Yuntong Hu

PhD Student in Computer Science, Emory University

✉ Email 🎓 Google Scholar in LinkedIn 📄 CV

I am a Ph.D. student at Emory University, supervised by Prof. Liang Zhao. My research lies at the intersection of Graph Learning and Natural Language Processing, spanning Agentic AI, Retrieval-Augmented Generation, LLM Post-Training, and graph & spatio-temporal modeling. My work has appeared at top venues including ICML, NeurIPS, KDD, NAACL, SIGIR, WSDM, CIKM, and ACL. Earlier, during my undergraduate studies, I worked with Prof. Yong Deng and Prof. Fuyuan Xiao on graph learning and spatio-temporal data.

I am always happy to discuss research and explore collaborations. I am also actively open to academic and industry internships, visiting positions, and full-time roles. If any of this resonates with you, please feel free to reach out — email me anytime.

Research Interests

Agentic AI

Self-improving multi-agent systems — evolutionary generation, configuration-space search, and cross-query experience memory.

Retrieval-Augmented Generation

Graph- and citation-aware retrieval with training-free memory that keeps LLMs grounded and up to date.

LLM Post-Training

Distillation, self-supervised objectives, and explanation-guided learning for language models on structured data.

Graph & Spatio-Temporal Learning

Representation learning over graphs, trajectories, and geometries for structured, dynamic data.

Education

Ph.D. in Computer Science

Emory University

Sep 2023 – May 2027 (expected)

B.E. in Network Engineering

Southwest University

Sep 2019 – Jun 2023

Experience

Applied Scientist Intern

AWS AI — Fundamental Research Team

Oct 2025 – Dec 2025

Software Engineering Intern

ByteDance — Applied Machine Learning

May 2025 – Aug 2025

News

Feb 2026Two papers accepted to ICML 2026 — on evolutionary multi-agent systems and continual RAG memory. 🎉
Oct 2025Started as an Applied Scientist Intern at AWS AI, Fundamental Research Team.
May 2025Joined ByteDance as a Software Engineering Intern on the Applied Machine Learning team.
Jan 2025GRAG accepted to NAACL 2025; CG-RAG accepted to SIGIR 2025.

Publications

Bold = me · * = equal contribution · full list on Google Scholar.

Awards & Honors

Outstanding Research Assistant, Emory University (2025–2026).
SIGSPATIAL 2024 — Best Paper Candidate.
Graduate Representative, Southwest University (2023).