Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Wang, Qizhou"'
The compelling goal of eradicating undesirable data behaviors, while preserving usual model functioning, underscores the significance of machine unlearning within the domain of large language models (LLMs). Recent research has begun to approach LLM u
Externí odkaz:
http://arxiv.org/abs/2406.09179
Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet. However, existing test datasets are typically curated based on ImageNet-trained models, which aim to capt
Externí odkaz:
http://arxiv.org/abs/2403.11497
Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and their respective impacts. Literature evidence from in-distribution data
Externí odkaz:
http://arxiv.org/abs/2312.16243
Autor:
Makarenko, Maksim, Wang, Qizhou, Burguete-Lopez, Arturo, Giancola, Silvio, Ghanem, Bernard, Passone, Luca, Fratalocchi, Andrea
Foundation models, exemplified by GPT technology, are discovering new horizons in artificial intelligence by executing tasks beyond their designers' expectations. While the present generation provides fundamental advances in understanding language an
Externí odkaz:
http://arxiv.org/abs/2312.10639
This paper considers an important Graph Anomaly Detection (GAD) task, namely open-set GAD, which aims to train a detection model using a small number of normal and anomaly nodes (referred to as seen anomalies) to detect both seen anomalies and unseen
Externí odkaz:
http://arxiv.org/abs/2311.06835
Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open-world classification. However, it is typically hard to collect real out-o
Externí odkaz:
http://arxiv.org/abs/2311.03236
Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may still fai
Externí odkaz:
http://arxiv.org/abs/2311.01796
Autor:
Barkey, Martin, Büchner, Rebecca, Wester, Alwin, Pritzl, Stefanie D., Makarenko, Maksim, Wang, Qizhou, Weber, Thomas, Trauner, Dirk, Maier, Stefan A., Fratalocchi, Andrea, Lohmüller, Theobald, Tittl, Andreas
Nanophotonic devices excel at confining light into intense hot spots of the electromagnetic near fields, creating unprecedented opportunities for light-matter coupling and surface-enhanced sensing. Recently, all-dielectric metasurfaces with ultrashar
Externí odkaz:
http://arxiv.org/abs/2308.15644
Autor:
Wang, Qizhou, Ye, Junjie, Liu, Feng, Dai, Quanyu, Kalander, Marcus, Liu, Tongliang, Hao, Jianye, Han, Bo
Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typically deviate from test OOD data. Thus, the performance of OE, when fa
Externí odkaz:
http://arxiv.org/abs/2303.05033
Cross-domain graph anomaly detection (CD-GAD) describes the problem of detecting anomalous nodes in an unlabelled target graph using auxiliary, related source graphs with labelled anomalous and normal nodes. Although it presents a promising approach
Externí odkaz:
http://arxiv.org/abs/2212.01096