Ouxiang Li

Orcid: 0009-0004-4967-9680

According to our database1, Ouxiang Li authored at least 10 papers between 2023 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
SO-TransUNet: enhanced TransUNet for fine-grained masonry crack segmentation.
Vis. Comput., January, 2026

Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model.
CoRR, January, 2026

2025
RL-MTJail: Reinforcement Learning for Automated Black-Box Multi-Turn Jailbreaking of Large Language Models.
CoRR, December, 2025

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
CoRR, September, 2025

Prior Preserved Text-to-Image Personalization Without Image Regularization.
IEEE Trans. Circuits Syst. Video Technol., February, 2025

Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.1, 2025

A Sanity Check for AI-generated Image Detection.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models.
CoRR, 2024

2023
Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023


  Loading...