This programme supports research on AI, Government and Policy.
Yushi Yang
DPhil Student
Yushi Yang
DPhil Student
Yushi is a third-year DPhil student in Social Data Science at the OII, where she is a member of the Reasoning with Machines Lab (OxRML) under the supervision of Prof. Adam Mahdi. Her research focuses on post-training mechanisms for aligning language model agents, in particular how reinforcement learning and preference tuning methods align model behaviours with human values. Her work spans LLM post-training, Agents, and AI alignment, and has been published at venues including EMNLP and ICML.
Alongside her doctoral research, Yushi joined Meta Superintelligence Labs as a Research Scientist Intern. She has previously worked as an AI Engineer at Reply, a Data Analyst at UNDP, and an AI Researcher at the University of Oxford and Imperial College London.
Yushi holds an MSc in Artificial Intelligence from Imperial College London, an MSc in Statistical Science from the University of Oxford, and a BSc in Mathematics and Statistics from the University of Warwick.
LLM Post-training; Agents; AI alignment; Reinforcement learning
This programme supports research on AI, Government and Policy.
31 October 2025
Researchers, including those from the Oxford Internet Institute’s Reasoning with Machine’s Lab (OxRML), will attend the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) in Suzhou, China from 4-9 November.
16 December 2024
Ten Oxford Internet Institute (OII) DPhil students have received Dieter Schwarz Foundation (DSF) funding to enable them to begin 12-month AI- related research projects during the course of their studies.
6 December 2024
Several researchers and DPhil students from the Oxford Internet Institute, University of Oxford, will head to Vancouver for the Thirty-Eighth annual Conference on Neural Information Processing Systems (NeurIPS) from 10-15 December 2024.
