Early-career researcher in full-duplex speech models and agentic video understanding, with recent arXiv-first work
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-14) 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 metrics are available yet: OpenAlex reports h-index 0 and i10-index 0, with yearly counts recorded only for 2026 (2 works). This axis would measure cumulative papers, venues, and first-author share once the record accumulates.
Impact—
Citation impact cannot be scored: the snapshot shows h-index 0 and i10-index 0, and both catalog papers are 2026 arXiv preprints too recent to have gathered citations. This axis would measure citations, uptake, and downstream use over time.
Focus0/100
The focus score is 0, reflecting a deliberately even split: OpenAlex field distribution is 50% speech processing / spoken dialogue systems and 50% human-computer interaction / sports visualization, with five topics each appearing exactly once. With only two works, no dominant line has emerged yet, though both areas share an agentic-systems thread.
Collaboration59/100
Collaboration scores 59, supported by 18 distinct coauthors across just two recent works — broad relative to output — and 12 recurring collaborators including Tica Lin, Deepak Chandran, Gauri Jagatap, Ke Hu, and Edresson Casanova. Both papers are middle-author and non-corresponding, indicating contribution within larger team settings rather than independent leads.
Activity32/100
Activity scores 32: the record shows 2 works in the last three years, both landing in 2026 per OpenAlex yearly counts, with no prior-year output in this snapshot. Output is recent and arXiv-first, so the cadence is too early to judge whether 2026 marks a ramp-up.
Reproducibility20/100
Reproducibility scores 20, the mean across 2 assessed papers, both rated low readiness. Evolve's review cites missing significance testing in the full-duplex tool-calling paper and a single-match, no-baseline design in the Semantic Action Graph study as the main gaps limiting strong claims.
Research summary
Chen Chen is an early-stage researcher whose public bibliographic footprint — resolved from OpenAlex — currently consists of two 2026 arXiv preprints spanning two distinct areas: a frontend-backend architecture for tool calling in full-duplex speech-to-speech models, and a Semantic Action Graph representation for agentic sports-highlight understanding. The record shows 2 works in the last three years, both published in 2026, with an h-index and i10-index of 0, so citation impact cannot yet be characterized. Authorship is middle position on both papers, neither corresponding, consistent with contributing inside larger research or engineering teams. The collaboration footprint is broad relative to output: 18 distinct coauthors, with recurring collaborators including Tica Lin, Deepak Chandran, Gauri Jagatap, Andrea Fanelli, Ke Hu, and Edresson Casanova. Topic coverage is narrow but split — five topics each appear once, and the field distribution splits evenly between speech processing / spoken dialogue systems and human-computer interaction / sports visualization. Evolve's review rates both papers low on reproducibility readiness (mean 20 across 2 papers), citing missing significance testing and absent baselines.
Collaboration pattern
Across just two 2026 works, OpenAlex records 18 distinct coauthors, and 12 recur as frequent collaborators — including Tica Lin, Deepak Chandran, Gauri Jagatap, Andrea Fanelli, Ke Hu, Elena Rastorgueva, and Edresson Casanova — suggesting steady work within larger speech and sports-media teams. Both papers are middle-author and non-corresponding, so no independent-lead pattern is yet visible.
Research keywords
Highlights
Token-based delegation brings tool calling to full-duplex speech models
Semantic Action Graph links LLM agents and viewers over sports highlights
Timeline
- 2026arXiv preprint: A frontend-backend architecture for tool calls in full-duplex speech models (middle author).
- 2026arXiv preprint: Semantic Action Graph — a shared representation for agent grounding and human interpretation of sports highlights (middle author).
- 2026OpenAlex yearly count reaches 2 works, with 18 distinct coauthors recorded across the two 2026 papers.
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.
- All bibliometric indicators come from OpenAlex only; h-index and i10-index are 0 in this snapshot and no citation counts are available.
- Chen Chen is a common name; this profile is name-resolved from public bibliographic data and may merge or omit same-name records.
- No institution, country, or ORCID was provided, so affiliation and career context is not represented.
- Both catalog papers are 2026 arXiv preprints with middle authorship; peer-reviewed venues and independent-lead work may not yet be captured.