Jun Gao (高俊) is a third-year master’s student at Soochow University supervised by Prof. Ziqiang Cao. Before graduation, I was a research assistant working for Prof. Wenjie Li at the NLP Group of The Hong Kong Polytechnic University. I also joined the LINS Lab of Westlake University as a visitor fortunately supervised by Prof. Tao LIN. Please check my CV for further information.

Outside of research, I excel in cycling 🚴, taekwondo 🥋, running 🏃, badminton 🏸, and basketball 🏀

Research

I am broadly interested in Natural Language Processing and Multidomal Fusion. My current research focuses on:

• (1). How to prompt large models efficiently.
• (2). How to help large models understand our beautiful worlds faithfully.

😀If you are interesed with me, please feel free to drop me an e-mail.

News

[2024. 12] Got a paper accepted by AAAI 2025.

[2024. 10] I joined the LINS Lab of Westlake University as a visitor.

[2024. 8] Got a paper accepted by Information Procession & Management (IP&M).

[2024. 7] Started my RA life. Co-working with Postdoc‌. Yongqi Li

[2024. 7] Heading to IJCNN 2024. Japanese beer and sashimi are delicious.

[2024. 4] I got an RA offer to work for Prof. Wenjie Li starting from July.

[2024. 4] I was invited by IJCNN to chair the Large Neural Network Session in July.

[2024. 2] My first paper was accepted by IJCNN 2024 (oral). Welcome to have a chat in Yokohama!

[2022. 9] Started my Master’s study at the SudaNLG, Soochow University, supervised by Prof. Ziqiang Cao.

Publications

Most recent publications on Google Scholar.

* indicates equal contribution

• Interleaved-Modal Chain-of-Thought (Arxiv)

  Jun Gao, Yongqi Li, Ziqiang Cao, Wenjie Li

• AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning (AAAI 2025)

  Jun Gao, Qian Qiao, Ziqiang Cao, Zili Wang, Wenjie Li

• SelfCP: Compressing over-limit prompt via the frozen large language model itself (Information Processing & Management)

  Jun Gao, Ziqiang Cao, Wenjie Li

• DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training (ACM MM 2024)

  Yu Xie^*, Qian Qiao^*, Jun Gao, Tianxiang Wu, Shaoyao Huang, Jiaqing Fan, Ziqiang Cao, Zili Wang, Yue Zhang, Jielei Zhang, Huyang Sun

• Unifying Demonstration Selection and Compression for In-Context Learning (Arxiv)

  Jun Gao, Qi Lv, Ziqiang Cao, Wenjie Li

• Contrastive Learning with High-Quality and Low-Quality Augmented Data for Query-Focused Summarization ( ICASSP)

  Shaoyao Huang, Ziqiang Cao, Luozheng Qin, Jun Gao, Jun Zhang

• Guiding ChatGPT to Generate Salient Domain Summaries (IJCNN(oral))

  Jun Gao, Ziqiang Cao, Shaoyao Huang, Luozheng Qin, Chunhui Ai

Services

Reviewer: ARR 2024 Feb/April/June/Aug, IJCNN, IP&M

Chair: IJCNN 2024 Large Neural Network Session