Ran Xu
Room N410, Mathematics and Science Center
400 Dowman Dr, Atlanta, GA 30307
My name is Ran Xu. I’m a 4th year Ph.D. student in Department of Computer Science at Emory University, co-advised by Prof. Carl Yang and Prof. Joyce C. Ho. Before that, I obtained my bachelor’s degree (with Highest Honors) from the Department of Computer Science, Emory University in 2021, where I worked with Prof. Jinho Choi.
My current research interest focuses on large language models, with a special interest on augmented (e.g. retrieval augmented, tool-augmented) language models and their biomedical applications. I have also worked on synthetic data generation and llm alignment.
Feel free to drop me an email (ran.xu at emory dot edu
) if you have any questions about my research, or want to discuss about potential collaborations.
I am looking for internship/fulltime industrial opportunities, starting from Spring 2025. Feel free to reach out if there is a good fit!
Educations
Industrial Experience
- Amazon (May 2024 - Oct 2024)
- Applied Scientist Intern, Amazon Search
- Topic: LLM Fine-tuning for Self-improving Retrieval-Augmented Generation [preprint].
- Mentor: Hui Liu, Manager: Qi He.
- Meta Platforms, Inc. (May 2020 - Aug 2020)
- Enterprise Engineer Intern
- Mentor: Zexi Zhang
News
Sep 20, 2024 | Three papers on LLMs for Text Retrieval, LLM Agents for Complex Tabular Reasoning and LLM Test-time Adaptation are accepted to EMNLP 2024. |
---|---|
May 20, 2024 | Started my internship at Amazon Search! |
May 16, 2024 | Two papers on Synthetic Data Generation and Retrieval Augmented clinical predictions are accepted to ACL 2024. |
Nov 28, 2022 | Our paper Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR received the Best Paper Award (2 in total) at the Machine Learning for Health 2022. |
Nov 19, 2022 | One paper on Few-shot Learning for Language Models is accepted to AAAI 2023 as Oral presenation. |
Selected Publications
- SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized DomainsarXiv preprint arXiv:2410.17952, 2024.