Minghao Fu
Scholar

Minghao Fu

Google Scholar ID: SsKm76gAAAAJ
Nanjing University
Computer VisionMachine Learning
Citations & Impact
All-time
Citations
133
 
H-index
8
 
i10-index
4
 
Publications
18
 
Co-authors
5
list available
Publications
18 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Published multiple papers, including:
  • - CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation (ICML 2025)
  • - Quantization without Tears (CVPR 2025)
  • - Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation (CVPR 2025)
  • - Rectify the Regression Bias in Long-Tailed Object Detection (ECCV 2024)
  • - Unified Low-rank Compression Framework for Click-through Rate Prediction (KDD 2024)
  • - Instance-based Max-margin for Practical Few-shot Recognition (CVPR 2024)
  • - DTL: Disentangled Transfer Learning for Visual Recognition (AAAI 2024)
  • - Multi-Label Self-Supervised Learning with Scene Images (ICCV 2023)
  • - Worst Case Matters for Few-Shot Recognition (ECCV 2022)
Research Experience
  • Research work in the LAMDA group, served as a Teaching Assistant for Pattern Recognition.
Education
  • PhD student at the School of Artificial Intelligence, Nanjing University, in the LAMDA group, supervised by Professor Zhi-Hua Zhou; B.Sc. in Computer Science and Technology from Yingcai Honors College, University of Electronic Science and Technology of China (UESTC), graduated in June 2021.
Background
  • Research interests include Machine Learning and Computer Vision. Currently focused on Few-Shot Learning and Efficient Learning.
Miscellany
  • Served as a reviewer for several conferences, including CVPR 2024, ECCV 2024, CVPR 2025, ICCV 2025, ACMMM 2025.