Zobrazeno 1 - 10
of 3 647
pro vyhledávání: '"P Onal"'
Autor:
Ning, Mang, Li, Mingxiao, Su, Jianlin, Jia, Haozhe, Liu, Lanmiao, Beneš, Martin, Salah, Albert Ali, Ertugrul, Itir Onal
This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosine transform (DCT) space. We investigate the design space of DCTdiff an
Externí odkaz:
http://arxiv.org/abs/2412.15032
{We present the radial metallicity gradients within the Galactic thin disc population through main-sequence stars selected on the chemical plane using GALAH DR3 accompanied with Gaia DR3 astrometric data. The [Fe/H], [$\alpha$/Fe] and [Mg/H] radial g
Externí odkaz:
http://arxiv.org/abs/2411.13660
Partitioning is a known problem in computer science and is critical in chip design workflows, as advancements in this area can significantly influence design quality and efficiency. Deep Learning (DL) techniques, particularly those involving Graph Ne
Externí odkaz:
http://arxiv.org/abs/2409.01387
Facial Action Unit (AU) detection has gained significant research attention as AUs contain complex expression information. In this paper, we unpack two fundamental factors in AU detection: data and subject identity regularization, respectively. Motiv
Externí odkaz:
http://arxiv.org/abs/2407.11243
The Rectilinear Steiner Minimum Tree (RSMT) problem is a fundamental problem in VLSI placement and routing and is known to be NP-hard. Traditional RSMT algorithms spend a significant amount of time on finding Steiner points to reduce the total wire l
Externí odkaz:
http://arxiv.org/abs/2407.01440
Recent advancements in quality control across various industries have increasingly utilized the integration of video cameras and image processing for effective defect detection. A critical barrier to progress is the scarcity of comprehensive datasets
Externí odkaz:
http://arxiv.org/abs/2406.07694
Fine-tuned Large Language Models (LLMs) often suffer from overconfidence and poor calibration, particularly when fine-tuned on small datasets. To address these challenges, we propose a simple combination of Low-Rank Adaptation (LoRA) with Gaussian St
Externí odkaz:
http://arxiv.org/abs/2405.03425
This paper aims to solve the contact-aware locomotion problem of a soft snake robot by developing bio-inspired contact-aware locomotion controllers. To provide effective contact information for the controllers, we develop a scale-covered sensor struc
Externí odkaz:
http://arxiv.org/abs/2309.02781
Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lacks in-depth exploration. In this paper, we systematically investigate t
Externí odkaz:
http://arxiv.org/abs/2308.15321
Neural Collapse (NC) gives a precise description of the representations of classes in the final hidden layer of classification neural networks. This description provides insights into how these networks learn features and generalize well when trained
Externí odkaz:
http://arxiv.org/abs/2308.02760