2 papers
cs.LG2024
Graph Diffusion Policy Optimization
Yijing Liu, Chao Du, Tianyu Pang +3
Recent research has made significant progress in optimizing diffusion models for downstream objectives, which is an important pursuit in fields such as graph generation for drug de…
cs.CV2024
Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing
Yunlong Zhao, Xiaoheng Deng, Yijing Liu +3
Model stealing (MS) involves querying and observing the output of a machine learning model to steal its capabilities. The quality of queried data is crucial, yet obtaining a large…