Zobrazeno 1 - 10
of 231 852
pro vyhledávání: '"Donald, P."'
Recent advancements in image generation models have enabled personalized image creation with both user-defined subjects (content) and styles. Prior works achieved personalization by merging corresponding low-rank adaptation parameters (LoRAs) through
Externí odkaz:
http://arxiv.org/abs/2412.05148
Parities have become a standard benchmark for evaluating learning algorithms. Recent works show that regular neural networks trained by gradient descent can efficiently learn degree $k$ parities on uniform inputs for constant $k$, but fail to do so w
Externí odkaz:
http://arxiv.org/abs/2412.04910
Autor:
Kurtz, Donald W., Handler, Gerald, Holdsworth, Daniel L., Cunha, Margarida S., Saio, Hideyuki, Medupe, Thebe, Murphy, Simon J., Krüger, Joachim, Brunsden, E., Antoci, Victoria, Hey, Daniel R., Shitrit, Noi, Matthews, Jaymie M.
HD 60435 is a well-known rapidly oscillating (roAp) Ap star with a series of alternating even and odd degree modes, making it a prime asteroseismic target. It is also an oblique pulsator with rotational inclination, $i$, and magnetic/pulsation obliqu
Externí odkaz:
http://arxiv.org/abs/2412.04840
It has recently been suggested that tuning towards the boundary of the positivity domain of the scalar potential may explain the separation between the electroweak scale and the unification scale in a grand unified theory. Here we explore the possibi
Externí odkaz:
http://arxiv.org/abs/2412.04609
Autor:
Lattanzi, Aaron, Almgren, Ann, Quon, Eliot, Natarajan, Mahesh, Kosovic, Branko, Mirocha, Jeff, Perry, Bruce, Wiersema, David, Willcox, Donald, Yuan, Xingqiu, Zhang, Weiqun
High performance computing (HPC) architectures have undergone rapid development in recent years. As a result, established software suites face an ever increasing challenge to remain performant on and portable across modern systems. Many of the widely
Externí odkaz:
http://arxiv.org/abs/2412.04395
Autor:
Galappaththige, Chamuditha Jayanga, Lai, Jason, Windrim, Lloyd, Dansereau, Donald, Suenderhauf, Niko, Miller, Dimity
Autonomous agents often require accurate methods for detecting and localizing changes in their environment, particularly when observations are captured from unconstrained and inconsistent viewpoints. We propose a novel label-free, pose-agnostic chang
Externí odkaz:
http://arxiv.org/abs/2412.03911
For a given positive integer $m$, the concept of {\it hyperdeterminantal total positivity} is defined for a kernel $K:\R^{2m} \to \R$, thereby generalizing the classical concept of total positivity. Extending the fundamental example, $K(x,y) = \exp(x
Externí odkaz:
http://arxiv.org/abs/2412.03000
Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselines revolves around enforcing the invariance to a variety of data augme
Externí odkaz:
http://arxiv.org/abs/2412.02896
Self Supervised learning (SSL) has demonstrated its effectiveness in feature learning from unlabeled data. Regarding this success, there have been some arguments on the role that mutual information plays within the SSL framework. Some works argued fo
Externí odkaz:
http://arxiv.org/abs/2412.02121
The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decoupling) as well as complete and dimensional representation collapse. While
Externí odkaz:
http://arxiv.org/abs/2412.02109