Scholar
Guangzhi Sun
Google Scholar ID: PzPAzf8AAAAJ
University of Cambridge
Citations & Impact
Citations
1,672
H-index
17
i10-index
22
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Paper 'Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?' accepted at EMNLP 2025 main conference
- - Paper 'SkillAggregation' accepted at ACL 2025 main conference
- - Papers 'video-SALMONN-o1', 'CASE-Bench', and 'F-16' accepted at ICML 2025
- - 1 paper accepted at ICLR 2025, and 1 paper accepted at NAACL 2025
- - 1 paper accepted at ICASSP 2025
- - Paper 'CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models' accepted at NeurIPS 2024 Workshop
- - Journal 'Large Language Models Surpass Human Experts in Predicting Neuroscience Results' published at Nature Human Behaviour
- - Won Best Short Paper Award at CUI 2024
- - 4 papers accepted at Interspeech 2024
- - Paper 'Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents' accepted at CUI 2024
- - Paper 'av-SALMONN: Speech-Enhanced Audio-Visual Large Language Models' accepted at ICML 2024
- - 4 papers accepted at ICASSP 2024
- - Journal 'Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator' published
- - Paper 'SALMONN: Towards Generic Hearing Abilities for Large Language Models' accepted at ICLR 2024
Research Experience
- - Junior Research Fellow at Trinity College, University of Cambridge starting from October 2024
- - Research Associate at the Machine Intelligence Laboratory, University of Cambridge, working with Prof. Phil Woodland
- - Closely collaborating with Prof. Chao Zhang at Tsinghua University
- - Research Internship at Google Brain with Dr Yu Zhang in 2019
- - Research Internship at ByteDance with Dr Wei Li in 2023
- - Collaborated with Poly AI Ltd working with Dr Ivan Vulić and Dr. Paweł Budzianowski in 2023
Education
- - Ph.D., June 2023, University of Cambridge, supervised by Prof. Phil Woodland (advisor Prof. Mark Gales)
- - B.A. and M.Eng, 2019, Trinity College, University of Cambridge
Background
- - Research Interest: Controllable and reliable multimodal conversational AI, including multi-modal contextual knowledge integration, reliability, hallucination reduction, and multimodal contextualised AI safety
- - Professional Fields: Speaker diarisation, language modelling, and speech synthesis
Co-authors