Minghao Fu

Orcid: 0000-0002-4685-6600

Affiliations:
  • Nanjing University, School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, China
  • Alibaba Group, Ovis Team, China (2024-2025)


According to our database1, Minghao Fu authored at least 18 papers between 2022 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models.
CoRR, November, 2025

Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality.
CoRR, August, 2025

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance.
CoRR, July, 2025

Ovis-U1 Technical Report.
CoRR, June, 2025

QwT-v2: Practical, Effective and Efficient Post-Training Quantization.
CoRR, May, 2025

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities.
CoRR, May, 2025

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Minimal Interaction Seperated Tuning: A New Paradigm for Visual Adaptation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Quantization without Tears.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
Minimal Interaction Edge Tuning: A New Paradigm for Visual Adaptation.
CoRR, 2024

Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning.
CoRR, 2024

Unified Low-rank Compression Framework for Click-through Rate Prediction.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Rectify the Regression Bias in Long-Tailed Object Detection.
Proceedings of the Computer Vision - ECCV 2024, 2024

Instance-based Max-margin for Practical Few-shot Recognition.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

DTL: Disentangled Transfer Learning for Visual Recognition.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Instance-based Max-margin for Practical Few-shot Recognition.
CoRR, 2023

Multi-Label Self-Supervised Learning with Scene Images.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
Worst Case Matters for Few-Shot Recognition.
Proceedings of the Computer Vision - ECCV 2022, 2022


  Loading...