3 papers
cs.CV2026
A one-step generation model with a Single-Layer Transformer: Layer number re-distillation of FreeFlow
Haonan Wei, Linyuan Wang, Nuolin Sun +3
Currently, Flow matching methods aim to compress the iterative generation process of diffusion models into a few or even a single step, with MeanFlow and FreeFlow being representat…
cs.CV2025
MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation
Nuolin Sun, Linyuan Wang, Haonan Wei +2
ResNet has achieved tremendous success in computer vision through its residual connection mechanism. ResNet can be viewed as a discretized form of ordinary differential equations (…
cs.CV2025
Are classical deep neural networks weakly adversarially robust?
Nuolin Sun, Linyuan Wang, Dongyang Li +2
Adversarial attacks have received increasing attention and it has been widely recognized that classical DNNs have weak adversarial robustness. The most commonly used adversarial de…