13 papers · ranked by Valyu relevance
Arisa Ikeda, Ryo Higuchi, Tomohiro Yokozeki, Katsuhiro Endo + 3 more
In this study, we develop a conditional diffusion model that proposes the optimal process parameters and predicts the microstructure for the desired mechanical properties. In materials development, it is costly to try many samples with different parameters in experiments and numerical simulations. The use of…
Chengyu Qiao, Eryun Liu, Jingwei Ren, Long He + 2 more
Accurate estimation of human joint moments from multimodal sensor signals is essential for lower-limb exoskeleton control. Recent studies have addressed this problem in an end-to-end manner, but remain limited by insufficient long-range temporal modeling, limited training data, and class imbalance. To address these…
Emanuele Caruso, Francesco Pelosin, Alessandro Simoni, Oswald Lanz + 3 more
Synthetic dataset generation in Computer Vision, particularly for industrial applications, is still underexplored. Industrial defect segmentation, for instance, requires highly accurate labels, yet acquiring such data is costly and time-consuming. To address this challenge, we propose a novel diffusion-based pipeline…
Haotian Chen, Yiting Shen, Jichun Li, Weizhong Zhao
Fragment-based molecular generation has emerged as a promising paradigm in structure-based drug design (SBDD), deriving effective compounds with advanced properties, including chemical validity, synthetic feasibility, pharmacological relevance, etc. However, existing approaches often struggle with generating molecules…
Xiaochen Zhang, Shuangxi Wang, Ying Fang, Qiankun Zhang + 1 more
Recent advancements in denoising diffusion models have revolutionized image, text, and video generation. Inspired by these achievements, researchers have extended denoising diffusion models to the field of molecule generation. However, existing molecular generation diffusion models are not fully optimized according to…
Alzahra Altalib, Chunhui Li, Alessandro Perelli, Emilio Quaia
Title: Simple Summary Cone Beam Computed Tomography (CBCT) is widely used in radiotherapy because it is fast and relatively low dose, but its image quality is lower than that of conventional CT. Conditional diffusion models have recently been proposed to convert CBCT into synthetic CT with improved anatomical detail…
Xuyuan Wang, Katharina Kusejko
We present a generative modeling framework for global sensitivity analysis (GSA) in complex systems characterized by strong and potentially high-dimensional parameter correlations. Traditional variance-based GSA methods rely on the assumption of independent inputs, which rarely holds for Bayesian-calibrated models.…
Alzahra Altalib, Chunhui Li, Alessandro Perelli
$(7)σ_{t}^{2}=β_{t}\cdot\frac{1-α¯_{t-1}}{1-α¯_{t}}$ This process has been iterated from to for the generation of a high fidelity sCT image, which is conditioned on the CBCT input. The final output is rescaled back to the clinical HU range by using inverse normalization. 2.1.4#### Conditional sampling stability To…
Yue Li, Yunyan Wang, Mingtian Tang, Lei Chu
The transition probability density of second-order diffusion processes plays a fundamental role in statistical inference and practical applications such as financial derivatives pricing. This paper combines nonparametric Nadaraya-Watson kernel smoothing and local linear smoothing techniques to devise a re-weighted…
Ganchao Wei, John Pearson
High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions across successive batches or time points form critical components of data analysis. The recent success of diffusion- and flow-based deep generative models for images, video…
Wen Su, Changyu Liu, Guosheng Yin, Jian Huang
Current status data are commonly encountered in modern medicine, econometrics and social science. Its unique characteristics pose significant challenges to the analysis of such data and the existing methods often suffer grave consequences when the underlying model is misspecified. To address these difficulties, we…
Călin Gheorghe Buzea, Florin Nedeff, Diana Mirilă, Valentin Nedeff + 5 more
Living systems exhibit anticipation, adaptability, and resilience that cannot be fully explained by stimulus-response models, static homeostasis, or convergence-based optimization. This work addresses this gap by proposing a theoretical framework in which a central aspect of biological function is understood through…
Tatsuhiro Furuta, Shuya Fan, Tadao Takada, Yohei Kondo + 4 more
We investigate the transition processes between the emitting (ON) and non-emitting (OFF) states of fluorescent molecules using a machine-learning approach. In fluorescently labeled DNA, continuous fluorescence is observed under irradiation; however, the system occasionally transitions to a non-emitting state, often…