Hello! I’m Weixiong Lin (林玮雄).

I’m an algorithm researcher of TikTok Search Department. The vision is to develop general multi-modal technologies for various applications with global influence (tiktok, lemon8, etc), such as superlarge-scale pre-training for image/text/video contents, guided with reinforcement learning.

Before that, I explore with some outstanding researchers from Future Living Laboratory (未来生活实验室), Alibaba, working to develop large-scale searching & question-answering system (拍立淘), one of the largest visual/multi-modal application scenarios in China.

I am fortunate to be advised by Prof. Weidi Xie(海外优青) and Prof. Ya Zhang(国家万人), also collaborating with Prof. Yanfeng Wang(人工智能学院院长) in MediaBrain Group, Shanghai Jiao Tong University.

Email: wx_lin[at]outlook[dot]com / wx_lin[at]alumni[dot]sjtu[dot]edu[dot]cn   Google Scholar: Citations 700+, H-index 5, I10-index 5

🔥 News

• Our new work, Squeeze Out Tokens from Sample for Finer-Grained Data Governance is out!
• Our new work, Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training is out!

💻 Researches

My research interest lie in

• Representation Learning: Alignment Pre-Training, Efficient Adaptation/Fine-Tuning.
• Multi-Modal Foundation Model: Data Synthesis, Knowledge Injection.
• Data Governance/Flywheel & Mining: Clean/Compress/Distill/Synthesize Data, Cross-Modal Retrieval/Recommendation/Advert.

As a young researcher, your interest and kind citation will definitely mean a lot for me and my collaborators.

Also feel free to reach me if you are seeking any form of cooperation.

📝 Publications

⚡️ Data-efficient Large-scale Pretraining

• preprint Squeeze Out Tokens from Sample for Finer-Grained Data Governance
  Weixiong Lin, Chen Ju, Haicheng Wang, Shengchao Hu, Shuai Xiao, et al.
• CVPR 2025 Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training | Project & Code
  Haicheng Wang, Chen Ju, Weixiong Lin, Shuai Xiao, et al.
• ICASSP 2025 Contrast and Unity for Partially-Supervised Temporal Sentence Grounding
  Haicheng Wang, Chen Ju, Weixiong Lin, Jinxiang Liu, Chaofan Ma, Ya Zhang, Yanfeng Wang

📚 Multimodal Large Language Models

• MICCAI 2023 PMC-CLIP: Contrastive Language-Image Pre-training Using Biomedical Documents
  Weixiong Lin*, Ziheng Zhao*, et al.
• JAMIA PMC-LLaMA: toward building open-source language models for medicine
  Chaoyi Wu*, Weixiong Lin*, et al.
• Nature Communication Towards Building Multilingual Language Model for Medicine
  Pengcheng Qiu, Chaoyi Wu, Xiaoman Zhang, Weixiong Lin, et al.
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
  Xiaoman Zhang, Chaoyi Wu, Ziheng Zhao, Weixiong Lin, et al.
• Can GPT-4V (ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis
  Chaoyi Wu, Jiayu Lei, Qiaoyu Zheng, Weke Zhao, Weixiong Lin, et al.

🗞 Academics and Communications

• I am fortunate to meet many interesting people & Team:

1. University System.   SJTU: Chaoyi Wu, Xiaoman Zhang, Haicheng Wang, Jinxiang Liu, Yue Hu, Chaoqin Huang, Aofan Jiang, Chen Gong.   ZJU: Yuheng Jiao.   USTC: Zuan Gao.
2. Shanghai AI Lab.  Pencheng Qiu, Yiqiu Guo, Shengchao Hu, Wanru Zhao, Yao Zhang, Xiao Zhou, Jiayu Lei, Qiaoyu Zheng, Weike Zhao, Ziheng Zhao.
3. Alibaba.  TAO Technology: Chen Ju, Shuai Xiao, Zida Cheng, Mengting Chen, Xuewen Hong, Yixuan Huang, Lianyu Du, Hao Yan.
4. Huawei.  Peisen Zhao, Maosen Li
5. Apple.   Jinge Yao
6. MSRA.  Bin Zhu
7. Hardware Company.   NVIDIA: Yangheng Zhao, Jiahui Liu, Yifan Zhou  Intel: Yujie Pan

📖 Educations

• 2022 - 2025, Graduate Student, Shanghai Jiao Tong University, Shanghai, China
• 2018 - 2022, Undergraduate, Shanghai Jiao Tong University, Shanghai, China

🎖 Honors and Awards

• 2024.10 MICCAI Young Scientist Publication Impact Award (Finalist)
• 2022.10 Zhiyuan Scholarship (Top 1%)
• 2021.10 Zhiyuan Scholarship (Top 1%)
• 2021.09 Finalist Prize in MCM Competition (Top 1%)