Tianyi Xu
School of EECS, Oregon State University
Corvallis, OR 97331
I’m Tianyi Xu, a first-year Ph.D. student in Computer Science at Oregon State University, advised by Prof. Huazheng Wang. I graduated from the University of Wisconsin–Madison with a B.S. in Computer Science, Data Science, and Mathematics, where I worked with Prof. Junjie Hu. I also worked closely with Shaobo Wang and Prof. Linfeng Zhang at Shanghai Jiao Tong University, and Prof. Claudia Solís-Lemus at UW–Madison.
Research interests. I develop efficient and adaptive methods for AI agents, spanning multi-agent systems, test-time training and adaptation, self-evolution, and data-centric AI, where capability, reliability, and compute efficiency must be jointly optimized.
selected publications
- arXiv
EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized SupervisionJun 2026Under review - arXiv
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population ScalesApr 2026Under review - Preprint
Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound ReconstructionMar 2026Under review - Preprint
MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-TrainingMar 2026Under review - arXiv
SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal LanguagesFeb 2026Under review - SSRN
Combined effects of methyl bromide and soil amendments on soil bacterial and fungal communities in turfgrassOct 2025Under review - Rhizosphere
Stem rot affects the structure of rhizosphere microbiome in berseem clover (Trifolium alexandrinum)Rhizosphere, Apr 2025