Florida State University researcher in POI recommendation and human mobility trace generation for urban computing
2
papers here
2
reviewed by Evolve
2
first-author
0
corresponding
—
works · OpenAlex
14
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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—
An output score is not yet computed. This axis would measure publication volume and productivity trends; the underlying OpenAlex record (h-index 14, 22 works already indexed in 2026) exists but has not yet been calibrated into a score.
Impact—
No impact score is available yet. This axis would measure citation-based influence such as citations per year and field-normalized rates; only h-index 14 and i10-index 17 are on record, which cannot yet be scored.
Focus0/100
The focus score is 0, the lowest on the scale, and the topic record explains why: OpenAlex attributes 25 works to rock mechanics and modeling, 20 to geomechanics and mining, and 9 to geotechnical engineering, alongside 8 in traffic prediction and 7 in energy load forecasting, while the reviewed papers sit in AI fields with fieldDist split exactly 50/50. This reads as either deliberate cross-domain breadth or a conflated author record.
Collaboration39/100
Collaboration scores 39. The OpenAlex record lists only 6 distinct coauthors in the recent window, a small pool, and the recurring names are Lin Jiang, Guang Wang, and Dahai Yu, pointing to a compact, repeat-partner working style rather than large multi-institution teams. Both 2026 arXiv papers are first-authored. The raw coauthor list contains duplicates and a self-entry, so the true network may be slightly larger.
Activity100/100
Activity is the standout axis at 100. The record shows 31 works in the recent three-year window, with 6 indexed works in 2025 accelerating sharply to 22 already in 2026 — the strongest year since counts begin at 3 works in 2014. Both catalog papers are 2026 first-author arXiv preprints, consistent with an intense current publishing phase.
Reproducibility38/100
Reproducibility averages 38 across the 2 papers reviewed by Evolve. EviRec is rated medium readiness — its +20.4% NDCG@10 gains were found consistent, but internal dataset-scale inconsistencies need checking. ZeroHAT is rated low: its reported 4.5–6.4× utility gains rest on very weak baselines, with no code and no error bars. Releasing code and fixing the flagged inconsistencies are the clearest paths to raising this score.
Research summary
Rongchao Xu is a researcher at Florida State University whose OpenAlex field distribution splits evenly (0.5/0.5) between recommender systems/urban mobility data mining and spatiotemporal data mining/urban computing. The Evolve catalog carries two 2026 first-author arXiv preprints. EviRec applies continual evidence learning with mixture-of-experts gating to dual cold-start POI recommendation; Evolve's review credits reliability gating with a +20.4% NDCG@10 lift and consistent results, while flagging dataset-scale inconsistencies. ZeroHAT generates human activity traces zero-shot through behavioral cloning and product-of-experts fusion; its reported 4.5–6.4× utility gains rest on weak baselines, with no code or error bars, earning low reproducibility readiness. Bibliometrically the record shows h-index 14, i10-index 17, and 31 works in the recent three-year window, accelerating from 6 indexed works in 2025 to 22 already in 2026 — the basis for a maximum activity score of 100. Collaboration is compact at 6 distinct coauthors, with Lin Jiang, Guang Wang, and Dahai Yu recurring. The topic record is unusually scattered — 25 works in rock mechanics and 20 in geomechanics sit beside the AI portfolio — producing a focus score of 0 and suggesting a possible conflated author record. Output and impact remain unscored pending sufficient data.
Collaboration pattern
The collaboration footprint is compact: OpenAlex counts 6 distinct coauthors in the recent window (collaboration score 39), and the recurring partners are Lin Jiang, Guang Wang, and Dahai Yu. Both 2026 catalog papers are first-authored without corresponding-author designation, consistent with a small, stable team rather than sprawling multi-group consortia. The raw coauthor list carries duplicates and a self-entry, a name-resolution artifact.
Research keywords
Highlights
EviRec: reliability-gated continual learning lifts dual cold-start POI recommendation
ZeroHAT: behavior-conditioned zero-shot human activity trace generation
A reliability-first agenda across recommendation and mobility synthesis
Across both 2026 first-author preprints the through-line is making urban-mobility AI dependable under sparse data: reliability estimation and continual evidence for cold-start recommendation on one side, zero-shot transfer for trace generation on the other. Evolve's reproducibility mean of 38 marks code release as the obvious next step.
Timeline
- 2014Earliest activity in the OpenAlex record: 3 works indexed in 2014.
- 20194 works indexed in 2019, one of the steadier years of the early period.
- 20224 works indexed in 2022, matching the 2019 pace.
- 20256 works indexed — output accelerating into a new publishing phase.
- 2026Strongest year on record with 22 works already indexed; two first-author arXiv preprints enter the Evolve catalog — EviRec on dual cold-start POI recommendation and ZeroHAT on zero-shot activity trace generation.
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.
- All bibliometrics derive from a single OpenAlex snapshot; h-index 14 and i10-index 17 are as recorded there and were not cross-checked against other databases.
- The OpenAlex topic record mixes rock mechanics, geomechanics, and geotechnical works with this profile's AI papers, suggesting possible conflation of author records sharing the name; identity is resolved bibliographically only.
- Output and impact dimensions are unscored (insufficient data): volume and citation-level metrics were not sufficient for calibration.
- Only 2 papers carry Evolve reproducibility reviews (reproMean 38); no code-availability audit beyond those verdicts was performed.