🧑‍🔬 Zhenguang Cai

🏛️ Affiliations

🎓Chinese University of Hong KongHong Kong · Hong Kong2017–2026 · 115 papersEmployment since 2018current🎓University of East AngliaNorwich · United Kingdom2016–2021 · 10 papers🎓University College LondonLondon · United Kingdom2014–2017 · 9 papersEmployment 2014–2015Employment 2015–2016🎓University of ManchesterManchester · United Kingdom2011–2016 · 7 papersEmployment 2011–2012🎓University of PlymouthPlymouth · United Kingdom2013–2014 · 4 papers🎓University of EdinburghEdinburgh · United Kingdom2007–2012 · 4 papersEducation 2007–2011🏥Prince of Wales HospitalShatin · China2023 · 2 papers🎓Guangdong University of Foreign StudiesGuangzhou · China2005–2007Employment 2005–2007

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Topics

🧠 Language models & pretraining (1)🧒 Psycholinguistics & language acquisition (1)🔬 Interpretability (1)🖼️ Vision & language (1)

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability (2025 · 8 citations)
   Large language models often respond like people in psycholinguistic experiments, but it remains unclear which internal units support these abilities.
2. Similar Predictions, Different Processes: A Multi-Level Comparison of Human and Multimodal LLM Language Prediction (2026)
   This study asks whether a multimodal LLM that hears speech and sees images resembles humans only in which referent it anticipates, or also in when that anticipation arises.

Also in our library

2 more works of theirs are in our library without a page here yet; they will appear as we publish them.

🔗 Cited by

Papers of our library cite their works 40 times (of the 140,884 papers whose bibliographies we read); 2 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhenguang-cai/