cv
Academic CV, generated from the latest structured CV data.
About Me
Sifan Li
Ph.D. Candidate in Computer Science
sflijohn@foxmail.com | johnnyzeppelin.github.io | github.com/johnnyZeppelin | scholar:Gc1bAVwAAAAJ
I am currently a Ph.D. candidate at the Institute of Computing Technology, Chinese Academy of Sciences, under the supervision of Prof. Shenghua Liu and Prof. Yiwei Wang. I am also an assistant researcher in AI4Science at Shanghai AI Lab and a research intern at the University of California, Merced, working under the supervision of Prof. Yiwei Wang. My research interests include NLP, multimodal LLMs, VLMs, AI interpretability, agentic systems, reinforcement learning, AI4Science, efficient training, and computer vision.
Employments
-
2026.04 - Present Assistant Researcher in AI4Science
Shanghai Artificial Intelligence Laboratory
Research on AI4Science and foundation-model systems.
-
2025.06 - 2026.04 Assistant Algorithm Engineer in NLP
vivo Mobile Communication Co., Ltd.
Research and engineering work on large language models and NLP applications.
-
2024.09 - Present Research Intern
University of California, Merced
Advised by Prof. Yiwei Wang.
- Published SemVink at the EMNLP 2025 Main Conference.
-
2024.06 - 2025.06 -
2023.12 - 2024.12 Research Assistant
Hong Kong University of Science and Technology (Guangzhou)
Advised by Prof. Bingzhuo Zhong, Dr. rer. nat.
Education
-
2026.09 - Present Doctor of Philosophy
Institute of Computing Technology, Chinese Academy of Sciences
Computer Science
-
2023.09 - 2026.06 -
2017.09 - 2021.06
Publications
-
2026.05.31 -
2026.02.13 -
2026.01.22 -
2026.01.01 TFFN: Three-Branch Feature Fusion Network for Stereoscopic Omnidirectional Image Quality Assessment
IEEE Transactions on Multimedia
Early Access; first student author
-
2026.01.01 MMIFN: A Multi-Modal Interactive Fusion Network for Omnidirectional Image Quality Assessment
IEEE Transactions on Multimedia
Early Access; first student author
-
2025.11.01 SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
EMNLP 2025 Main Conference
Oral presentation
-
2025.10.14 -
2025.10.10 -
2025.09.01 BPGI: A Brain-Perception Guided Interactive Network for Stereoscopic Omnidirectional Image Quality Assessment
IEEE Open Journal on Immersive Displays
First student author
-
2025.05.21 -
2025.03.17 Multi-Task Guided No-Reference Omnidirectional Image Quality Assessment With Feature Interaction
IEEE Transactions on Circuits and Systems for Video Technology
First student author
-
2024.01.01 A Multimodal Fake News Detection Model with Self-supervised Unimodal Label Generation
Advanced Intelligent Computing Technology and Applications
Conference chapter
-
2024.01.01 Image Aesthetics Assessment Based on Visual Perception and Textual Semantic Understanding
Digital Multimedia Communications
Conference chapter
Academic Service
-
2027.01 - 2027.12 -
2026.01 - 2026.12 -
2026.01 - 2026.12 -
2026.01 - 2026.12 -
2026.01 - 2026.12 -
2025.01 - 2025.12