Zikai Liao
Profile Photo

Zikai Liao

Graduate Student | Computer Science

I am currently a research assistant in Stony Brook University in the field of computer vision and multimodal learning, including generative AI, conversational agent, and object detection, advised by professor Zhaozheng Yin.

I obtained my Bachelor's degree at Chongqing University of Posts and Telecommunications in 2021, and my Master's degree at Xidian University under supervision of Zhangfang Hou.

Email Google Scholar Department of Computer Science, Stony Brook University

News

Jan 2026

BREAKING NEWS

Something drastic is taking place...

May 2025

Internship at Atmanity Inc. (Currently atmee.ai)

Honored to obtain an intern role at Atmanity Inc. as an intern research scientist on topics such as generative AI, conversational agents, audio-driven diffusion models.

Aug 2024

New life

Joining Computer Science Department of Stony Brook University as a PhD student for 24 Fall semester.

Publications

Journal Publications

"Differentiated Attention Guided Network over Hierarchical and Aggregated Features for Intelligent UAV sSurveillance"

Houzhang Fang, Zikai Liao (equal contribution), Xuhua Wang, Yi Chang, Luxin Yan

IEEE Transactions on Industrial Informatics, Vol. 19, No. 9, pp. 9909-9920, 2023

PDF DOI

Conference Publications

"DANet: Multi-scale UAV Target Detection with Dynamic Feature Perception and Scale-aware Knowledge Distillation"

Houzhang Fang, Zikai Liao (co-first author, equal contribution), Lu Wang, Qingshan Li, Yi Chang, Luxin Yan, Xuhua Wang

Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), pp. 2121-2130, 2023

PDF DOI

"Prior-BERT and Multi-Task Learning for Target-Aspect-Sentiment Joint Detection"

Cai Ke, Qingyu Xiong, Chao Wu, Zikai Liao, Hualing Yi

ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7817-7821, 2022

PDF DOI

"A Real-time Anti-distractor Infrared UAV Tracker with Channel Feature Refinement Module"

Houzhang Fang, Xiaolin Wang, Zikai Liao, Yi Chang, Luxin Yan

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1240-1248, 2021

PDF DOI

ArXiv Submissions

"Beyond Words: Multimodal LLM Knows When To Speak"

Zikai Liao, Yi Ouyang, Yi-Lun Lee, Chen-Ping Yu, Yi-Hsuan Tsai, Zhaozheng Yin

arXiv preprint arXiv:2505.14654, 2025

PDF DOI

Work Experience

Research Assistant

Department of Computer Science, Stony Brook University

Aug 2025 - Present
  • Developing and optimizing novel diffusion architectures and sampling strategies to improve generative performance and efficiency.
  • Building automated pipelines for large-scale dataset collection, cleaning, and multimodal alignment.
  • Writing papers for top-tier conferences like CVPR or NeurIPS and maintaining reproducible open-source codebases.
  • Collaborate with labmates on various projects.

Intern Research Scientist

Atmanity Inc.

Jun 2025 - Aug 2025
  • Architected and refined high-performance generative AI pipelines, focusing on multimodal fusion techniques and robust prototype iterations.
  • Conducted rigorous system profiling and hyperparameter tuning that enhanced training stability and reduced GPU memory consumption.
  • Collaborated in an agile environment to translate research prototypes into production-ready AI services.

Teaching Assistant

Department of Computer Science, Stony Brook University

Sep 2024 - May 2025
  • Creating and refining challenging algorithmic problems and comprehensive grading rubrics for assignments.
  • Leading weekly discussion sessions to explain complex topics like dynamic programming, graph theory, and NP-completeness.
  • Providing one-on-one guidance to help students debug logical fallacies and optimize the time complexity of their solutions.

Academic Activity

Conference Reviewer

  • NeurIPS (Conference on Neural Information Processing Systems)
  • CVPR (IEEE Conference on Computer Vision and Pattern Recognition)
  • ECCV (European Conference on Computer Vision)
  • ACM MM (ACM International Conference on Multimedia)

Journal Reviewer

  • IEEE Transactions on Industrial Informatics

Membership

  • Association for Computing Machinery (ACM)
  • Institute of Electrical and Electronics Engineers (IEEE)

Miscellaneous

Awards

  • Outstanding Graduate (2024)
  • National Scholarship for Master's Student (2023)
  • National Scholarship for Undergraduate Student (2019 & 2018)
  • Merit Student & Administrator (2021 & 2020 & 2019 & 2018)

Skills

Python PyTorch Multimodal Learning Computer Vision Machine Learning Data Science