Training-method researcher

Yu Meng

ORCID lookup ↗DBLP lookup ↗Scholar lookup ↗Semantic Scholar ↗arXiv ↗

Worked on the preference-optimization family of alignment objectives beyond RLHF.

Works in the archive (1)

Preference Optimization Family (IPO/KTO/ORPO/SimPO) · 2024

“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.

Co-authors in the archive

Mohammad Gheshlaghi Azar, Rémi Munos, Kawin Ethayarajh, Douwe Kiela, Jiwoo Hong, James Thorne, Danqi Chen

View co-author network (8 people)

Loading graph…