Zifan Song

---

I am a Ph.D candidate in Computer Science and Technology at Tongji University, advised by Prof. Cairong Zhao and Guosheng Hu. Prior to this, I obtained my bachelor degree in Computer Science and Technology from Tongji University. After an unforgettable internship in OpenMMLab at Shanghai AI Laboratory (working with Dr. Wenwei Zhang and Yudong Wang), my current research interests lie in Multimodal Learning, Data-centric AI, and LLM Fine-tuning.

News

---

• [2024/09] 2 Papers on LLM Fine-tuning (AlchemistCoder) and Video Understanding (Open-Vocabulary Online Action Detection) are accepted by Advances in Neural Information Processing Systems, NeurIPS 2024.
• [2024/08] I have been invited to serve as a Reviewer for International Conference on Learning Representations, ICLR 2025.
• [2024/05] 1 Paper on LLM Pre-training (Code Needs Comments) is accepted by Annual Meeting of the Association for Computational Linguistics, ACL 2024.
• [2023/12] 1 Paper on Multimodal Learning (Diverse Person) is accepted by Proceedings of the AAAI Conference on Artificial Intelligence, AAAI 2024.
• [2023/08] 1 Paper on Graph Application (Scene-Pedestrian Graph) is accepted by IEEE Transactions on Industrial Informatics, IEEE TII.
• [2023/07] 1 Paper on Training Paradigm (Deep Perturbation Learning) is accepted by International Conference on Machine Learning, ICML 2023.

Publications

---

AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data

Zifan Song*, Yudong Wang*, Wenwei Zhang*, Kuikun Liu, Chengqi Lyu, Demin Song, Qipeng Guo, Hang Yan, Dahua Lin, Kai Chen, Cairong Zhao

Advances in Neural Information Processing Systems, NeurIPS 2024

[📃 Paper] [👨‍💻 Code] [🌐 Project Page] [🤗 HuggingFace]

Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?

Qingsong Zhao, Yi Wang, Jilan Xu, Yinan He,

Zifan Song, Limin Wang, Yu Qiao, Cairong Zhao

Advances in Neural Information Processing Systems, NeurIPS 2024

[📃 Paper]

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang,

Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

Annual Meeting of the Association for Computational Linguistics, ACL 2024

[📃 Paper]

Diverse Person: Customize Your Own Dataset for Text-Based Person Search

Zifan Song, Guosheng Hu, Cairong Zhao

Proceedings of the AAAI Conference on Artificial Intelligence, AAAI 2024

[📃 Paper] [👨‍💻 Code]

Learning Scene-Pedestrian Graph for End-to-End Person Search

Zifan Song, Cairong Zhao, Guosheng Hu, Duoqian Miao

IEEE Transactions on Industrial Informatics, IEEE TII 2023

[📃 Paper] [👨‍💻 Code]

Deep perturbation learning: enhancing the network performance via image perturbations

Zifan Song, Xiao Gong, Guosheng Hu, Cairong Zhao

International Conference on Machine Learning, ICML 2023

[📃 Paper] [👨‍💻 Code]

Pre-Prints

---

InternLM2 Technical Report

InternLM Group

ArXiv 2024

[📃 Paper] [👨‍💻 Code] [🌐 Website]

Industry

---

Education

---

Connections

---

Shuguang Dou, Junyao Gao, Zefan Qu, Yuanpeng Tu, Yubin Wang, Siyuan Li, Yudong Wang, Wenwei Zhang