Early-career NTU Singapore researcher advancing few-shot multitask and evolutionary transfer optimization
2
papers here
2
reviewed by Evolve
2
first-author
0
corresponding
—
works · OpenAlex
5
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: no verified total publication count or venue-level breakdown is available in the snapshot. This axis would measure total and annual research output, publication venues, and authorship roles across the full bibliographic record.
Impact—
Not yet scored: citation counts, per-year citation series, and venue-level influence are unavailable for this profile. This axis would measure citation impact, uptake by other researchers, and the influence of the work across fields.
Focus0/100
Focus scores 0: the record splits evenly (0.5/0.5) between machine learning (optimization and evolutionary computation) and evolutionary computation and transfer optimization, and OpenAlex topics span five clusters — advanced multi-objective optimization (7), metaheuristics (5), evolutionary algorithms (4), plus earlier applied work in video surveillance and tracking (2) and sparse/compressive sensing (2). The recent catalog papers do converge tightly on few-shot multitask optimization.
Collaboration39/100
Collaboration scores 39, reflecting a compact network: 6 distinct coauthors in the recent three-year window against 8 works over the same period. Recurring partners include Haofeng Wu, Jiao Liu, Zhao Wei, Yew-Soon Ong, Puay Siew Tan, and Ananda Phan Iman. Both Evolve-reviewed 2026 papers are first-author, non-corresponding arXiv preprints, consistent with contributor roles within a small, stable team at NTU Singapore.
Activity64/100
Activity scores 64. The snapshot shows works in 2018–2021 at 1–2 per year, a gap with no indexed works in 2022–2023, then resumption with 2 works in 2024, 1 in 2025, and 5 in 2026 — the strongest year on record — with 8 works across the recent three-year window. Output is accelerating and currently concentrated in arXiv preprints.
Reproducibility78/100
Reproducibility scores 78 (reproMean), computed from the 2 Evolve-reviewed papers. The IST iterative sequential transfer paper is rated high readiness, while the TabPFN-based in-context guidance paper is rated medium — Evolve notes strong results but no ablation isolating the informed-guidance contribution. The score rests on a small base of two preprints and should be read as provisional.
Research summary
Tingyang Wei is an early-career researcher at Nanyang Technological University (Singapore) working at the interface of evolutionary computation, machine learning, and optimization. The OpenAlex snapshot linked to ORCID 0000-0001-6848-031X lists an h-index of 5 and an i10-index of 5, with works spanning 2018–2026 (no indexed works in 2022–2023) and a peak of 5 works in 2026. Recent output is concentrated: 8 works in the last three years, split evenly (0.5/0.5) between machine learning (optimization and evolutionary computation) and evolutionary computation and transfer optimization. Topic counts place advanced multi-objective optimization (7) and metaheuristic algorithms (5) at the core, with evolutionary algorithms (4) alongside earlier applied clusters in video surveillance and tracking (2) and sparse/compressive sensing (2). Both papers Evolve has reviewed are 2026 arXiv preprints with Wei as first author: an in-context guidance framework using a frozen TabPFN foundation model for few-shot multitask optimization, and IST, an iterative sequential transfer method with GP-kernel task prioritization for few-shot multiobjective multitask optimization. Evolve rates reproducibility readiness high for IST and medium for the TabPFN work, yielding a reproducibility mean of 78 across the two assessed papers. Collaboration is compact — 6 distinct coauthors in the recent three-year window, with recurring partners including Yew-Soon Ong, Jiao Liu, and Haofeng Wu. Output and impact dimensions are not yet scored due to insufficient data.
Collaboration pattern
Collaboration is compact: 6 distinct coauthors in the recent three-year window across 8 works, yielding a collaboration score of 39. Recurring partners are Haofeng Wu, Jiao Liu, Zhao Wei, Yew-Soon Ong, Puay Siew Tan, and Ananda Phan Iman, anchored at Nanyang Technological University. Both Evolve-reviewed 2026 papers position Wei as first author without corresponding authorship, consistent with hands-on experimental roles within a small, stable optimization group.
Research keywords
Highlights
In-context guidance from a frozen TabPFN for few-shot multitask optimization
IST: iterative sequential transfer for few-shot multiobjective multitask optimization
Accelerating output on an early-stage, compact profile
The OpenAlex snapshot records 5 indexed works in 2026 — the most active year — including both Evolve-reviewed first-author preprints, with 8 works across the recent three-year window after the 2022–2023 gap. Reproducibility mean is 78 across the 2 assessed papers; output and impact remain unscored.
Timeline
- 2018Earliest indexed publication year in the OpenAlex snapshot, with 1 work; the opening years 2018–2019 each show a single indexed work.
- 2020Indexed output rises to 2 works in 2020 and holds at 2 works in 2021, according to the snapshot's counts by year.
- 2024After two years (2022–2023) with no indexed works in the snapshot, activity resumes with 2 indexed works in 2024.
- 2026Most active year: 5 indexed works, including both Evolve-reviewed first-author arXiv preprints on few-shot multitask optimization — the TabPFN in-context guidance framework and the IST iterative sequential transfer method.
Papers in the Evolve catalog
Frequent co-authors
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 metrics (h-index 5, i10-index 5, counts by year, topics) come from an OpenAlex identity snapshot and may lag or incompletely cover the record.
- Evolve has reviewed 2 papers to date, both 2026 arXiv preprints; the reproducibility score (78) rests on these two papers only.
- Output and impact dimensions are unscored because citation and verified output data are insufficient in the snapshot.
- Profile is name-resolved from public bibliographic data (OpenAlex identity plus ORCID 0000-0001-6848-031X); biography beyond these sources is not covered.