AI researcher working across multimodal agent memory and ophthalmic imaging AI, with a 45-strong collaboration network
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-28) 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: publication-volume data are insufficient in this snapshot. This axis would measure total output, venue spread, and first/corresponding-author share across the researcher's full record.
Impact—
Not yet scored: citation and influence indicators are absent from the current data. This axis would measure citations, h-index-type metrics, and downstream uptake of the reviewed papers.
Focus100/100
Focus is scored 100/100, the maximum, and the raw field distribution concentrates on a single field — AI in ophthalmology (medical imaging). The reviewed catalog adds one AI-agents paper on multimodal memory, so the perfect score reflects how the bibliometric record is coded, and the agent-memory line reads as an adjacent, still-narrow second track rather than scattered interests.
Collaboration76/100
Collaboration scores 76/100, grounded in 45 distinct coauthors on record and a recurring core of 12 frequent collaborators, including Xueshu Chen, Zihao Xue, Jiefu Li, Jungang Lou, Raghavan Lavanya, and Quan V. Hoang. Both reviewed papers place Yan Wang in a middle, non-corresponding position, consistent with contributor roles inside sizable clinical-AI teams rather than solo or leading-author work.
Activity—
Not yet scored: longitudinal publishing data are too thin in this snapshot. This axis would measure output cadence over time — papers per year, gaps, and momentum — across the full career record.
Reproducibility20/100
Reproducibility scores 20/100, computed from a very small base — reproPapers is 1, with a mean of 20 — so the figure is indicative at best. Within the reviewed catalog, readiness differs by paper: the C3M agent-memory work is rated medium, while the multicentre glaucoma ViT study is rated low, in line with Evolve's note that its headline metrics benefit from excluding uncertain cases.
Research summary
Yan Wang is an early-stage profile on Evolve: a researcher name-resolved from public bibliographic data, with institution, country, and ORCID not yet on record. The reviewed catalog contains two 2026 arXiv papers in distinct but adjacent areas. The first, C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks, addresses memory systems for AI agents, coupling a relation-aware index with provenance-preserving budgeted routing; Evolve notes results lead at 32K/64K context lengths but trail CDRs at 128K and lack significance testing. The second is a multicentre study of an uncertainty-aware vision transformer for glaucoma screening across multi-ethnic myopic and non-myopic populations, with external validation on 16 datasets and AUROC 86–100%, though headline metrics are aided by excluding uncertain cases. On both papers Yan Wang holds a middle, non-corresponding author position, consistent with a contributor role in larger teams. The collaboration radar score is 76/100, drawing on 45 distinct coauthors and a recurring core of 12 frequent collaborators spanning clinical ophthalmology and AI. Focus is scored a perfect 100/100 on the coded field distribution, while reproducibility sits at 20/100 from a single assessed paper. Output, impact, and activity axes are unscored because the underlying metrics are missing. Overall, this is a dual-track applied-AI profile — agent memory and medical imaging — whose evidence base is real but narrow.
Collaboration pattern
Yan Wang's collaboration footprint spans 45 distinct coauthors with a recurring core of 12 frequent collaborators, including Xueshu Chen, Zihao Xue, Jiefu Li, Zhenfang Liu, Zhen Bi, Jungang Lou, Raghavan Lavanya, Quan V. Hoang, and Linda Yi-Chieh Poon. Both catalogued papers are middle-author, non-corresponding contributions, suggesting a pattern of working within larger clinical-AI teams across ophthalmology and AI-agent research rather than leading small groups.
Research keywords
Highlights
Multicentre glaucoma screening ViT with strong external validation
C3M: budgeted multimodal memory maintenance for long-horizon agents
Timeline
- 2026Co-authored C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks (arXiv), in a middle, non-corresponding position.
- 2026Co-authored the multicentre uncertainty-aware vision transformer study for glaucoma screening across multi-ethnic myopic and non-myopic populations (arXiv).
- 2026Both catalogued works appear in the same year, establishing a dual-track record across agent memory systems and ophthalmic imaging AI.
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.
- Yan Wang is a very common name; this profile is name-resolved from public bibliographic data and may aggregate records from different individuals.
- Institution, country, and ORCID are not on record; evidence is limited to the two 2026 arXiv papers reviewed by Evolve.
- Output, impact, and activity dimensions are unscored because citation counts, productivity, and longitudinal data are absent from the input snapshot.
- The reproducibility score (20/100) rests on a single assessed paper (reproPapers = 1), so it should be read as indicative only.