Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yilun Yao

Yilun Yao

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2

Frequent co-authors

Yaoming Li2×
Tong Yang2×
Jiaming Pan1×
Elsie Dai1×
Peizhuang Cong1×
Xinyu Tan1×

Research Timeline

2026
Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows

The paper introduces Harness-Bench, a diagnostic benchmark that measures how different system 'harnesses' affect LLM agent performance in realistic workflows, showing that agent capability must be reported at the model-harness configuration level.

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

ConMoE proposes a train-free method for compressing Mixture-of-Experts (MoE) models by consolidating the large expert pool into a smaller set of reusable prototypes and deterministically remapping all original expert calls to these prototypes.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 28, 2026

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

Yilun Yao, Jiaming Pan, Elsie Dai, Peizhuang Cong +2 more

ConMoE proposes a train-free method for compressing Mixture-of-Experts (MoE) models by consolidating the large expert pool into a smaller set of reusable prototypes and deterministically remapping all…

View →
cs.AIRecentMay 27, 2026

Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows

Yilun Yao, Xinyu Tan, Chao-Hsuan Liu, Yaoming Li +8 more

The paper introduces Harness-Bench, a diagnostic benchmark that measures how different system 'harnesses' affect LLM agent performance in realistic workflows, showing that agent capability must be rep…

View →