Zijun Long

420

18 Lilybank Gardens, G12 8RZ

Glasgow, UK

Currently, I am a PhD candidate at the University of Glasgow, Terrier Team. My research primarily focuses on artificial intelligence (AI) for the development of novel multi-modal (text+image) learning techniques, with a particular emphasis on the research of large language models at the intersection of machine learning, computer vision, and natural language processing. My research track record is distinguished by 11 peer-reviewed full papers as first-author, published in prestigious conferences and journals, such as ECCV (h5-index 238, CORE A), SIGIR (h5-index 103, CORE A), ICRA (h5-index 122, CORE A*), ICASSP (h5-index 129). Significantly, I have shown a substantial increase in the number of citations, which has quadrupled compared to what I had in 2022. I am proficient in programming, including Python, C++. I possess extensive experience in large-scale data analysis and am proficient in numerous deep learning and data analysis frameworks, including scikit-learn, PyTorch, and Bayesian methods.

news

Jan 31, 2024	Happy to announce that our full paper is accepted by CORE A* IEEE International Conference on Robotics and Automation (ICRA 2024): ZIJUN LONG, George Killick, Richard McCreadie, Gerardo Aragon Camarasa. ‘RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models’
Dec 18, 2023	More good news with two papers accepted at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) headed up by us. MultiWay-Adapter: Adapting Multimodal Large Language Models for scalable image-text retrieval with ZIJUN LONG (PGR), George Killick (PGR), Richard Mccreadie, and Gerardo Aragon Camarasa LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers ZIJUN LONG (PGR), Richard Mccreadie, Gerardo Aragon Camarasa and Zaiqiao Meng

Jan 31, 2024

Happy to announce that our full paper is accepted by CORE A* IEEE International Conference on Robotics and Automation (ICRA 2024): ZIJUN LONG, George Killick, Richard McCreadie, Gerardo Aragon Camarasa. ‘RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models’

Dec 18, 2023

More good news with two papers accepted at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) headed up by us.

MultiWay-Adapter: Adapting Multimodal Large Language Models for scalable image-text retrieval with
- ZIJUN LONG (PGR), George Killick (PGR), Richard Mccreadie, and Gerardo Aragon Camarasa
LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers
- ZIJUN LONG (PGR), Richard Mccreadie, Gerardo Aragon Camarasa and Zaiqiao Meng

selected publications

MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval

Zijun Long , George Killick , Richard McCreadie , and 1 more author

In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) , 2023
RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models

Zijun Long , George Killick , Richard McCreadie , and 1 more author

In IEEE International Conference on Robotics and Automation (ICRA 2024) , 2023
LACVIT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers

Zijun Long , Richard McCreadie , Gerardo Aragon Camarasa , and 1 more author

In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) , 2023