NUS researcher spanning LLM agents for scientific peer review and vision-language robot control
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) 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—
No output score is available yet. This axis would measure publication volume and productivity over time. The snapshot lists only 3 works in 2026 plus two Evolve-reviewed arXiv papers — too thin a record to score reliably.
Impact—
No impact score is available yet. This axis would measure citation-based influence, such as h-index and i10-index; both are recorded as 0 in this snapshot, so influence cannot be assessed from the current data.
Focus0/100
The focus score is 0, reflecting an even split — 0.5 versus 0.5 — between natural language processing for science and robotics / embodied AI in the OpenAlex field distribution. Topic records echo the spread: multimodal machine learning applications (2), plus single counts for topic modeling, NLP techniques, reinforcement learning in robotics, and robot manipulation and learning. Current work spans two domains rather than one concentrated research line.
Collaboration64/100
Collaboration scores 64. The snapshot records 24 distinct coauthors — a wide network for an early-stage profile. The frequent-coauthor list spans 12 named collaborators, including Mike Zheng Shou, Kevin Qinghong Lin, Siyuan Hu, and Pan Lu, covering both the multi-author PaperDoctor team on the NLP-for-science side and the Show-Harness robotics work, consistent with the dual-field distribution.
Activity40/100
Activity scores 40. The counts-by-year record contains a single year, 2026, with 3 works, and recent3yWorks is likewise 3 — modest recent volume, concentrated entirely in one year. Both Evolve-reviewed papers also date to 2026, so the activity signal rests on a very short observation window.
Reproducibility55/100
Reproducibility scores 55, computed across 2 papers (reproMean 55), both rated medium readiness. Evolve's verdicts temper confidence: Show-Harness reports 89% versus 57% for the best baseline but has a small sample, no significance tests, and unreported latency; PaperDoctor reports 70.6% author acceptance without a baseline or independent correctness validation.
Research summary
Yanzhe Chen is a researcher at the National University of Singapore whose recorded output splits evenly between natural language processing for science (0.5) and robotics / embodied AI (0.5) in OpenAlex field assignments. The bibliometric snapshot is early-stage: it records 3 works in 2026, an h-index and i10-index of 0, and 24 distinct coauthors, so citation-based impact cannot yet be assessed. Evolve has reviewed two 2026 arXiv papers. Show-Harness, with Chen as first author, reports that semantic action units let a vision-language model agent control robots zero-shot, at 89% versus 57% for the best baseline, though the review flags small sample size, no significance testing, and unreported latency. PaperDoctor, a middle-author contribution, presents a three-level agent producing evidence-grounded pre-submission feedback on scientific papers in progress, with a reported 70.6% author acceptance rate but no baseline or independent correctness validation. Both papers carry a medium reproducibility-readiness rating, and the aggregate reproducibility score is 55 across 2 papers. Radar dimensions with sufficient data: collaboration 64, activity 40, focus 0, reproducibility 55; output and impact currently lack sufficient data.
Collaboration pattern
Collaboration scores 64, with 24 distinct coauthors in the snapshot. The listed frequent coauthors — Mike Zheng Shou, Kevin Qinghong Lin, Siyuan Hu, Pan Lu, Yu Chen, Owen Queen, Yupeng Chen, Jialin Yu, Junchi Yu, Zifeng Ding, Yuanfeng Ji, and Sheng Liu — form a broad network spanning both of Chen's fields: the large multi-author PaperDoctor team on the NLP-for-science side and the Show-Harness robotics work.
Research keywords
Highlights
First-authored Show-Harness: VLM agent drives robots zero-shot
Co-authored PaperDoctor: evidence-grounded pre-submission feedback
Timeline
- 2026Published Show-Harness as first author on arXiv, reporting zero-shot robot control by a VLM agent (89% vs 57% for the best baseline in the Evolve verdict).
- 2026Co-authored PaperDoctor on arXiv, a three-level agent for evidence-grounded feedback on papers in progress (70.6% reported author acceptance).
- 2026OpenAlex records 3 works in 2026, split evenly between natural language processing for science and robotics / embodied AI, with 24 distinct coauthors.
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.
- Bibliometrics come from OpenAlex only (identity: openalex); no ORCID is linked, and h-index and i10-index are recorded as 0, so citation-based impact is not yet meaningful.
- 'Yanzhe Chen' is a shared name; this profile is name-resolved from public bibliographic data and may mix same-name records without ORCID-based disambiguation.
- Both reviewed papers are 2026 arXiv preprints; venue acceptance and peer-review status are not reflected in this data.
- The reproducibility score (55) is computed from only 2 papers, and the radar output and impact dimensions currently lack sufficient data.