Jiahui Liu

Jiahui Liu

Central South University

Hi there! I’m Jiahui Liu 👋

Junior at Central South University (CSU) Aspiring AI Researcher

I am dedicated to pushing the boundaries of how machines perceive and reason about the world. Driven by a passion for Artificial Intelligence, I aim to bridge the gap between multimodal perception and complex reasoning.

🔍 Research Interests

Previously, under the mentorship of Yishuo Cai, I focused on MLLM Reasoning, with a specific emphasis on “Thinking with Images” — exploring how multimodal models can move beyond simple recognition to deep visual cognition.

🚀 Future Horizons

My current interests lie in developing AI systems that can reason and learn from the visual world. I am particularly excited about:

  • 👁️ Vision-Centric Reasoning — multimodal reasoning beyond purely linguistic chains of thought, where visual states, spatial structures, and visual primitives become part of the reasoning process.
  • 🎨 Deep Generative Models — understanding how generative models learn, represent, and synthesize complex data distributions.
  • 🎬 Video Generation & World Models — exploring video generation as a path toward learning dynamics, causality, and physical knowledge from visual experience.

📫 Let’s Connect!

I’m always open to collaborating on innovative projects or just having a chat about the future of AI. Feel free to reach out!

🖨️ Preprints & In Submission

📖 Educations

  • 2023.09 - Present, Undergraduate, School of Computer Science and Engineering, Central South University, Changsha, China. Majoring in Data Science and Big Data Technology.