👨‍🎓 About Me

Hi there! 👋 I’m a First Year PhD student at the University of California, Santa Barbara NLP Group, Department of Computer Science, advised by Dr. Eric Xin Wang. I graduated from the School of Engineering at the University of Liverpool.

My research interests lie in trustworthy AI and the algorithmic foundations of multimodal large models, with a focus on:

  • 🎯 Multimodal reasoning and visual grounding
  • 🛡️ Reliability and robustness of LLMs and VLMs
  • 🔍 Autonomous agent frameworks with self-evolution

I am always open to collaboration and the exchange of ideas. If you’d like to discuss potential research opportunities or simply connect, please don’t hesitate to reach out!

📧 Contact: chengzhi@ucsb.edu

📌 I'm always happy to collaborate with graduate/undergraduate students. Please drop me an email if you want to work with me!


🔥 News

2026.01 🎉 One paper is accepted by ICLR 2026 👉 Check our paper and project
2025.09 🎉 One paper is accepted by NeurIPS 2025 👉 paper | project
2025.04 🎉 One paper is accepted by ACL 2025 👉 paper
2025.04 🎉 One paper is accepted by CVPR 2025 👉 paper
2025.02 🎉 Two papers are accepted by ICLR 2025 👉 MSSBench & ANTRP
2025.01 🎉 One paper is accepted by AAAI 2025 Oral 👉 paper

📝 Selected Publications

Only (co-)first author papers are listed. See more on the Google Scholar.
(*indicates equal contribution)

ICLR 2026
EvoPresent

Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space

Chengzhi Liu *, Yuzhe Yang*, Yue Fan, Qinyue Wei, Sheng Liu, Xin Eric Wang

🌐 Project 📄 Paper 📢 Talk GitHub stars

ICLR 2026
EvoPresent

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

Chengzhi Liu *, Yuzhe Yang*, Kaiwen Zhou, Zhen Zhang, Yue Fan, Yanan Xie, Peng Qi, Xin Eric Wang

🌐 Project 📄 Paper GitHub stars

NeurIPS 2025
MLRM-Halu

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Chengzhi Liu*, Zhongxing Xu*, Qinyue Wei, Juncheng Wu, James Zou, Xin Eric Wang, Yuyin Zhou, Sheng Liu

🌐 Project 📄 Paper GitHub stars

ICLR 2025
MSSBench

Multimodal Situational Safety

Kaiwen Zhou*, Chengzhi Liu*, Xuandong Zhao, Anderson Compalas, Dawn Song, Xin Eric Wang

🌐 Project 📄 Paper GitHub stars

AAAI 2025 Oral
IMDR

Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis

Chengzhi Liu*, Zile Huang*, Zhe Chen, Feilong Tang, Yu Tian, Zhongxing Xu, Zihong Luo, Yalin Zheng, Yanda Meng

🌐 Project 📄 Paper

ICLR 2025
ANTRP

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

Feilong Tang*, Zile Huang*, Chengzhi Liu, Qiang Sun, Harry Yang, Ser-Nam Lim

📄 Paper GitHub stars


📖 Education

🎓

Ph.D. in Computer Science

University of California, Santa Barbara

2025.09 - 2030.06 (Expected)

🎓

Bachelor of Engineering

University of Liverpool, United Kingdom

2021.09 - 2025.07


🧑‍⚖️ Academic Services

Conference Reviewer:

AAAI 2025 ICLR 2026 ICML 2026 CVPR 2025 ARR 2026 TCSVT ICME 2024-26