👋 Hi! I'm Hetong Wang.
My name is 王鹤童 in Chinese. Feel free to call me Hetong
or Erika
alternatively!
My ultimate research goal is to build a general-purpose model that could go beyond imitation and simple memorization, i.e. perform as intelligent agents, who can learn new strategies from few but essential data, e.g. task description and instruction, rules and interaction with the environment.
Meanwhile, I found (1) the interpretability of deep neural models, (2) data and parameter efficient skill discovery and alignment methods, (3) cross-lingual and Out-Of-Distribution(OOD) generalisation, are interesting topics that could lead me towards the grand goal.
Moreover, formulating and explaining deep learning through the lens of information theory attracted and inspired me a lot, I am excited to discuss this topic with folks who interested as well!
About
I am currently a research intern at TsinghuaNLP, under the supervision of Prof. Zhiyuan Liu. Here, I focus on scalable oversight problems and self-alignment approaches to create less data hungry LLMs. I obtained my master in Artificial Intelligence at The Univerisity of Edinburgh, where I am fortunately advised by Prof. Edoardo Ponti and Dr. Pasquale Minervini. Before that, I obtained my bachelor in Computer Science at The University of Liverpool, working closely with Prof. Gabriella Pizzuto under the supervision of Prof. Andy Cooper, with a research focus on Reinforcement Learning. Please check my CV here.
news
May 15, 2024 | 🎉 Our paper Probing the Emergence of Cross-lingual Alignment during LLM Training is accepted at ACL 2024! |
---|---|
May 1, 2024 | 👩🏻🎓 I am actively looking for PhD position start by 25 spring/fall! |
Jan 12, 2024 | 🗣️ I gave a talk on AI self-alignment at THUNLP&OpenBMB Lab. Check the recording here (in Manderin Chinese). |
Dec 20, 2023 | 📍 I start my research internship on-site at Tsinghua University, Bejing. |