Publications

Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J. Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab (2025). GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning. ArXiv Preprint.

PDF Cite

Michael J. Ryan, Omar Shaikh, Aditri Bhagirath, Daniel Frees, William Held, Diyi Yang (2025). SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs. ACL 2025.

PDF Cite Code Dataset Poster Slides

Ella Li, William Held, Michael J. Ryan, Kunat Pipatanakul, Potsawee Manakul, Hao Zhu, Diyi Yang (2025). Mind the Gap: Static and Interactive Evaluations of Large Audio Models. ACL 2025.

PDF Cite Code Source Document

Potsawee Manakul, Woody Haosheng Gan, Michael J. Ryan, Ali Sartaz Khan, Warit Sirichotedumrong, Kunat Pipatanakul, William Held, Diyi Yang (2025). AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation. ArXiv Preprint.

PDF Cite Code

Michael J. Ryan, Danmei Xu, Chris Nivera, Daniel Campos (2025). EnronQA: Towards Personalized RAG over Private Documents. ArXiv Preprint.

PDF Cite Dataset

Shangyin Tan, Lakshya A Agrawal, Arnav Singhvi, Liheng Lai, Michael J. Ryan, Dan Klein, Omar Khattab, Koushik Sen, Matei Zaharia (2025). LangProBe: a Language Programs Benchmark. ArXiv Preprint.

PDF Cite

Krista Opsahl-Ong*, Michael J. Ryan*, Josh Purtell, David Broman, Christopher Potts, Matei Zaharia, Omar Khattab (2024). Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs. EMNLP 2024.

PDF Cite Code Dataset Slides Video DOI

William Held, Yanzhe Zhang, Ella Li, Weiyan Shi, Michael J. Ryan, Diyi Yang (2024). Distilling an End-to-End Voice Assistant Without Instruction Training Data. ACL 2025.

PDF Cite Code Video Source Document

Michael J. Ryan, William Held, Diyi Yang (2024). Unintended Impacts of LLM Alignment on Global Representation. ACL 2024.

PDF Cite Code Dataset Poster Slides Video DOI

Michael J. Ryan, Tarek Naous, Wei Xu (2023). Revisiting non-English Text Simplification: A Unified Multilingual Benchmark. ACL 2023.

PDF Cite Code Dataset Poster Slides Video DOI

Tarek Naous, Michael J. Ryan, Anton Lavrouk, Mohit Chandra, Wei Xu (2023). Towards Massively Multi-domain Multilingual Readability Assessment. EMNLP 2024.

PDF Cite Dataset

Tarek Naous, Michael J. Ryan, Alan Ritter, Wei Xu (2023). Having Beer after Prayer? Measuring Cultural Bias in Large Language Models. ACL 2024.

PDF Cite Dataset

Michael J. Ryan (2019). Facial Composite Generation from Natural Language Text Descriptions using Stacked Generative Adversarial Networks. AP Research (Score 5/5).

PDF Cite

Ashley Chung, Sean Kim, Ethan Kwok, Michael J. Ryan, Erika Tan, Ryan Gamadia (2018). Cloud Computed Machine Learning Based Real-Time Litter Detection using Micro-UAV Surveillance. IEEE MIT URTC.

PDF Cite Code Video DOI