Zhiming Liu

Zhiming Liu

HITSZ

Hi, There👋! I am an undergraduate student at Harbin Institute of Technology (Shenzhen), working on Trustworthy Multimodal AI and Adaptive, Data-Efficient Learning. My recent research focuses on robust and reliable multimodal model adaptation under distribution shift, especially for test-time adaptation and hallucination mitigation in vision-language systems.

🔥 News

  • 2026.02:  🎉🎉 One paper “Do All Individual Layers Help?”, was accepted by CVPR 2026 Findings.
  • 2026.02:  🎉🎉 One paper “Test-Time Distillation for Continual Model Adaptation”, was accepted by CVPR 2026 Findings.
  • 2025.11:  🎉🎉 Recognized as one of the ‘Top Ten Outstanding College Students’ at Harbin Institute of Technology (Shenzhen)

📝 Publications

CVPR 2026
paper-1

Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Models

Zhiming Liu, Yujie Wei, Lei Feng, Xiu Su, Xiaobo Xia, Weili Guan, Zeke Xie, Shuo Yang

  • We identify task-interfering layers in vision-language models and propose a lightweight test-time intervention strategy that improves downstream few-shot reasoning without retraining.
CVPR 2026
paper-2

Test-Time Distillation for Continual Model Adaptation

Xiao Chen, Jiazhen Huang, Zhiming Liu, Qinting Jiang, Fanding Huang, Jingyan Jiang, Zhi Wang

  • We propose a collaborative test-time distillation framework for continual model adaptation that improves robustness and generalization under realistic distribution shifts.
Under Review
paper-1

Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification

Quanjiang Li†, Zhiming Liu†, TianxiangXu†, Tingjin Luo, Chenping Hou

  • We proposed ADRL, a novel framework that jointly addresses structural distortion and semantic ambiguity in incomplete multi-view settings by integrating label-guided feature disentanglement and category-aware embedding interaction.
  • † indicates equal contribution (co-first authors).

🎖 Honors and Awards

  • 2024: Finalist Award in the Mathematical Contest in Modeling (MCM)
  • 2024: Chinese National Scholarship
  • 2025: National Second Prize, Global Campus Artificial Intelligence Algorithm Elite Competition 2025
  • 2025: Top Ten Outstanding College Students of Harbin Institute of Technology (Shenzhen)

📖 Educations

  • Sep. 2023 - Jul. 2027, Harbin Institute of Technology (Shenzhen), B.Eng. in Autonomous.

🔬 Research Experience

  • May. 2025 - Nov. 2025, Task-Interfering Layer Optimization for Test-Time Adaptation of Multimodal Large Language Models (Leader).
  • Nov. 2025 - Jan. 2026, Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory (Leader).
  • Jan. 2025 - Jun. 2025, Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification (Leader).
  • Aug. 2025 - Nov. 2025, CoDiRe: Collaborative Test-Time Distillation for Robust Domain Generalization (Core Member).
  • Nov. 2025 - Jan. 2026, Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction (Core Member).
  • Aug. 2025 - Jan. 2026, Multimodal Large Language Models for Industrial Quality Inspection (Core Member).
  • Dec. 2024 - Nov. 2025, AI-Powered Microscopic Parasite Recognition and Extraction System (Core Member).
  • Sep. 2025 - Dec. 2025, Deterministic Transition State Prediction via Flow Matching and Equivariant Geometric Learning (Core Developer).

💻 Internships

  • 2025.03 - now, Research Intern at HITSZ, advised by Prof. Shuo Yang.
  • 2025.11 - now, Research Intern at THU, advised by Prof. Zhi Wang.