CV

Education

• B.S. in Internet of Things Engineering, Beijing University of Posts and Telecommunications, 2022 - Present
  • GPA: 3.82/4.0 (Rank: 2/182)
  • Weighted Average: 91.29/100
  • English Proficiency: CET-6: 627

Research Experience

• 2025.08 - Present: Project Leader - “Chasing the Silver Bullet: An Inquiry into the Potential and Limits of Vibe-Coding”
  • Beijing University of Posts and Telecommunications
  • Independently designed and developed “Vibe Entropy” evaluation system
  • Exploring optimal theoretical boundaries of Vibe-Coding
• 2025.05 - 2025.07: Fourth Author - “TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models”
  • Beijing University of Posts and Telecommunications
  • Proposed visual feature reuse method for VLA models
  • Validated feasibility through experiments considering locality principle
• 2025.01 - 2025.05: Co-first Author - “MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and Feature Enhancement”
  • Beijing University of Posts and Telecommunications
  • Proposed MSNav, a modular framework with dynamic topological memory
  • Responsible for all experimental implementation and paper writing
• 2024.09 - 2025.02: Project Leader - “VLA Strategy Guidance Based on the Process Reward Model”
  • Beijing University of Posts and Telecommunications
  • Proposed independent process reward model for VLA guidance
  • Designed overall architecture and verified through virtual simulation

Skills

• Programming Languages: Python, C, C++, Java
• Machine Learning: PyTorch, TensorFlow, Scikit-learn
• Research Areas: Multimodal Models, Embodied AI, Computer Vision
• Tools: Linux, Git, Jupyter Notebook, LaTeX

Publications

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

Jian Zhao, Runze Liu, Kaiyan Zhang, Zhimu Zhou, Junqi Gao, Dong Li, Jiafei Lyu, Zhouyi Qian, Biqing Qi, Xiu Li, Bowen Zhou. (2025). "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning." arXiv preprint arXiv:2505.15825.

TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models

Chenghao Liu, Jiachen Zhang, Chengxuan Li, Zhimu Zhou, Songfang Huang, Huiling Duan. (2025). "TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models." Under Review. (Fourth Author)

MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and Feature Enhancement

Chenghao Liu*, Zhimu Zhou*, Jiachen Zhang, Minghao Zhang, Songfang Huang, Huiling Duan. (2025). "MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and Feature Enhancement." Under Review. (*Co-first Author, randomly ordered by dice rolling)

Talks

Teaching

Awards and Honors

• 2024: First Prize, IC Innovation Contest (MIIT) - National No. 1
• 2024: Xiaomi Social Scholarship (Only 1 in Major, BUPT)
• 2023-2024: Second-Class Scholarship (Major Top 10%, BUPT)
• 2024: First Prize, China Innovation and Entrepreneurship Competition Beijing (Provincial Top 10%, Ministry of Education)
• 2024: Second Prize, Computer Design Competition (Provincial Top 15%, Ministry of Education)

Service and leadership

• Undergraduate Research Assistant, Beijing University of Posts and Telecommunications
• Project Leader for multiple research initiatives
• Active contributor to open-source machine learning projects