Diffusion models have made high-fidelity visual generation widely accessible, while also lowering the barrier to producing convincing visual forgeries and complicating content provenance. Existing watermarking methods typically use a fixed embedding strength throughout denoising or treat all watermark dimensions equall...
Yu-Hao Xue, Jiu-An Zhou, Yu Cheng et al.· 0 citations
This paper proposes a personalized Federated Mask-based Selective PEFT framework, which significantly outperforms the existing federated PEFT method on both seen and unseen classes, and achieves balanced performance on all clients.
Wen-Tao Gu, Xin-Yang Jiang, Jun-Yao Gao et al.· Proceedings of the 34th ACM...· 0 citations
A central challenge in multimodal in-context learning (MICL) arises from tasks that are ill-defined without context and require uncovering the underlying rules from demonstrations. Existing methods predominantly treat MICL as direct input-output mapping, overlooking the importance of explicitly inducing and reasoning o...
Yu-Quan Li, Xin-Yang Jiang, Yu-Hao Xue et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.