First-author builder of reproducible wet-lab robot kits that let coding agents drive biological laboratory automation.
1
papers here
1
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-20) 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: the output axis measures the volume and consistency of a researcher's publications over time. Only one cataloged paper (WetRobo, 2026) is available, so no reliable output score can be computed yet.
Impact—
Not yet scored: the impact axis tracks citations and uptake of a researcher's work across the literature. With a single 2026 arXiv paper and no citation data supplied, no impact estimate is possible yet.
Focus100/100
Focus is a perfect 100/100: every paper in the cataloged record — currently one work, WetRobo (2026) — falls in the single field of robotics / laboratory automation (robot learning), targeting one problem: making wet-lab hardware operable by coding agents. With such a small record this concentration is real but easy to maintain, so read it as an early, sharply defined agenda rather than long-proven specialization.
Collaboration41/100
Collaboration scores 41/100, based on 7 distinct coauthors in the record: Kei Endo, Takanori Uzawa, Yunzhe Zhang, Manan Anjaria, Lerrel Pinto, Sherry Yang, and Koji Tsuda. The first-author WetRobo paper required both wet-lab robotics and learning expertise, consistent with a network mixing robot-learning and laboratory-side partners. The moderate score reflects a small sample — one cataloged paper — rather than evidence against working with others.
Activity—
Not yet scored: the activity axis measures publication cadence and recent output. The available data covers a single 2026 paper, so yearly productivity and research momentum cannot be assessed.
Reproducibility55/100
Reproducibility averages 55/100 across the single assessed paper, which Evolve tags as medium readiness. WetRobo is explicitly designed as a reproducible kit — a coding agent carried it across two real wet labs — yet the review notes single-run, single-model evidence. The score therefore captures a genuinely reproducibility-oriented design with thin empirical validation; more assessed papers are needed to stabilize the number.
Research summary
Yuna Oikawa is an early-stage researcher working at the intersection of robot learning and laboratory automation; this profile is name-resolved from public bibliographic data. The Evolve catalog contains one reviewed first-author paper: WetRobo (arXiv, 2026), a reproducible robot kit built so that coding agents can operate it in biological laboratories. Per Evolve's verdict, a coding agent adapted the kit across two real wet labs and beat a fine-tuned vision-language-action (VLA) model on cross-lab cap transfer, though single-run, single-model evidence tempers that claim; reproducibility readiness is rated medium. The radar mirrors this concentrated record. Focus is a perfect 100/100, with all cataloged work in one field, robotics / laboratory automation (robot learning), while output, impact, and activity are unscored for lack of data. Collaboration sits at 41/100 across 7 distinct coauthors — Kei Endo, Takanori Uzawa, Yunzhe Zhang, Manan Anjaria, Lerrel Pinto, Sherry Yang, and Koji Tsuda — a mix consistent with wet-lab deployments plus robot-learning expertise. Reproducibility averages 55 over one assessed paper. Read this as a sharply defined early agenda — hardware plus coding agents for wet labs — whose quantitative footprint is still accumulating.
Collaboration pattern
The visible network is small but distinctive: 7 distinct coauthors, including Kei Endo, Takanori Uzawa, Yunzhe Zhang, Manan Anjaria, Lerrel Pinto, Sherry Yang, and Koji Tsuda. WetRobo's deployment in two real wet labs implies hands-on work with laboratory-side partners alongside robot-learning researchers. The collaboration score of 41/100 reflects sample size — one cataloged paper — not isolation; additional cataloged work would quickly reshape this picture.
Research keywords
Highlights
WetRobo: a reproducible robot kit operated by coding agents
Cross-lab transfer beats a fine-tuned VLA
Evidence base: single run, single model
Timeline
- 2026Publishes first-author WetRobo on arXiv: a reproducible robot kit for coding agents in biological laboratories.
- 2026Demonstrates the kit adapting across two real wet labs, with the coding agent beating a fine-tuned VLA on cross-lab cap transfer.
- 2026Evolve reviews WetRobo, rating reproducibility readiness medium and noting that single-run, single-model evidence tempers the claim.
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 scores are computed from public bibliometric data (OpenAlex-based); no institutional or ORCID linkage was available, so this profile is name-resolved and may require verification.
- Only one paper (WetRobo, 2026) is in the Evolve catalog; the output, impact, and activity dimensions lack sufficient data and are intentionally left unscored.
- The reproducibility score (55) averages a single assessed paper and may shift substantially as more work is reviewed.
- Institution, country, and ORCID are unlisted in the source data; career facts beyond the cataloged paper are not covered by this profile.