Cheng Zhang | 张 诚

Cheng Zhang | 张 诚

Second year graduate student at HUST.

About me

I’m currently studying at Huazhong University of Science and Technology, under the supervision of Prof. Xiang Bai. My current research interests are mainly in Multi-modal Large Language Models (MLLMs), embodied AI, and 3D vision. I work closely with Dingkang Liang at HUST VLRLab.

Less is more, slow is fast.

🔍 Research Interests

  • 3D Multimodal Large Language Models (3D MLLMs)
  • Embodied AI
  • 3D Vision

🔥 News

  • [2025/11/8] 🎉 One paper is accepted by AAAI2026 as oral presentation!
  • [2024/4/20] Open personal website.

📝 Publicaitons

* Equal Contribution, † Corresponding Author

toc3d

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution

AAAI 2026 (oral)

Dingkang Liang*, Cheng Zhang*, Xiaopeng Xu, Jianzhong Ju, Zhenbo Luo, Xiang Bai

Introduces a new task that challenges agents to generate efficient, 3D grounded action schedules guided by operations research principles.

toc3d

Make Your ViT-Based Multi-view 3D Detectors Faster via Token Compression

ECCV 2024

Dingyuan Zhang, Dingkang Liang, Zichang Tan, Xiaoqing Ye, Cheng Zhang, Jingdong Wang, Xiang Bai

An efficient sparse query-based multi-view 3D detector for autonomous driving.

toc3d

MMATrans: Muscle Movement Aware Representation Learning for Facial Expression Recognition via Transformers

IEEE Transactions on Industrial Informatics (TII), 2024

Hai Liu, Qiyun Zhou, Cheng Zhang, Junyan Zhu, Tingting Liu, Zhaoli Zhang, You-Fu Li

toc3d

Orientation Cues-aware Facial Relationship Representation for Head Pose Estimation via Transformer

IEEE Transactions on Image Processing (TIP), 2023

Hai Liu, Cheng Zhang†, Yongjian Deng, Tingting Liu, Zhaoli Zhang, You-Fu Li†

toc3d

TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers

CVPR 2023

Cheng Zhang, Hai Liu, Yongjian Deng, Bochen Xie, Youfu Li

toc3d

TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification

IEEE Transactions on Multimedia (TMM), 2023

Hai Liu, Cheng Zhang†, Yongjian Deng, Bochen Xie, Tingting Liu, Zhaoli Zhang, You-Fu Li†

toc3d

Affinity Relation-aware Fine-grained Bird Image Recognition for Robot Vision Tracking via Transformers

IEEE International Conference on Robotics and Biomimetics (ROBIO), 2022

Hai Liu, Cheng Zhang†, Bochen Xie, Tingting Liu, Qingsong Xu, You-Fu Li†

See full publication list on Google Scholar ->

📘 Research Experience

VLRLab, Huazhong University of Science and Technology, Wuhan

Member

  • Advisor: Xiang Bai
  • Research Topics: 3D Multimodal Large Language Models, Embodied AI
Sep 2024 - Current

National Engineering Research Center for E-Learning, Central China Normal University, Wuhan

Research Assistant

  • Advisor: Hai Liu
  • Research Topics: Head Pose Estimation, Fine-grained Image Classification, Facial Expression Recognition
Sep 2022 - Jun 2024

🏅 Honors and Awards

Graduate Academic First-Class Scholarship, 10,000RMB

Huazhong University of Science and Technology

Oct 2024

National Scholarship (Top 0.2%, Undergraduate), 10,000RMB

Central China Normal University

Oct 2023

Patents

一种基于 Transformer 网络的学习专注度监测方法

国家发明专利，中国，专利号：202211596338.9

刘海、张诚、刘婷婷、张昭理、朱晓倩、宋林森、林丹月、王镜淇

Nov 2025

一种基于多模态数据融合的在线学习状态检测方法

国家发明专利，中国，专利号：202211596371.1

刘海、林丹月、刘婷婷、张昭理、王镜淇、张诚、朱晓倩、宋林森

Nov 2025

一种基于特征交互学习网络的学生心理状态检测方法

国家发明专利，中国，CN116172556A

刘海、朱晓倩、刘婷婷、张昭理、宋林森、林丹月、王镜淇、张诚

Nov 2025

一种基于人体姿态估计的动态课堂签到方法

国家发明专利，中国，CN116311572A

刘海、王镜淇、刘婷婷、张昭理、张诚、朱晓倩、宋林森、林丹月

Nov 2025

一种基于双相机多分支网络的虚拟现实教学手势识别方法

国家发明专利，中国，CN116466816A

刘海、宋林森、刘婷婷、张昭理、林丹月、王镜淇、张诚、朱晓倩

Nov 2025

📖 Educations

Huazhong University of Science and Technology

Graduate Student, Pursuing Master’s degree in Software Engineering

Sep 2024 - Current

Central China Normal University

Bachelor of Engineering in Artificial Intelligence

Jun 2024

IELTS: 7.5

Listening-8.0; Speaking-6.0; Reading-8.5; Writing-6.5

Apr 2023

GRE: 324

Verbal-155; Quantitative-169; Analytical Writing-3.0

Jul 2023

CET 6

Overall-587

May 2022

🎓 Academic Service

Reviewer: NeurIPS 2024, AISTATS 2025, ICML 2025, AAAI 2026, ICLR 2026

💼 Internship

I am now available on the job market.

Homepage Gallery Personal Posts Google Scholar Profile Curriculum Vitae