5 papers
GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness
Zhiyuan Ye, Xiangyu Zhou, Ji Qi +2
Adversarial Training (AT) improves neural network robustness, but most methods train a fixed parameter space from the start. This paper asks whether the order in which parameters b…
IQ-LUT: interpolated and quantized LUT for efficient image super-resolution
Yuxuan Zhang, Zhikai Dong, Xinning Chai +4
Lookup table (LUT) methods demonstrate considerable potential in accelerating image super-resolution inference. However, pursuing higher image quality through larger receptive fiel…
Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)
Xiangyu Zhou, Chenhan Xiao, Yang Weng
Shapley value-based methods have become foundational in explainable artificial intelligence (XAI), offering theoretically grounded feature attributions through cooperative game the…
Attention Retention for Continual Learning with Vision Transformers
Yue Lu, Xiangyu Zhou, Shizhou Zhang +3
Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In t…
LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation
Xiaoqi Dong, Xiangyu Zhou, Nicholas Evans +1
Text-to-Image (T2I) generation has made significant advancements with diffusion models, yet challenges persist in handling complex instructions, ensuring fine-grained content contr…