Sifan Li

A Master's Student.

aportrait.jpg

104 Building Zheli

66 Chongshan Mid. Rd

Shenyang, Liaoning 110036

I am currently in the final year of my M.S. program at Liaoning University. I have previously been a visiting student at HKUST-GZ under the supervision of Dr. Bingzhuo Zhong, and at Peking University under the supervision of Dr. Hao Tang. I am now a research intern at vivo Co., Ltd. and the University of California, Merced, working under the supervision of Dr. Yiwei Wang.

My research interests include NLP, multimodal LLMs, human-like models, computer vision, Diffusion Models on T2I, Diffusion Models on LLM, efficient training and inference, multimedia quality assessment, controllable T2I, AIGC, world model, etc.

I am actively seeking Ph.D. opportunities.

news

Nov 07, 2025 The paper SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking is presented in A106-107 as an oral session in the Main Conference of EMNLP 2025 in Suzhou.
Oct 07, 2025 The paper SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking will be presented in A106-107 as an oral session in the Main Conference of EMNLP 2025 in Suzhou.
Aug 20, 2025 The paper SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking has been accepted to the Main Conference of EMNLP 2025.

latest posts

Sep 08, 2025 SemVink
Mar 26, 2025 a post with plotly.js
Dec 04, 2024 a post with image galleries

selected publications

  1. logos.png
    Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
    Sifan Li, Hongkai Chen, Yujun Cai, and 4 more authors
    2025
  2. semvink.png
    SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking
    Sifan Li, Yujun Cai, and Yiwei Wang
    2025
    Main Conference of EMNLP 2025.
  3. cpm.png
    Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs
    Sifan Li, Yujun Cai, Bryan Hooi, and 2 more authors
    2025
  4. replace.png
    Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image
    Sifan Li, Ming Tao, Hao Zhao, and 2 more authors
    2025