Weihang You

University of Georgia · United States

Unclaimed · AI-structured profileORCID OpenAlex

Early-career ML researcher at University of Georgia working across LLM reasoning and vision-language efficiency

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-16) 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 scored: citation-backed output metrics are too sparse for a reliable estimate (h-index 2, i10-index 1). This axis would measure publication volume and productivity relative to field norms and career stage.

Impact—

Not scored: citation signal is too thin to assess influence (h-index 2, i10-index 1, no per-paper citation counts provided). This axis would measure how often the work is cited, used, or built upon by later research.

Focus0/100

Scored 0, the lowest reading, reflecting a wide research spread rather than a single lane. The OpenAlex topic list spans five distinct areas — multimodal machine learning applications (8), topic modeling (6), information retrieval and search behavior (5), AI-based problem solving and planning (4), and quantum information and cryptography (3) — and the field distribution splits evenly (0.5 machine learning/statistics, 0.5 computer vision with vision-language models).

Collaboration75/100

This is one of the stronger axes, scored 75 from real bibliometric data. The OpenAlex record shows 42 distinct coauthors within the recent three-year window (recent3yWorks: 20), and the input lists 12 recurring collaborators, including Jiazhang Cai, Tao Wang, and Ruidong Zhang. Both Evolve-reviewed papers place Weihang You in a middle author position, consistent with contributing inside larger, multi-author teams rather than single-author work.

Activity89/100

The strongest axis at 89, driven by a sharp recent acceleration. The counts-by-year series records 18 works in 2026 and 2 in 2025, against a single work in 2019, and the profile lists 20 works over the last three years. Both catalog entries are 2026 arXiv preprints, confirming that the surge is current rather than backlog; citation-side measures have not yet caught up.

Reproducibility38/100

Scored 38, computed as the mean readiness across the 2 papers Evolve has reviewed (reproMean 38). The LLM problem-solving survey is rated low: its diagnostic framework is clearly organized but its hypotheses remain untested. The visual token pruning paper is rated medium: reported best-average gains are consistent yet modest, and the review notes the absence of statistical significance testing.

Research summary

Weihang You is an early-stage researcher at the University of Georgia whose profile, resolved from OpenAlex bibliographic data, shows a rapidly accelerating but still thin publication record. The record spans 20 works in the last three years, including a surge to 18 works recorded in 2026, compared with 2 in 2025 and 1 in 2019. Topic coverage is unusually broad: OpenAlex assigns the most weight to multimodal machine learning applications (8), topic modeling (6), information retrieval and search behavior (5), AI-based problem solving and planning (4), and quantum information and cryptography (3), and the field distribution splits evenly between machine learning/statistics and computer vision (vision-language models). Two 2026 arXiv preprints reviewed by Evolve anchor the profile: a survey reframing complex problem solving in large language models as sequential estimation and statistical control, and a study recasting visual token pruning in vision-language models as coverage optimization. Evolve rates the first paper's reproducibility readiness as low and the second as medium, yielding a mean reproducibility score of 38 across the two reviewed papers. Citation-based measures remain minimal (h-index 2, i10-index 1), so output and impact are left unscored. Collaboration is a relative strength, with 42 distinct coauthors in the recent three-year window and a recurring set of 12 frequent collaborators.

Collaboration pattern

The OpenAlex record lists 42 distinct coauthors in the recent three-year window, with a stable inner circle of 12 frequent collaborators — including Jiazhang Cai, Tao Wang, Ruidong Zhang, Siyuan Li, and Terry Ma. On both Evolve-reviewed papers Weihang You sits in a middle author position and is not the corresponding author, suggesting a contributor role inside larger multi-author teams spanning machine learning and vision-language work.

Research keywords

large language modelscomplex problem solvingstatistical decision theoryvision-language modelsvisual token pruninginference efficiencycoverage maximizationmultimodal machine learningtopic modelinginformation retrieval

Highlights

Reframing LLM complex problem solving as sequential estimation and control
A 2026 arXiv survey (middle authorship) applies statistical control and a diagnostic framework — drawing on Bayes filters and uncertainty quantification — to complex problem solving in large language models. Evolve finds it clearly organized and candid, but rates reproducibility readiness low because its diagnostic hypotheses remain untested.
Visual token pruning cast as a coverage optimization problem
The second 2026 preprint reframes token pruning in vision-language models as maximizing coverage of pruned tokens, using coverage maximization, submodular selection, and a first-layer attention probe. Evolve judges the best-average gains consistent but modest, with no statistical significance testing; reproducibility readiness is medium.

Timeline

2019Earliest recorded publication activity in the OpenAlex profile: 1 work.
2025Output resumes at modest scale: 2 works recorded in the year.
2026Sharp acceleration: 18 works recorded in a single year, bringing the recent three-year window to 20 works.
2026Two arXiv preprints enter the Evolve catalog: the statistical-control survey of LLM complex problem solving and the coverage-optimization study of visual token pruning.

Papers in the Evolve catalog

Frequent co-authors

Jiazhang Cai×1 Tao Wang×1 Ruidong Zhang×1 Siyuan Li×1 Terry Ma×1 Luyang Fang×1 Haoran Lu×1 Huimin Cheng×1 Yingchuan Zhang×1 Shushan Wu×1 Rui Xie×1 Lin Tang×1

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 are resolved from OpenAlex only (identity: openalex); coverage of very recent 2026 arXiv preprints and their citations may be incomplete.
Output and impact dimensions are unscored because citation-based measures are minimal (h-index 2, i10-index 1); no per-paper citation counts were provided.
The name is resolved from public bibliographic data; common-name collisions are possible, so read this profile against ORCID 0000-0002-1563-6293 and the listed institution.
The reproducibility score averages Evolve reviews of only 2 papers, both 2026 arXiv preprints; it may not represent the full body of work.