Machine learning researcher working on generative tabular-data synthesis with diffusion models and LLM guidance.
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
5
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—
Not yet scored: the snapshot has no verified full publication list, only aggregated per-year counts (rising from 1 work in 2022 to 14 in 2025 and 2026). This axis would measure total publication volume, consistency over time, and venue quality.
Impact—
Not yet scored: citation-based influence cannot be assessed from the reviewed data. This axis would measure citations, citing works, and citation trajectory over time; the snapshot's h-index of 5 is too sparse for a reliable impact estimate.
Focus100/100
Scores 100 on focus. The topic distribution is strongly concentrated: Machine Learning and Data Classification leads with 16 topic-assigned works, followed by Domain Adaptation and Few-Shot Learning (8), Machine Learning in Healthcare (6), Computational Drug Discovery Methods (5), and Artificial Intelligence in Healthcare (5). The single classified field record, 'machine learning — generative models for tabular data', and both 2026 preprints on tabular synthesis point to one coherent line.
Collaboration50/100
Scores 50 (moderate). The snapshot records 11 distinct coauthors in the recent window, and the frequent-coauthor list includes Jinmeng Li, Quan Zhang, He Zhao, Firas Laakom, Dandan Guo, Jürgen Schmidhuber, Yili Wang, Ruxue Shi, Mengnan Du, Yi Chang, and Xin Wang. Both catalog papers place this researcher in a middle author position without corresponding-author status, suggesting contribution within larger teams rather than independent leadership.
Activity100/100
Scores 100. Output intensity is the strongest signal in the record: 32 works in the most recent three-year window, with per-year counts climbing from 1 (2022), 3 (2023), and 4 (2024) to 14 in each of 2025 and 2026. The 2025–2026 step change coincides with the shift toward tabular-data generative modeling visible in the two 2026 arXiv preprints.
Reproducibility55/100
Scores 55, based on a single assessed paper (reproMean 55 across 1 reproPaper). The reviewed SCTab-Diff preprint carries a medium reproducibility readiness: Evolve's verdict finds the results sound but notes marginal semantic gains and partly circular evaluation, leaving reproduction feasible yet dependent on careful re-implementation of the semantic-prior pipeline.
Research summary
Hangting Ye is an early-career machine learning researcher affiliated with Jilin University whose recorded output concentrates on generative modeling for tabular data and LLM-assisted data synthesis. The bibliometric snapshot (OpenAlex identity) shows a steep activity ramp: per-year work counts rise from 1 in 2022 and 3 in 2023 to 4 in 2024, then 14 in 2025 and 14 in 2026 — 32 works in the most recent three-year window, against an h-index of 5 and an i10-index of 2, consistent with a citation record that has not yet caught up with publication volume. Topical counts are led by Machine Learning and Data Classification (16 works), followed by Domain Adaptation and Few-Shot Learning (8), Machine Learning in Healthcare (6), Computational Drug Discovery Methods (5), and Artificial Intelligence in Healthcare (5). In the Evolve catalog, two 2026 arXiv preprints address tabular data synthesis: SCTab-Diff, which conditions tabular diffusion on LLM-extracted semantic priors and is judged sound though with marginal semantic gains and partly circular evaluation, and a study framing LLMs as strategy designers for privacy-preserving tabular synthesis. Both list the researcher as a middle author, indicating team-based collaboration, and the reviewed paper carries a medium reproducibility readiness rating.
Collaboration pattern
The snapshot records 11 distinct coauthors in the recent window, with a broad frequent-coauthor list spanning Jinmeng Li, Quan Zhang, He Zhao, Firas Laakom, Dandan Guo, Jürgen Schmidhuber, Yili Wang, Ruxue Shi, Mengnan Du, Yi Chang, and Xin Wang. Both catalog papers are middle-authored and non-corresponding, indicating contribution within larger, likely multi-institution teams rather than sole or corresponding leadership; the moderate collaboration score (50) reflects an early but expanding network.
Research keywords
Highlights
SCTab-Diff: semantics-consistent tabular diffusion with LLM-extracted priors
LLMs as strategy designers for privacy-preserving tabular synthesis
A second 2026 arXiv preprint frames large language models as designers of synthesis strategies for privacy-preserving tabular data. It is listed in the Evolve catalog without a verdict, keywords, or reproducibility assessment yet.
Sharp output acceleration centered on tabular generative modeling
Per-year work counts climb from 1 (2022) to 14 (2025) and 14 (2026), with 32 works in the recent three-year window; the classified field record, 'machine learning — generative models for tabular data', marks the current research line.
Timeline
- 2022First recorded output appears, with 1 work in the per-year count.
- 2023Recorded output grows to 3 works, still an early accumulation phase.
- 20244 works recorded, the last year before the output step change.
- 2025Output jumps to 14 works, the largest single-year count in the record.
- 202614 works recorded, including two arXiv preprints on LLM-guided tabular data synthesis (SCTab-Diff and a privacy-preserving synthesis strategy study).
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.
- Bibliometrics (h-index, i10-index, per-year counts, topics, coauthor counts) come from an OpenAlex-based snapshot; the 2026 counts cover a year still in progress.
- Output and impact dimension scores are not computed because verified full publication and citation records are unavailable in the snapshot.
- Only 2 of this researcher's works appear in the Evolve catalog, both 2026 arXiv preprints; only 1 carries a review verdict and reproducibility rating, so findings may not represent the full body of work.
- The profile is name-resolved from public bibliographic data; the listed affiliation is Jilin University while the record's country field is NZ, and this discrepancy has not been independently verified.