

Research profile

Output—

Not yet scored: this axis measures cumulative publication volume and productivity over time, but the snapshot contains no year-by-year output record — only the two Evolve-reviewed 2026 papers — so productivity cannot be quantified.

Impact—

Not yet scored: this axis would capture citation-based influence such as citation counts and h-index, but no citation data exists in the snapshot; two 2026 arXiv preprints are too recent and too few to estimate.

Focus0/100

Scores 0, and the raw field distribution explains it: reviewed output splits exactly 50/50 between computational neuroscience (EEG visual decoding / brain-computer interfaces) and machine learning (NeuroAI / continual learning). This is not scattered work but a deliberate dual-track profile — the same continual-learning theme, from catastrophic forgetting to cross-subject generalization, recurs across both EEG decoding benchmarks and brain-inspired modular architectures.

Collaboration58/100

Scores 58 from a raw count of 17 distinct coauthors across the cataloged work. The recurring partner list is dense — Kanglei Zhou, Dongyang Li, Liyuan Wang, Jun Zhu, Hongwei Yan, Qi Cheng, Weiyi Dong, Guanglong Sun, Jun Zhou, Qian Li, and Yi Zhong all appear — and co-authorship spans both research lines. Middle author positions on both papers suggest a contributing team member rather than a solo or corresponding-author lead.

Activity—

Not yet scored: this axis measures recent publication cadence and sustained engagement, but the snapshot lacks a multi-year publication history; both cataloged papers carry the same 2026 date, so no activity trend can be computed.

Reproducibility55/100

Scores 55, the mean reproducibility rating across the 2 Evolve-reviewed papers, both tagged medium readiness. Evolve's verdicts help explain the middle band: ProCA shows gains consistent across evaluation protocols, and the continual-learning framework reports strong empirical results but informal theory, so methods appear documented and checkable while exact replication — spanning EEG pipelines and modular expert training — would still demand careful protocol reconstruction.

Research summary

Chunyan Lan is a researcher at the McGovern Institute for Brain Research whose cataloged output spans two fields in near-equal measure: computational neuroscience (EEG visual decoding and brain-computer interfaces) and machine learning (NeuroAI and continual learning), each accounting for half of the reviewed work. Two 2026 arXiv papers anchor the profile. ProCA introduces progressive confusion-guided contrastive alignment with structured mixup for robust EEG visual decoding, with gains consistent across evaluation protocols on benchmarks such as THINGS-EEG2, though Evolve notes that relative improvements mask small absolute margins. The second paper proposes brain-inspired hierarchical modularity for general continual learning, drawing on the Drosophila mushroom body to build mixture-of-experts and ensemble structures that yield large continual-learning gains in vision and robotics, with strong empirics but informal theory and replay-competitive performance. A shared continual-learning thread — catastrophic forgetting, cross-subject generalization, parameter-efficient fine-tuning — connects the two lines. The collaboration footprint is team-based: 17 distinct coauthors, with recurring partners including Kanglei Zhou, Liyuan Wang, Jun Zhu, and Yi Zhong; both papers place this researcher in middle, non-corresponding author positions. Reproducibility scores 55 (medium readiness) across both papers, while output, impact, and activity lack the underlying bibliometric data to score, making this an early-stage, evidence-limited profile.

Collaboration pattern

Co-authorship is team-based: 17 distinct coauthors appear across the cataloged papers, and the recurring list includes Kanglei Zhou, Dongyang Li, Jun Zhu, Liyuan Wang, Hongwei Yan, Qi Cheng, Weiyi Dong, Guanglong Sun, Jun Zhou, Qian Li, and Yi Zhong, spanning both the EEG decoding and continual-learning lines. Both papers list this researcher in a middle, non-corresponding position, consistent with a hands-on contributor inside larger collaborative groups rather than a sole leader.

Research keywords

continual learningcatastrophic forgettingmixture-of-expertsensemble learningDrosophila mushroom bodyparameter-efficient fine-tuningEEG visual decodingcontrastive learningcross-subject generalizationbrain-computer interfacesTHINGS-EEG2

Highlights

ProCA: robust EEG visual decoding via progressive contrastive alignment
Evolve's verdict on this 2026 arXiv paper: progressive confusion-guided alignment plus structured mixup delivers robust EEG visual decoding, with gains consistent across evaluation protocols — though relative improvements can mask small absolute margins.
Drosophila-inspired hierarchical modularity for general continual learning
This 2026 paper builds mixture-of-experts plus ensemble modularity modeled on the Drosophila mushroom body; Evolve reports large continual-learning gains in vision and robotics, with strong empirics, informal theory, and performance competitive with replay baselines.
One continual-learning thread across two fields
Continual learning is keyworded in both cataloged papers: ProCA targets cross-subject generalization in EEG decoding while the modularity work attacks catastrophic forgetting — evidence of a single research program on learning under shifting distributions, spanning brain-computer interfaces and NeuroAI.

Timeline

2026ProCA appears on arXiv: progressive confusion-guided contrastive alignment plus structured mixup for robust EEG visual decoding, evaluated on THINGS-EEG2 (middle author, non-corresponding).
2026Brain-inspired hierarchical modularity paper appears on arXiv, applying Drosophila mushroom-body-inspired mixture-of-experts and ensemble structures to general continual learning in vision and robotics.
2026Profile status in Evolve: 2 reviewed papers split 50/50 across EEG/BCI and NeuroAI/continual learning, 17 distinct coauthors, reproducibility mean 55; output, impact, and activity remain unscored for lack of data.

Papers in the Evolve catalog

Frequent co-authors

Kanglei Zhou×2 Dongyang Li×1 Jun Zhu×1 Liyuan Wang×1 Hongwei Yan×1 Qi Cheng×1 Weiyi Dong×1 Guanglong Sun×1 Jun Zhou×1 Qian Li×1 Yi Zhong×1 Liyuan Wang×1

About this profile

This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.

Bibliometric scores are computed from a thin snapshot: no citation counts, h-index, or multi-year output history are provided, so output, impact, and activity remain unscored.
Only two Evolve-reviewed papers underlie this profile, both 2026 arXiv preprints with middle, non-corresponding author positions; the catalog may not be exhaustive.
Country and ORCID are missing, and 'Chunyan Lan' is a fairly common name — this profile is name-resolved from public bibliographic data plus the stated McGovern Institute for Brain Research affiliation.
The focus score of 0 reflects the exact 50/50 split across two fields rather than an absence of direction; the reproducibility mean of 55 covers only the two reviewed papers.