Zhenyi's Website

A brief self-intro

I am a first-year PhD student at King’s College London (2024-2028). I am supervised by Prof. Yulan He. My current research interests focus on Natural Language Reasoning and Multimodal Learning in NLP.

I worked as a Speech Synthesis Research at iFLYTEK and a Computer Vision Engineer at Zhuofan. Before that I completed my MEng degree (2016-2020) in Electrical and Electronic Engineering at Imperial College London with a First Class Honour.

Publications

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Zhenyi Shen, Hanqi Yan, Linhai Zhang, Zhanghao Hu, Yali Du, Yulan He

Under Review | paper

Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning

Hanqi Yan, Linhai Zhang, Jiazheng Li, Zhenyi Shen, Yulan He

ICML 2025 | paper

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering

Zhanghao Hu, Hanqi Yan, Qingling Zhu, Zhenyi Shen, Yulan He, Lin Gui

Under Review | paper

Hi, I am Zhenyi Shen 沈振翼

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering