Princeton researcher bridging AI-driven discovery frameworks and machine-learning models of the immune system
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
0
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—
Output metrics are not yet available: the resolved OpenAlex record yields no reliable publication count, so career volume cannot be scored. This axis would measure aggregate publications, venue mix, and productivity consistency over time.
Impact—
Impact data is insufficient: the snapshot reports h-index 0 and i10-index 0, which for a common name most likely reflects incomplete identity resolution rather than measured influence. This axis would measure citations, citation concentration, and uptake in later work.
Focus0/100
Focus scores 0/100, reflecting an evenly split record: the field distribution assigns 0.5 to artificial intelligence and 0.5 to computational biology / machine learning for immunology, and five indexed topics each carry a single paper — Cancer Immunotherapy and Biomarkers, AI-based Problem Solving and Planning, Logic, Reasoning, and Knowledge, Artificial Immune Systems Applications, and vaccines/immunoinformatics. Both catalog papers nonetheless share one thread — AI systems that generate scientific hypotheses — which may consolidate as the record matures.
Collaboration54/100
Collaboration scores 54/100, based on 14 distinct coauthors in the record. Coauthorship is broad but not yet deep: recurring names include Zhenfei Yin, Yingcheng Wu, Taoyong Cui, Xi Wang, Zonghang Li, Jinchao Ding, Lingsen You, Yuzhi Xu, Wanghan Xu, Fang Wu, and Kejun Ying. Neither cataloged paper is corresponding-authored — one is first-authored, one middle-positioned — suggesting a contributor pattern within small-to-mid-sized teams rather than sustained independent group leadership.
Activity32/100
Activity scores 32/100. The record shows 2 works in the last three years, with countsByYear listing only 2026 (2 papers): the first-authored Discovery Foundation Models framework paper and the immune world model study. With a single visible active year and both outputs on arXiv, the signal is too short to establish a steady cadence; the profile reads as newly active, with 2026 as its first recorded year.
Reproducibility20/100
Reproducibility scores 20/100 (reproMean 20 across 2 papers). Both cataloged papers rate low on reproducibility readiness: the Discovery Foundation Models paper implements no system, so there is nothing to run, and the immune world model paper applies disciplined gating but keeps its code unreleased with modest reported gains. For a profile centered on AI-for-science claims, releasing code and evaluation protocols would be the fastest way to lift this score.
Research summary
Ling Yang (Princeton University, US) is an early-stage researcher whose profile is name-resolved from public OpenAlex bibliographic data; 'Ling Yang' is a common name and no ORCID is on file, so identity confidence is limited. The Evolve catalog holds two 2026 arXiv preprints. The first-authored 'Discovery Foundation Models: Toward Open-Ended Discovery Intelligence' proposes a taxonomy and process protocol for open-ended AI-driven discovery — covering research state, hypothesis revision, and experimental design — but implements nothing. The second, an immune world model for multiscale forecasting and therapeutic hypothesis generation (middle authorship), uses an AI-Scientist pipeline to forecast multiscale immune states and nominates IL-36γ+SIRPα, with disciplined gating but unreleased code and modest gains. The record splits evenly between artificial intelligence and computational biology / machine learning for immunology (0.5 each), spread across five topics with one paper apiece — a breadth-first, framework-heavy style rather than one deep line. Collaboration is moderate: 14 distinct coauthors, with recurring partners including Zhenfei Yin, Yingcheng Wu, Fang Wu, and Wanghan Xu. Activity is thin and recent — 2 works in the last three years, both in 2026 — and both papers rate low on reproducibility readiness (mean 20). Citation indicators are not yet reliably resolved.
Collaboration pattern
The record lists 14 distinct coauthors. Recurring names include Zhenfei Yin, Yingcheng Wu, Taoyong Cui, Xi Wang, Zonghang Li, Jinchao Ding, Lingsen You, Yuzhi Xu, Wanghan Xu, Fang Wu, and Kejun Ying, indicating stable small-team clusters. Positioning spans first author on the framework paper and middle author on the immune world model study, with neither paper corresponding-authored — a contributor-style pattern across two loosely connected lines (AI methods and ML-for-immunology) rather than a single lab-led agenda.
Research keywords
Highlights
Discovery Foundation Models: a taxonomy for open-ended AI-driven discovery
An immune world model nominates IL-36γ+SIRPα as a therapeutic hypothesis
Timeline
- 2026First-authored arXiv preprint 'Discovery Foundation Models: Toward Open-Ended Discovery Intelligence' proposes a taxonomy and process protocol for open-ended AI discovery; nothing is implemented or measured.
- 2026Coauthors (middle position) 'An immune world model for multiscale forecasting and therapeutic hypothesis generation', built with an AI-Scientist pipeline; it nominates IL-36γ+SIRPα.
- 2026Both papers enter the Evolve catalog in the same year, splitting the record evenly between artificial intelligence and machine learning for immunology, and both rate low on reproducibility readiness.
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.
- Name-resolved from OpenAlex public bibliographic data; 'Ling Yang' is a common name and no ORCID is on file, so identity confidence is limited.
- Citation indicators (h-index 0, i10-index 0) and the missing output/impact dimensions most likely reflect incomplete identity resolution, not measured performance.
- Bibliometrics come from OpenAlex only; both cataloged papers are arXiv preprints with no peer-reviewed venue on file.
- Early-stage profile: a single visible active year (2026), with reproducibility and verdicts based on Evolve's review of these two papers only.