Yew-Soon Ong

Agency for Science, Technology and Research · Singapore

Unclaimed · AI-structured profileOpenAlex

A*STAR researcher in evolutionary computation and transfer optimization, focused on few-shot multitask optimization.

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—

Output data is not yet available for this axis, which would measure total publication volume and per-year production. The OpenAlex snapshot supplies no usable lifetime output counts, so output is left unscored rather than estimated.

Impact—

Impact data is insufficient: this axis would measure citations and scholarly uptake of the work, but the snapshot's citation records (h-index and i10-index logged as 0) are not usable, so impact is left unscored.

Focus0/100

Focus scores 0 in this snapshot. The recorded field split is an even 50/50 between machine learning (optimization and evolutionary computation) and evolutionary computation and transfer optimization — two adjacent subfields — while OpenAlex topic assignments span adversarial robustness (7), multimodal machine learning (6), topic modeling (3), reinforcement learning in robotics (3), and stochastic gradient optimization (3), indicating low measured concentration.

Collaboration39/100

Collaboration scores 39. Within the recent OpenAlex window this profile records 6 distinct coauthors; the most frequent collaborators include Tingyang Wei, Haofeng Wu, Jiao Liu, Zhao Wei, Puay Siew Tan, and Ananda Phan Iman. On both Evolve-reviewed 2026 papers the researcher appears in the last author position (non-corresponding), a pattern consistent with senior or supervisory involvement in small teams.

Activity90/100

Activity scores 90, the strongest axis in this profile. The OpenAlex snapshot records 21 works in the recent three-year window, with all 21 of the year-counted outputs falling in 2026. This dense recent cadence aligns with the two 2026 arXiv preprints reviewed by Evolve, both in optimization-oriented fields, indicating a highly active current publishing phase.

Reproducibility78/100

Reproducibility scores 78, computed from 2 Evolve-reviewed papers with a mean readiness of 78. The iterative sequential transfer MTO paper is rated high readiness, while the in-context guidance paper is rated medium — its review notes no ablation isolating the informed guidance — suggesting generally sound experimental reporting with room for tighter ablations.

Research summary

This profile describes Yew-Soon Ong, affiliated with the Agency for Science, Technology and Research (A*STAR) in Singapore, and resolved from public OpenAlex bibliographic records. The recorded field distribution splits evenly, 50% machine learning (optimization and evolutionary computation) and 50% evolutionary computation and transfer optimization. Activity is the standout signal: the snapshot logs 21 works in the recent three-year window, with all 21 year-counted outputs falling in 2026, earning an activity score of 90. The Evolve catalog holds two 2026 arXiv preprints, on both of which the researcher is last author: an in-context guidance framework in which a frozen TabPFN model captures inter-task synergies for few-shot multitask optimization, and an iterative sequential transfer method (IST: MTO) using GP-kernel task prioritization for few-shot multiobjective multitask optimization. Evolve rates the latter's reproducibility readiness high and the former medium, averaging 78 across the two reviewed papers. OpenAlex topic assignments extend beyond optimization into adversarial robustness (7), multimodal machine learning (6), topic modeling (3), reinforcement learning in robotics (3), and stochastic gradient optimization (3), which drives the measured focus score to 0. Collaboration scores 39 on 6 distinct recent coauthors. Citation-based output and impact metrics were unavailable in this snapshot and are left unscored.

Collaboration pattern

Collaboration scores 39 on a 0-100 scale. The recent OpenAlex window records 6 distinct coauthors, with Tingyang Wei, Haofeng Wu, Jiao Liu, Zhao Wei, Puay Siew Tan, and Ananda Phan Iman among the most frequent. On both Evolve-reviewed 2026 arXiv papers the researcher sits in the last author position without corresponding-author flagging, consistent with a senior supervisory role within small, optimization-focused teams.

Research keywords

multitask optimizationevolutionary computationtransfer optimizationBayesian optimizationfew-shot optimizationmultiobjective optimizationin-context learningfoundation modelsGaussian processessurrogate-assisted optimizationsequential transfer

Highlights

Frozen TabPFN provides in-context guidance for few-shot multitask optimization
In a 2026 arXiv preprint (last author), a frozen TabPFN model supplies in-context priors that guide inter-task coupling in few-shot multitask optimization; Evolve notes strong results but no ablation isolating the informed guidance, and rates reproducibility readiness medium.
Iterative sequential transfer tackles few-shot multiobjective multitask optimization
The 2026 arXiv paper proposes IST: MTO, framing multitask optimization as iterative sequential transfer with GP-kernel task prioritization; Evolve finds the few-shot gains promising though win counts slightly outrun the tables, and rates reproducibility readiness high.
Consistent last-author role across a concentrated 2026 push
Both Evolve-reviewed entries are 2026 arXiv preprints in the profile's two recorded fields (50% each), with the researcher in the last author position and not corresponding; the same year accounts for all 21 counted recent outputs, matching the activity score of 90.

Timeline

2026Publishes 'In-Context Guidance: Learning Inter-Task Synergies via Numerical Foundational Models for Few-Shot Multitask Optimization' on arXiv, in the last author position.
2026Publishes 'Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer' on arXiv; Evolve rates its reproducibility readiness high.
2026All 21 of the profile's year-counted recent outputs fall in this year, supporting an activity score of 90.
2026Evolve completes reviews of both preprints, yielding a mean reproducibility readiness of 78 across 2 papers.

Papers in the Evolve catalog

Frequent co-authors

Tingyang Wei×2 Haofeng Wu×2 Jiao Liu×2 Zhao Wei×2 Puay Siew Tan×1 Ananda Phan Iman×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.

All bibliometrics come from OpenAlex only; no ORCID was provided, so this profile is name-resolved from public bibliographic records.
Citation-based metrics (h-index and i10-index recorded as 0) are unreliable in this snapshot; the output and impact axes are marked missing, not scored.
The Evolve catalog covers only two 2026 arXiv preprints; profile depth beyond these reviews is limited.
OpenAlex topic assignments (e.g., adversarial robustness, multimodal machine learning) diverge from the optimization-focused reviewed papers and may reflect indexing noise.