Zewen Yang
Robotics Research (United States) · United States
Control researcher advancing Gaussian-process cooperative learning for distributed estimation and multi-robot systems
3
papers here
1
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
1
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) 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—
Insufficient data: the snapshot contains only five works, all surfacing in 2026, so no multi-year publication trajectory or venue record exists to score. This axis would measure cumulative output volume, publication venues, and yearly productivity.
Impact—
Insufficient data: with an h-index of 1, an i10-index of 0, and all works appearing in 2026, there is no citation accumulation to evaluate. This axis would measure citations, the citing literature, and downstream influence.
Focus100/100
The focus score of 100 reflects an exceptionally concentrated record: of the topic counts — Gaussian processes and Bayesian inference (4), distributed control of multi-agent systems (3), control systems and identification (3), data stream mining (2), stability of uncertain systems (1) — nearly all sit on one control-and-learning continuum, and the OpenAlex field distribution lists a single field, distributed estimation at the control/ML interface.
Collaboration50/100
Collaboration scores 50. The record lists 11 distinct coauthors, and the catalog positions Yang as first author on COIN-GP but middle author on the two other 2026 arXiv papers — leading one line of work while contributing inside team projects. Recurring partners in the data include Xiaobing Dai, Sandra Hirche, Armin Lederer, Yang Tang, Wei Ren, and Zhijun Li.
Activity52/100
Activity scores 52. The snapshot records 5 works in the last three years, but countsByYear shows all five in 2026, indicating one concentrated burst of preprints rather than a sustained multi-year cadence. With no earlier years indexed, it is too soon to tell whether this rate will continue.
Reproducibility55/100
Reproducibility scores 55, computed from a single assessed paper. Evolve's review of COIN-GP (medium repro-readiness) finds the theory sound but validation resting on one small simulation, so the score reflects promising methodological transparency with thin empirical support; the other two papers are not yet assessed.
Research summary
Zewen Yang is a researcher at the interface of control systems and machine learning, working on networked and multi-robot systems; the identity here is resolved from public OpenAlex bibliographic data. The snapshot records five works within the last three years, all surfacing in 2026, with an h-index of 1 and an i10-index of 0 — a citation record at its earliest stage. Topic counts concentrate tightly: Gaussian processes and Bayesian inference (4), distributed control of multi-agent systems (3), control systems and identification (3), plus data stream mining (2) and stability of uncertain systems (1). Evolve's catalog holds three 2026 arXiv papers: first-authored COIN-GP, which applies Gaussian process regression to cooperative online learning for distributed estimation under partial measurements, and two middle-author papers on event-triggered control and asynchronous cooperative learning for networked and multi-robot systems under computational delays. An Evolve review judged COIN-GP theoretically sound but validated only by a single small simulation, giving medium repro-readiness (reproducibility mean 55 from one assessed paper). The profile pairs a maximal focus score (100) with moderate collaboration (50) and activity (52); output and impact cannot yet be scored.
Collaboration pattern
Yang's record lists 11 distinct coauthors. The authorship pattern mixes leadership and teamwork: first author on COIN-GP, middle author on the two companion 2026 preprints, which look like outputs of one ongoing networked-control effort. The most frequent partners in the data are Xiaobing Dai, Sandra Hirche, Armin Lederer, Sihua Zhang, Lu Wan, Yang Tang, Wei Ren, Zhenxiao Yin, Hang Zhao, Zhijun Li, and C. C. Chan.
Research keywords
Highlights
COIN-GP: first-author framework for cooperative online learning
Event-triggered control and online learning under computational delays
A 2026 middle-author arXiv paper extending the delay-aware networked-control line, combining event-triggered control with online learning for networked systems; Evolve has not yet reviewed it, so no verdict or readiness rating exists.
Asynchronous cooperative learning for multi-robot control
This 2026 middle-author arXiv preprint studies asynchronous cooperative online learning for multi-robot control under computational delays, complementing COIN-GP's estimation-focused setting; it awaits Evolve review.
Timeline
- 2026First-author arXiv preprint COIN-GP introduces cooperative online learning via Gaussian process regression for distributed estimation with partial measurements.
- 2026Middle-author arXiv preprint on event-triggered control and online learning for networked systems under computational delays.
- 2026Middle-author arXiv preprint on asynchronous cooperative online learning for multi-robot control under computational delays.
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 figures (h-index 1, i10-index 0, works, topics, coauthors) come from an OpenAlex-derived snapshot only; no ORCID was available, so the profile is name-resolved from public bibliographic data and same-name authors may be merged or split.
- All indexed works surface in 2026; career history, education, and affiliation details are absent from the data and were not inferred.
- Output and impact dimensions are unscored because the underlying citation and volume data are insufficient (h-index 1, i10-index 0, a single snapshot year).
- The reproducibility score rests on one assessed paper (COIN-GP); two of the three catalog papers lack Evolve reviews, keywords, and readiness ratings.