CV
Education
- Ph.D. in Engineering, University of Cambridge, Oct 2022 – Jun 2026
- Machine Intelligence Laboratory, Peterhouse
- Supervised by Prof. Bill Byrne
- Research interests: Vision-Language models, Information retrieval, RL and reasoning models
- M.Eng & B.A. in Information and Computer Engineering, University of Cambridge, Oct 2018 – Jun 2022
- Courses: Statistical signal processing, Statistical machine learning, Deep learning for Sequenced Data, Computer vision, Optimizations, Computational neuroscience, Computer systems, Machine Learning, Information Theory and Coding, Signal and systems, Medical Imaging & 3D Computer Graphics, Business modules
Work Experience
Multimodal Large Language Model Research Intern – RedNote (Xiaohongshu), Mar 2025 – Present
- Develop techniques for detecting and filtering harmful or unsafe content to support content moderators and enhance social media platform safety and integrity.
- Develop reinforcement learning and preference optimization methods to fine-tune MLLMs for higher accuracy and more explainable decision-making process in content moderation.
- Contribute to internal research reports, model evaluation frameworks, and experimental design for assessing harmful content detection on multimodal (text-image) social media posts.
- Translated research on GRPO and curriculum learning into production, boosting model performance in small-sample scenarios and reducing edge-case failures.
AI Strategy Research Intern – Huawei Cambridge Research Centre (Institute of Strategic Research), May 2024 – Present
- Conduct research and produce strategic reports on emerging trends in artificial intelligence, with a focus on NLP, CV and Computer Graphics.
- Provide technical guidance on project planning and exploratory research initiatives within the AI research team.
- Co-organise workshops, challenges, sponsorship programs, and special sessions at conferences such as ECCV, WWW, BMVC, ECAI, and Eurographics.
- Support academic outreach initiatives by identifying and engaging with leading researchers globally to foster research collaboration.
AI Research Intern – Huawei Cambridge Research Centre (Kirin AI Solution), Jul 2022 – Jan 2023
- Researched and developed on-device efficient streaming automatic speech recognition (ASR) system.
- Applied compression techniques, like pruning or low rank adaptation to reduce the model parameters.
- Proposed and led research on a novel non-attention-based transformer architecture, achieving a 50% reduction in model size and computation along with a 60% decrease in end-to-end latency; secured a patent (EP4404187A1).
Deep Learning Research Intern – University of Cambridge Department of Engineering, Jun 2021 – Sep 2021
- Developed multimodal hateful speech detection systems leveraging pretrained visual-language models.
- Designed and implemented ensemble learning techniques to achieve state-of-the-art performance in hateful speech detection.
Deep Learning Research Intern – Shanghai Jiao Tong University, Sep 2020 – Dec 2020
- Researched fault-tolerant neural network architectures addressing resistance variation and bit-flip in ReRAM devices.
- Enhanced robustness through error-correction coding, Bayesian methods, and neural architecture search.
- Achieved over 30% improvement in robustness for image classification and object detection tasks, with results published in DAC 2021 and secured patent (CN113570056A).
Web Programmer – Jieqi Edge Computing, Jul 2019 – Sep 2019
- Developed websites using Jekyll to enhance efficiency and integrate features such as news updates, downloads, login functionality, comments, and discussion forums.
- Diagnosed and tested faulty PCBs, devising effective solutions to repair and restore functionality.
Publications
G. Yang, J. Chen, J. Mei, W. Lin, B. Byrne. "Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models." ACL 2026 Main.
J. Chen, J. Mei, G. Yang, B. Byrne. "BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering." arXiv preprint arXiv:2604.22678.
Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization.
J. Mei, J. Chen, G. Yang, X. Hou, M. Li, B. Byrne. "According to Me: Long-Term Personalized Referential Memory QA." arXiv preprint arXiv:2603.01990.
J. Mei, M. Sun, J. Chen, P. Qin, Y. Li, D. Chen, B. Byrne. "ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection." ICLR 2026.
J. Chen, G. Yang, W. Lin, J. Mei, B. Byrne. "On Extending Direct Preference Optimization to Accommodate Ties." NeurIPS 2025.
J. Mei, J. Chen, G. Yang, W. Lin, B. Byrne. "Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection." EMNLP 2025 Main (Oral).
J. Mei, J. Chen, W. Lin, B. Byrne, M. Tomalin. "Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning." ACL 2024 Main.
W. Lin*, J. Mei*, J. Chen*, B. Byrne. "PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-Modal Retrievers." ACL 2024 Main.
J. Chen, W. Lin, J. Mei, B. Byrne. "Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata." NAACL 2024 Main.
J. Mei, Z. Zhang. "Apparatus and Method for Streaming Automatic Speech Recognition." EP Patent EP4404187A1, 2024.
W. Lin, J. Chen, J. Mei, A. Coca, B. Byrne. "Fine-Grained Late-Interaction Multi-Modal Retrieval for Retrieval Augmented Visual Question Answering." NeurIPS 2023.
N. Ye*, J. Mei*, Z. Fang, Y. Zhang, Z. Zhang, H. Wu, X. Liang. "BayesFT: Bayesian Optimization for Fault Tolerant Neural Network Architecture." DAC 2021.
N. Ye, Z. Fang, J. Mei. "Method, System, Medium, and Electronic Device for Optimizing Fault-Tolerant Neural Network Structure." CN Patent CN113,570,056 A, 2021.
Academic Service
Supervision
- Co-supervision Cambridge Engineering MPhil in Machine Learning and Machine Intelligence (MLMI) student projects (2022–2026)
- Co-supervision Cambridge Engineering Undergraduate Research Opportunities Program (UROP) summer students (2024–2025)
- Co-supervision Cambridge Engineering MEng Fourth Year Project (2025–2026)
- Cambridge Engineering Medical Imaging & 3D Computer Graphics 3G4 paper (2022–2025)
- Cambridge Engineering Machine Learning 3F8 paper (2024–2025)
Teaching
- Designed, demonstrated, supervised, and assessed coursework and projects for MLMI 8 on Machine Translation and Visual Question Answering (2022–2025)
- Designed, demonstrated, supervised, and assessed coursework and projects for MLMI 8 on Large Language Model Applications (2025–2026)
Workshop Organising
- Co-organiser, Multimodal Information Retrieval Challenge, at Efficient Representation Learning for Multimodal Information Retrieval at WWW 2025
- Co-organiser, UK and Ireland Speech Workshop 2024
Reviewing
- ACL ARR Feb 2025, May 2025, July 2025, Jan 2026
- NeurIPS 2025, ICLR 2025, 2026, ICML 2026
Skills
- Deep Learning Frameworks: PyTorch, TensorFlow, Keras, JAX
- Programming: Python, Visual Basic, C++, JS
- Web & Typesetting: HTML, CSS, Ruby, Markdown, LaTeX
- Media: Adobe Lightroom, Premiere, Photoshop, After Effects
