Zobrazeno 1 - 10
of 1 805
pro vyhledávání: '"Xia, Shu"'
Fine-tuning large-scale text-to-image diffusion models for various downstream tasks has yielded impressive results. However, the heavy computational burdens of tuning large models prevent personal customization. Recent advances have attempted to empl
Externí odkaz:
http://arxiv.org/abs/2410.21759
Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong generalization wi
Externí odkaz:
http://arxiv.org/abs/2410.15430
Recent studies have shown that LLMs are vulnerable to denial-of-service (DoS) attacks, where adversarial inputs like spelling errors or non-semantic prompts trigger endless outputs without generating an [EOS] token. These attacks can potentially caus
Externí odkaz:
http://arxiv.org/abs/2410.10760
Autor:
Zha, Yaohua, Dai, Tao, Wang, Yanzi, Guo, Hang, Zhang, Taolin, Ouyang, Zhihao, Fan, Chunlin, Chen, Bin, Chen, Ke, Xia, Shu-Tao
Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds based on the modeled content. Masked autoencoders (MAE) have become the mainstream paradigm in point clouds self-su
Externí odkaz:
http://arxiv.org/abs/2410.09886
Autor:
Zhang, Taolin, Pan, Junwei, Wang, Jinpeng, Zha, Yaohua, Dai, Tao, Chen, Bin, Luo, Ruisheng, Deng, Xiaoxiang, Wang, Yuan, Yue, Ming, Jiang, Jie, Xia, Shu-Tao
With recent advances in large language models (LLMs), there has been emerging numbers of research in developing Semantic IDs based on LLMs to enhance the performance of recommendation systems. However, the dimension of these embeddings needs to match
Externí odkaz:
http://arxiv.org/abs/2410.09560
Model Inversion Attacks (MIAs) aim at recovering privacy-sensitive training data from the knowledge encoded in the released machine learning models. Recent advances in the MIA field have significantly enhanced the attack performance under multiple sc
Externí odkaz:
http://arxiv.org/abs/2410.05814
Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from the hallucin
Externí odkaz:
http://arxiv.org/abs/2410.05601
Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising widespread concerns on privacy threats of Deep Neural Networks (DNNs). Unfortunately, in tandem with the ra
Externí odkaz:
http://arxiv.org/abs/2410.05159
Non-stationarity poses significant challenges for multivariate time series forecasting due to the inherent short-term fluctuations and long-term trends that can lead to spurious regressions or obscure essential long-term relationships. Most existing
Externí odkaz:
http://arxiv.org/abs/2410.04442
Multi-view image compression is vital for 3D-related applications. To effectively model correlations between views, existing methods typically predict disparity between two views on a 2D plane, which works well for small disparities, such as in stere
Externí odkaz:
http://arxiv.org/abs/2409.04013