Shuguang Cui
Chinese University of Hong Kong · Hong Kong SAR China
CUHK researcher bridging vision-language-action robot learning and AI-based coronary angiography video analysis
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-09) 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—
Missing. The output axis would measure cumulative publication volume and yearly productivity; the current record shows h-index and i10-index of 0 with no reliable year-by-year output series, so this dimension is not yet assessable.
Impact—
Missing. This axis would measure citation-based influence (total citations, h-index and i10-index); no citation counts exist in the current OpenAlex record beyond zero-valued indices, so impact cannot be scored yet.
Focus0/100
The focus score is 0/100, consistent with the raw field distribution: an even 50/50 split between medical image analysis (AI for cardiology) and robotics (vision-language-action models / robot learning), plus five OpenAlex topics each counted once. The two 2026 papers address unrelated problems — SYNTAX scoring from angiography videos and masking against VLA trajectory overfitting — so the profile currently reads exploratory rather than specialized.
Collaboration56/100
Collaboration scores 56/100 on the strength of 16 distinct co-authors within the recent window and 12 recurring collaborators, including Zhen Li, Suzhong Fu and Jingqi Dong. However, both cataloged 2026 papers list this researcher in a middle author position with no corresponding role, indicating active team membership rather than leadership; the small two-paper base keeps the score moderate.
Activity32/100
Activity scores 32/100: the OpenAlex record lists 2 works in the recent three-year window, both in 2026 (countsByYear shows a single year, 2026, with 2 outputs). Publication cadence is thus very recent and thin — an early or newly-disambiguated profile — so sustained output over time cannot yet be demonstrated.
Reproducibility55/100
Reproducibility scores 55/100, averaged over the 2 reviewed papers (reproMean 55, reproPapers 2), both rated medium readiness. Evolve's reviews note concrete quantitative gains — R² improving from 0.328 to 0.529 for SYNTAX scoring, strong RoboTwin 2.0 and real-robot results for MaskVLA — tempered by missing error bars, an augmentation confound, single baselines and no external validation.
Research summary
Shuguang Cui is a researcher at the Chinese University of Hong Kong whose cataloged work, profiled from OpenAlex bibliographic data, spans two areas in equal measure: medical image analysis for cardiology and robot learning with vision-language-action (VLA) models. Two 2026 arXiv preprints define the current record. The first, MaskVLA, applies visual masking to primary-camera inputs against trajectory overfitting in VLA fine-tuning, reporting strong RoboTwin 2.0 and real-robot gains, though Evolve notes the absence of error bars and an augmentation confound. The second reframes SYNTAX scoring from coronary angiography videos as segment-level anatomical reasoning, lifting R² from 0.328 to 0.529, with a single baseline and no external validation. Both papers carry medium reproducibility readiness (reproMean 55 across 2 reviewed papers). In each, Cui is a middle author rather than corresponding author, embedded in teams of 16 distinct recent co-authors. OpenAlex topics — medical image segmentation, coronary interventions, cardiac imaging, reinforcement learning in robotics and robot manipulation — mirror this dual profile. Overall this is an early-stage, exploratory profile: recent three-year output is only 2 works, activity scores 32/100 and focus is split 50/50 across fields, while the output and impact dimensions lack sufficient data to score.
Collaboration pattern
Collaboration is team-based and spans both fields: 16 distinct co-authors appear in the recent window, with 12 recurring collaborators including Zhen Li, Suzhong Fu, Jingqi Dong, Xuan Ding and Rui Sun. In both cataloged 2026 papers, Shuguang Cui is a middle author and not corresponding, suggesting contribution within larger cardiology-imaging and robotics teams rather than an independent lead-PI pattern.
Research keywords
Highlights
Visual masking curbs trajectory overfitting in VLA fine-tuning
SYNTAX scoring reframed as segment-level anatomical reasoning
Timeline
- 2026Two arXiv preprints enter the OpenAlex record — the profile's entire current output (countsByYear: 2026, 2 works; recent3yWorks: 2).
- 2026MaskVLA released on arXiv: visual masking against trajectory overfitting of vision-language-action models, with the researcher as a middle author.
- 2026SYNTAX scoring from coronary angiography videos published on arXiv as segment-level anatomical reasoning, again with middle authorship.
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.
- Bibliometric figures come from OpenAlex only; h-index and i10-index are recorded as 0, reflecting sparse or unresolved author records rather than measured productivity.
- "Shuguang Cui" is a relatively common Chinese name; this profile is name-resolved from public bibliographic data and may merge or omit same-name authors.
- Both cataloged works are 2026 arXiv preprints with middle, non-corresponding authorship; peer-reviewed venue status and individual contribution level cannot be confirmed.
- Output and impact dimensions are reported as missing; no citation counts or multi-year publication series were available in the data.