Songlin Fan

About Me （范松林）

I am a Postdoctoral Fellow jointly affiliated with China Mobile (Shanghai) Industrial Research Institute and Fudan University. I received my Ph.D. in 2024 from the School of Computer Science, Peking University, and spent five years as a research intern at Peng Cheng Laboratory. My research lies at the intersection of multimodal learning and computer vision, with a particular emphasis on 3D data processing and analysis.

😊I am deeply driven by a passion for scientific innovation and a strong commitment to lifelong learning. 🤝Feel free to reach out for potential collaborations or academic discussions.

Research Interests

• Computer Vision: self-supervised pretraining, segmentation, saliency, quality assessment, compression
• Multimodal Learning: multimodal large language model, vision-language-action

News

• [Nov. 2025] 🔥🔥Our paper about OCR is accepted to AAAI 2026.
• [Jul. 2025] Our paper about compression is accepted to TPAMI 2025.
• [Apr. 2025] Our paper about quality assessment is accepted to IJCAI 2025.
• [Mar. 2025] Our paper about visaul detection is accepted to NAACL 2025.
• [Jan. 2025] Our paper about quality assessment is accepted to AAAI 2025.
• [Oct. 2024] Our paper about self-supervised pretraining is accepted to TNNLS 2024.

Selected Publications

Services

Conference Reviewers

• ACM International Conference on Multimedia (ACM MM)
• IEEE International Conference on Multimedia and Expo (ICME)
• Data Compression Conference (DCC)
• IEEE International Symposium on Circuits and Systems (ISCAS)

Journal Reviewers

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Powered by Jekyll and Minimal Light theme.