With the rapid advancements in diffusion models and 3D generation techniques, dynamic 3D content generation has become a crucial research area. However, achieving high-fidelity 4D (dynamic 3D) generation with strong spatial-temporal consistency remains a challenging task. Inspired by recent findings that pretrained diffusion features capture rich correspondences, we propose FB-4D, a novel 4D generation framework that integrates a Feature Bank mechanism to enhance both spatial and temporal consistency in generated frames. In FB-4D, we store features extracted from previous frames and fuse them into the process of generating subsequent frames, ensuring consistent characteristics across both time and multiple views. To ensure a compact representation, the Feature Bank is updated by a proposed dynamic merging mechanism. Leveraging this Feature Bank, we demonstrate for the first time that generating additional reference sequences through multiple autoregressive iterations can continuously improve generation performance. Experimental results show that FB-4D significantly outperforms existing methods in terms of rendering quality, spatial-temporal consistency, and robustness. It surpasses all multi-view generation tuning-free approaches by a large margin and achieves performance on par with training-based methods. Our code and data will be publicly available to support future research.

Graph analytics has become a major workload in recent years. The underlying core algorithms tend to be irregular and data dependent, making them challenging to parallelize. Yet, these algorithms can be implemented and parallelized in many ways for CPUs and even more ways for GPUs. We took 6 key graph algorithms and created hundreds of CUDA, OpenMP, and parallel C++ versions of each of them, most of which have never been described or studied. To determine which parallelization and implementation styles work well and under what circumstances, we evaluated the resulting 1106 programs on 2 GPUs and 2 CPUs using 5 input graphs. Our results show which styles and combinations perform well and which ones should be avoided. We found that choosing the wrong implementation style can yield over a 10× slowdown on average. The worst combinations of styles can cost 6 orders of magnitude in performance.

Irregular programs are found in many domains and tend to exhibit input-dependent control flow and memory accesses. This paper introduces the Indigo suite of important irregular parallel code patterns for testing verification and other tools. We studied many irregular CPU and GPU programs and extracted the key code patterns. Then, we methodically built variations of these patterns to alter the control-flow and memory-access behavior and/or introduce bugs, yielding the thousands of OpenMP and CUDA microbenchmarks in the suite. Indigo includes a set of generators to systematically create an unbounded number of inputs for each microbenchmark, which is essential to exercise the wide range of possible behaviors of input-dependent codes. To manage the millions of code and input combinations, Indigo provides the flexibility to generate user-defined subsets of the suite. Experiments with a subset of buggy and bug-free codes illustrate that irregular programs pose a significant challenge to both static and dynamic program verification tools. Moreover, such tools can perform quite differently across code patterns that contain the same bug.

We propose an online resource regulation strategy based on resource allocation benefit-state transition in 5G Fronthaul Network (5G-RAB ST). Results show that the presented system can significantly reduce the waste of resources in 5G fronthaul and highly improve the quality of users' service.

Wind power prediction is of great importance in the utilization of renewable wind power. A lot of research has been done attempting to improve the accuracy of wind power predictions and has achieved desirable performance. However, there is no complete performance evaluation of machine learning methods. This paper presents an extensive empirical study of machine learning methods for wind power predictions. Nine various models are considered in this study which also includes the application and evaluation of deep learning techniques. The experimental data consists of seven datasets based on wind farms in Ontario, Canada. The results indicate that SVM, followed by ANN, has the best overall performance, and that k-NN method is suitable for longer ahead predictions. Despite the findings that deep learning fails to give improvement in basic predictions, it shows the potential for more abstract prediction tasks, such as spatial correlation predictions.