Harbin Institute of Technology researcher working across radiology report generation and test-time image restoration.
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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—
The output axis, which would measure publication volume and productivity over time, cannot be scored yet: OpenAlex currently records h-index 0 and i10-index 0, with year-by-year counts available only for 2026, leaving insufficient data for a reliable score.
Impact—
The impact axis, which would measure citation influence such as h-index and citedness across published work, has no usable data here: the profile records h-index 0 and i10-index 0 with no citation history, so this axis is left unscored rather than estimated.
Focus0/100
The recorded field distribution is an exact 50/50 split between medical AI — radiology report generation and computer vision image restoration, which yields a focus score of 0: activity is spread evenly across two quite different research areas. The OpenAlex topic profile reinforces this breadth, with five clusters (advanced neural network applications, human pose and action recognition, multimodal machine learning, GANs and image synthesis, domain adaptation and few-shot learning) each holding two to three works.
Collaboration56/100
OpenAlex links Yaowei Wang to 16 distinct coauthors in the recent window, producing a collaboration score of 56. Twelve recurring collaborators are named, including Futian Wang, Xiao Wang, Jin Tang, Yuhan Qiao and Dan Xu. On the two reviewed papers Wang sits in non-corresponding positions — middle author on MAC-RRG and last author on TTTIR — a pattern consistent with contributing as a technical team member within larger, multi-author groups.
Activity64/100
The activity score of 64 reflects a recent and concentrated publication burst: OpenAlex records 8 works within the most recent three-year window, and the year-by-year counts place all of them in 2026. Both reviewed outputs — the MAC-RRG and TTTIR preprints — appeared on arXiv in 2026, indicating that current output is fast-moving preprint activity whose longer-term trajectory is still being established.
Reproducibility55/100
Reproducibility is scored at 55 as the mean readiness rating over 2 reviewed papers, each rated medium. Evolve's review notes limit confidence: MAC-RRG leaves its knowledge sources unspecified, and TTTIR reports strong state-of-the-art gains but includes several results, such as the LOL-v2-Real 30.78 dB figure, flagged as needing verification. Code availability is not recorded, so independent replication is not yet demonstrated.
Research summary
Yaowei Wang is a researcher at Harbin Institute of Technology (CN) whose recorded output sits at the intersection of medical AI and low-level computer vision. This is an early-stage profile built from OpenAlex bibliometric data and Evolve's reviews of two 2026 arXiv preprints. The first, MAC-RRG, proposes iterative multi-agent collaboration — combining knowledge-graph and retrieval signals — to inject domain knowledge into large language models for chest X-ray radiology report generation; Evolve judged the gains real but small, with the 'iterative' framing overstated and knowledge sources unspecified. The second, TTTIR, applies test-time training to image restoration with spatial-frequency target states, reporting strong state-of-the-art gains on low-light enhancement, deraining and dehazing, though several results (e.g., LOL-v2-Real 30.78 dB) still require verification. OpenAlex records 8 works in the most recent three-year window — all dated 2026 — alongside 16 distinct coauthors, and a topic profile spanning advanced neural network applications, human pose and action recognition, multimodal machine learning, GAN-based image synthesis, and domain adaptation/few-shot learning. Citation-based metrics are not yet meaningful: the profile shows h-index 0 and i10-index 0, so output and impact axes are left unscored. The even 50/50 field split between radiology report generation and image restoration yields a focus score of 0, signaling breadth rather than a single established specialty.
Collaboration pattern
OpenAlex links Yaowei Wang to 16 distinct coauthors, with 12 recurring collaborators including Futian Wang, Xiao Wang, Jin Tang, Yuhan Qiao and Dan Xu. On both reviewed papers he occupies non-corresponding positions — middle author on MAC-RRG and last author on TTTIR — suggesting he contributes within larger, team-led projects rather than acting as sole or corresponding lead. The collaboration score of 56 reflects a moderate-sized, active co-author network.
Research keywords
Highlights
MAC-RRG: multi-agent knowledge injection for chest X-ray reporting
TTTIR: test-time training for adaptive image restoration
Dual-track output across medical AI and low-level vision
OpenAlex field distribution splits evenly (0.5/0.5) between radiology report generation and image restoration, with 8 works recorded in 2026 and topics extending to human pose and action recognition, multimodal machine learning, GAN-based image synthesis, and domain adaptation and few-shot learning.
Timeline
- 2026Posted the MAC-RRG preprint on arXiv: iterative multi-agent collaboration combining knowledge-graph and retrieval signals for chest X-ray radiology report generation.
- 2026Posted the TTTIR preprint on arXiv: test-time training with spatial-frequency target states for image restoration spanning low-light enhancement, deraining and dehazing.
- 2026OpenAlex year-by-year counts record all 8 recent works as 2026 output, marking the visible start of this researcher's publication record.
- 2026Collaboration network reached 16 distinct coauthors across the recent window, with recurring collaborators including Futian Wang, Xiao Wang and Jin Tang.
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 metrics are derived from OpenAlex (identity source: openalex); h-index and i10-index are currently recorded as 0, so output and impact dimensions are unscored.
- Both reviewed papers are 2026 arXiv preprints; peer-reviewed venue publication is not yet established in the available data.
- Year-by-year publication counts are available for 2026 only, so longer-term productivity trends cannot be assessed.
- Profile is name-resolved from public bibliographic data via ORCID 0009-0000-9290-1356; 'Yaowei Wang' is a common name and homonym records may be mixed.