diffusion models

Corridor connectivity and cross-diffusion-induced spatiotemporal dynamics in a Leslie–Gower model with Allee effect

Multivariate time-series forecasting for complex industrial processes via a dual-stream conditional cooperative diffusion probabilistic model

CA-DLM: Causal-aware diffusion language model for interpretable industrial defective image generation

A conditional generative diffusion model enables joint retrieval of rice LAI and LCC

DiTFusion: Prostate magnetic resonance image fusion based on Scalable Diffusion Models with transformers

Diffusion-enhanced multi-perspective inconsistency modeling for graph anomaly detection

Generative Artificial Intelligence and Diffusion models in Drug Discovery: A Critical Review

Dual Effects of Brown Algae Impurities on Coral Concrete: Sulfate Resistance Decay and Multiscale Predictive Modeling

In island construction, the application of coral aggregate concrete (CAC) is challenged by marine biological impurities, particularly brown algae, which impact material performance. This study systematically investigates the effects of brown algae content (0%–6%), water-to-cement ratio, and sulfate ion wet–dry cycles on CAC’s fluidity, air content, compressive/splitting/axial strengths, and sulfate ion diffusion behavior. Results showed that brown algae content ≤ 2 % has negligible effect on fluidity, but higher contents significantly reduce workability. All strength parameters decreased with increasing impurity content and water-to-cement ratio. Early-stage seawater-immersion curing enhanced strength, but prolonged exposure led to significant degradation. A proposed strength prediction model demonstrated strong correlation with experimental data ( R 2 > 0.94 ). Under sulfate cycles, CAC’s mass loss rate, relative dynamic elastic modulus, and compressive strength exhibit a nonmonotonic increase-then-decrease trend, and the damage layer thickness grows exponentially with cycle, impurity content, and water-to-cement ratio. Controlling brown algae ≤ 2 % and water-to-cement ratio ≤ 0.3 optimizes sulfate erosion resistance. Numerical simulations reveal an exponential relationship between erosion depth and cycle, with uneven sulfate ion accumulation in CAC’s porous structure, highlighting diffusion heterogeneity. These findings provide critical technical guidelines for deploying CAC in marine environments, balancing ecological sustainability and engineering durability.

Adaptive Diffused Spatiotemporal Graph Convolution for Traffic Flow Forecasting

A novel method called adaptive diffused spatiotemporal graph convolution network (ADSTGCN) is proposed for accurate traffic flow prediction and achieves superior performance compared to other state-of-the-art methods.

Experimental study and theoretical model on structure of horizontal turbulent jet diffusion flame with co-flowing wind

A Vehicle Detector Based on Feature Focused Diffusion

Experimental results and robustness tests showed that RDT-YOLO has broad application prospects in different scenarios and can provide reliable support for intelligent transportation systems and autonomous driving technologies.

Dual-Constrained Diffusion Model for Nonlinear Microstructure Inverse Design with Direct Evaluation