Portrait of Hai-Long Sun

Hai-Long Sun

Hai-Long Sun in Chinese calligraphy
Bailing Multimodal Team Ant Group
School of Artificial Intelligence
Nanjing University
sunhl (at) lamda.nju.edu.cn

👀 About Me

I am currently with the Bailing Team at Ant Group. Prior to joining Ant Group, I received my M.Sc. degree from the School of Artificial Intelligence, Nanjing University, in 2026, under the supervision of Prof. Han-Jia Ye. During my graduate studies, I was a member of the LAMDA Group, led by Prof. Zhi-Hua Zhou.

Before that, I received my B.Sc. degree from the College of Computer Science & Technology, Nanjing University of Aeronautics and Astronautics, in June 2023 (GPA ranked 1 / 120). In the same year, I was admitted to the M.Sc. program at Nanjing University without entrance examination.

Beyond research, I am a National Level-II Tennis Athlete and former captain of both NUAA and NJU Tennis Teams.

Internship Opportunities

I am seeking highly self-motivated students for internships in multimodal foundation models. If interested, please email your resume and transcript to yimo.shl@antgroup.com.

📣 News

🌟 Research Interests

My research focuses on building capable and reliable learning systems, with an emphasis on multimodal foundation models and continual learning.

Multimodal Foundation Models Multimodal Agent and Coding Continual Learning

🚀 Selected Publications Google Scholar citations Google Scholar h-index Google Scholar i10-index GitHub stars

Representative work in multimodal reasoning, multilingual MLLMs, and continual learning. My name is highlighted in bold.

Full publication list
  1. TVC ACL
    Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning
    Hai-Long Sun, Zhun Sun, Houwen Peng, Han-Jia Ye.
    First Author
    ACL'25. CCF-A
    TVC GitHub stars
    Paper Project Page Huggingface
  2. Parrot ICML
    Parrot: Multilingual Visual Instruction Tuning
    Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye.
    First Author
    ICML'25. CCF-A
    Parrot GitHub stars
    Paper Code Project Page Huggingface
  3. PILOT SCIS
    PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
    Hai-Long Sun, Da-Wei Zhou, De-Chuan Zhan, Han-Jia Ye.
    First Author
    SCIS 2025. CCF-A
    PILOT GitHub stars PILOT citations
    Paper Code 中文解读
  4. MOS AAAI
    MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
    Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye.
    First Author
    AAAI'25. CCF-A
    MOS GitHub stars
    Paper Code
  5. EASE CVPR
    Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
    Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan.
    Student First Author
    CVPR'24. CCF-A
    EASE GitHub stars EASE citations
    Paper Code
  6. Survey IJCAI
    Continual Learning with Pre-Trained Models: A Survey
    Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan.
    Student First Author
    IJCAI'24. CCF-A
    Survey citations
    Top-3 Most Influential IJCAI Papers
    Paper Code 中文解读 Media
  7. Length-Adaptive Caption Generation with LLMs IJCAI
    Length-Adaptive Caption Generation with LLMs
    Hai-Long Sun, Qing-Guo Chen, Da-Wei Zhou, De-Chuan Zhan, Han-Jia Ye.
    First Author
    IJCAI'24 Workshop · SCICAP Challenge 2024
    Paper Challenge Page
View additional publications
  1. Ovis2.5 Technical Report
    Ovis2.5 Technical Report
    Ovis Contributors
    Technical Report
    Ovis GitHub stars Ovis citations
    Paper Code
  2. VLMEvalKit Technical Report
    VLMEvalKit: A Toolkit for Evaluating Large Vision-Language Models
    VLMEvalKit Contributors
    Technical Report
    VLMEvalKit GitHub stars VLMEvalKit citations
    Paper Code
  3. Insight-V CVPR
    Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
    Yuhao Dong, Zuyan Liu, Hai-Long Sun, Jingkang Yang, Winston Hu, Yongming Rao, Ziwei Liu.
    CVPR'25 (Highlight). CCF-A
    Insight-V GitHub stars Insight-V citations
    Paper Code
  4. TSPIN NeurIPS
    Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
    Yibo Wang, Hai-Long Sun, Guangda Huzhang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang
    NeurIPS'25. CCF-A
    Paper
  5. TURBO NeurIPS
    Multimodal Tabular Reasoning with Privileged Structured Information
    Jun-Peng Jiang, Yu Xia, Hai-Long Sun, Shiyin Lu, Qing-Guo Chen, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye
    NeurIPS'25. CCF-A
    Paper

🏆 Awards & Honors

👨‍💻 Experience

2026.03 — Present
Ant-Ling Ant Group

Ant Group

Bailing Team
2025.04 — 2026.02
Alibaba

Alibaba Token Hub · MaaS Team

Multimodal Research Intern
2024.10 — 2025.04
Hunyuan Tencent

Tencent · TEG

Hunyuan Research Intern
2024.03 — 2024.10
Alibaba

Alibaba · AIDC-AI Business

MLLM Research Intern
2022.08 — 2023.03
ByteDance

ByteDance

Data

🎯 Service

📮 Contact

For research discussions and internship applications, email is the best way to reach me.