About Me

I am a PhD candidate at the Artificial Intelligence Applications Institute (AIAI), School of Informatics, University of Edinburgh, advised by Prof. Tiejun Ma. I previously completed an MRes at the Institute for Language, Cognition and Computation (ILCC), University of Edinburgh, advised by Prof. Shay Cohen.

My research focuses on algorithmic foundations for large language models and learning-to-rank / retrieval, and on how these advances can be translated into robust solutions for financial AI. Around this, my interests span:

1. LLM fundamental algorithms — developing training-free and efficient inference-time methods for controllable and reliable LLM behavior, especially attention steering under modern optimized kernels. { SEKA (ICLR 2026) }

2. Learning-to-rank and retrieval — designing ranking algorithms that better combine pairwise signals with global listwise structure for stronger and more stable ranking performance across domains. { TSPRank (KDD 2025), MATcH (EACL 2023) }

3. Financial AI applications — applying LLM and ranking breakthroughs to high-stakes financial tasks, including trader risk ranking and long-horizon evaluation of LLM-based investment strategies. { PA-RiskRanker (TOIS 2025), FINSABER (KDD 2026), SynthRank (AAAI 2024) }

I have multiple first-author papers at leading venues, including ICLR, KDD, TOIS, and EACL. Additionally, I have industrial experience as a researcher at Tencent Lightspeed Studio, Huawei Technologies Research & Development (UK) Ltd, and The Alan Turing Institute. I have also contributed to teaching several courses related to machine learning and natural language processing at the University of Edinburgh.

Overall, my work is driven by a single question: how to make algorithmic advances that matter, and how to deploy them reliably in high-stakes real-world decision-making.