Multilayer Extreme Learning Machine (ML-ELM) and its variants have proven to be an effective technique for the classification of different natural signals such as audio, video, acoustic and images. In this paper, a Hybrid Multilayer Extreme Learning Machine (HML-ELM) that is based on ELM-based autoencoder (ELM-AE) and an Interval Type-2 fuzzy Logic theory is suggested for active image classification and applied to Unmanned Aerial Vehicles (UAVs). The proposed methodology is a hierarchical ELM learning framework that consists of two main phases: 1) self-taught feature extraction and 2) supervised feature classification. First, unsupervised multilayer feature encoding is achieved by stacking a number of ELM-AEs, in which input data is projected into a number of high-level representations. At the second phase, the final features are classified using a novel Simplified Interval Type-2 Fuzzy ELM (SIT2-FELM) with a fast output reduction layer based on the SC algorithm; an improved version of the algorithm Center of Sets Type Reducer without Sorting Requirement (COSTRWSR). To validate the efficiency of the HML-ELM, two types of experiments for the classification of images are suggested. First, the HML-ELM is applied to solve a number of benchmark problems for image classification. Secondly, a number of real experiments to the active classification and transport of four different objects between two predefined locations using a UAV is implemented. Experiments demonstrate that the proposed HML-ELM delivers a superior efficiency compared to other similar methodologies such as ML-ELM, Multilayer Fuzzy Extreme Learning Machine (ML-FELM) and ELM.

Generative image editing using diffusion models has become a prevalent application in today's AI cloud services. In production environments, image editing typically involves a mask that specifies the regions of an image template to be edited. The use of masks provides direct control over the editing process and introduces sparsity in the model inference. In this paper, we present InstGenIE, a system that efficiently serves image editing requests. The key insight behind InstGenIE is that image editing only modifies the masked regions of image templates while preserving the original content in the unmasked areas. Driven by this insight, InstGenIE judiciously skips redundant computations associated with the unmasked areas by reusing cached intermediate activations from previous inferences. To mitigate the high cache loading overhead, InstGenIE employs a bubble-free pipeline scheme that overlaps computation with cache loading. Additionally, to reduce queuing latency in online serving while improving the GPU utilization, InstGenIE proposes a novel continuous batching strategy for diffusion model serving, allowing newly arrived requests to join the running batch in just one step of denoising computation, without waiting for the entire batch to complete. As heterogeneous masks induce imbalanced loads, InstGenIE also develops a load balancing strategy that takes into account the loads of both computation and cache loading. Collectively, InstGenIE outperforms state-of-the-art diffusion serving systems for image editing, achieving up to 3x higher throughput and reducing average request latency by up to 14.7x while ensuring image quality.

Selçuk University, Computer Engineering Department, Konya, Turkey, stasdemir@selcuk .edu.tr, https://orcid.org/0000 - 0002 - 2433 - 246X Abstract: Potholes cause vehicle damage and traffic accidents, creating serious safety and economic problems. Therefore, early and accurate detection of potholes is crucial. Existing detection methods are usually only based on 2D RGB images and cannot accurately analyze the physical characteristics of potholes. In this paper, a publicly available dataset of RGB - D images (PothRGBD) is created and an impr oved YOLOv8 - based model is proposed for both pothole detection and pothole physical features analysis. The Intel RealSense D415 depth camera was used to collect RGB and depth data from the road surfaces, resulting in a PothRGBD dataset of 1000 images. The data was labeled in YOLO format suitable for segmentation. A novel YOLO model is proposed based on the YOLOv8n - seg architecture, which is structurally improved with Dynamic Snake Convolution (DSConv), Simple Attention Module (SimAM) and Gaussian Error Lin ear Unit (GELU). The proposed model segmented potholes with irregular edge structure more accurately, and performed perimeter and depth measurements on depth maps with high accuracy. With the proposed model, the values increased to 93.7%, 90.4% and 93.8% respectively. Thus, an improvement of 1.96% in precision, 6.13% in recall and 2.07% in mAP was achieved. The proposed model performs pothole detection as well as perimet er and depth measurement with high accuracy and is suitable for real - time applications due to its low model complexity. In this way, a lightweight and effective model that can be used in deep learning - based intelligent transportation solutions has been acq uired. Pothole Detection, YOLOv8 Segmentation, Depth Estimation, Intelligent Transportation Systems, RGB - D Imaging, Deep Learning 1. Introduction Potholes are one of the most common and dangerous types of road surface deterioration. It usually oc curs when water seeps into the asphalt or concrete surface and weakens the sub - layers, then the traffic load erodes the weakened area [1, 2] . Over time, small cracks widen into deep potholes.

A Nonlinear Hash-based Optimization Method for SpMV on GPUs Chen Y an a,b, Boyu Diao a,b, Hangda Liu a,b, Zhulin An a,b and Y ongjun Xu a,b a Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China b University of Chinese Academy of Sciences, Beijing, China {yanchen23s, diaoboyu2012, liuhangda21s, anzhulin, xyj } @ict.ac.cn Abstract --Sparse matrix-vector multiplication (SpMV) is a fundamental operation with a wide range of applications in scientific computing and artificial intelligence. However, the large scale and sparsity of sparse matrix often make it a performance bottleneck. In this paper, we highlight the effectiveness of hash-based techniques in optimizing sparse matrix reordering, introducing the Hash-based Partition (HBP) format, a lightweight SpMV approach. HBP retains the performance benefits of the 2D-partitioning method while leveraging the hash transformation's ability to group similar elements, thereby accelerating the pre-processing phase of sparse matrix reordering. Additionally, we achieve parallel load balancing across matrix blocks through a competitive method. Our experiments, conducted on both Nvidia Jetson AGX Orin and Nvidia RTX 4090, show that in the pre-processing step, our method offers an average speedup of 3.53 times compared to the sorting approach and 3.67 times compared to the dynamic programming method employed in Regu2D. Furthermore, in SpMV, our method achieves a maximum speedup of 3.32 times on Orin and 3.01 times on RTX4090 against the CSR format in sparse matrices from the University of Florida Sparse Matrix Collection. I NTRODUCTION Sparse matrix-vector multiplication (SpMV) has a wide range of applications, such as mathematical solutions for sparse linear equations [13], iterative algorithm-solving processing [15] [25], graph processing [9] [14] [24], and weight calculations for forward and backward propagation in neural networks [3] [12] [17] [19], etc. However, SpMV is actually the bottleneck for many algorithms. The sparse matrix used in SpMV has the following characteristics [4]: (1) Sparsity. On the one hand, sparse matrices contain a large number of zero elements.

KV cache techniques in Transformer models aim to reduce redundant computations at the expense of substantially increased memory usage, making KV cache compression an important and popular research topic. Recently, state-of-the-art KV cache compression methods implement imbalanced, per-head allocation algorithms that dynamically adjust the KV cache budget for each attention head, achieving excellent performance in single-GPU scenarios. However, we observe that such imbalanced compression leads to significant load imbalance when deploying multi-GPU inference, as some GPUs become overburdened while others remain underutilized. In this paper, we propose FairKV, a method designed to ensure fair memory usage among attention heads in systems employing imbalanced KV cache compression. The core technique of FairKV is Fair-Copying, which replicates a small subset of memory-intensive attention heads across GPUs using data parallelism to mitigate load imbalance. Our experiments on popular models, including LLaMA 70b and Mistral 24b model, demonstrate that FairKV increases throughput by 1.66x compared to standard tensor parallelism inference. Our code will be released as open source upon acceptance.

Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets, enabling task-specific adaptation while preserving data privacy. However, fine-tuning the extensive parameters in LLMs is particularly challenging in resource-constrained federated scenarios due to the significant communication and computational costs. To gain a deeper understanding of how these challenges can be addressed, this article conducts a comparative analysis three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues: 1) FedLLMs, where clients upload model parameters or gradients to enable straightforward and effective fine-tuning; 2) KD-FedLLMs, which leverage KD for efficient knowledge sharing via logits; and 3) Split-FedLLMs, which split the LLMs into two parts, with one part executed on the client and the other one on the server, to balance the computational load. Each framework is evaluated based on key performance metrics, including model accuracy, communication overhead, and client-side computational load, offering insights into their effectiveness for various federated fine-tuning scenarios. Through this analysis, we identify framework-specific optimization opportunities to enhance the efficiency of FedLLMs and discuss broader research directions, highlighting open opportunities to better adapt FedLLMs for real-world applications. A use case is presented to demonstrate the performance comparison of these three frameworks under varying configurations and settings.

We propose a novel algorithm for combined unit/filter and layer pruning of deep neural networks that functions during training and without requiring a pre-trained network to apply. Our algorithm optimally trades-off learning accuracy and pruning levels while balancing layer vs. unit/filter pruning and computational vs. parameter complexity using only three user-defined parameters, which are easy to interpret and tune. The optimal network structure is found as the solution of a stochastic optimization problem over the network weights and the parameters of variational Bernoulli distributions for 0/1 Random Variables scaling the units and layers of the network. Pruning occurs when a variational parameter converges to 0 rendering the corresponding structure permanently inactive, thus saving computations during training and prediction. A key contribution of our approach is to define a cost function that combines the objectives of prediction accuracy and network pruning in a computational/parameter complexity-aware manner and the automatic selection of the many regularization parameters. We show that the solutions of the optimization problem to which the algorithm converges are deterministic networks. We analyze the ODE system that underlies our stochastic optimization algorithm and establish domains of attraction around zero for the dynamics of the network parameters. These results provide theoretical support for safely pruning units/filters and/or layers during training and lead to practical pruning conditions. We evaluate our method on the CIFAR-10/100 and ImageNet datasets using ResNet architectures and demonstrate that our method improves upon layer only or unit only pruning and favorably competes with combined unit/filter and layer pruning algorithms requiring pre-trained networks with respect to pruning ratios and test accuracy.

Domain decomposition is a technique used to reduce memory overhead on large neutron transport problems. Currently, the optimal load-balanced processor allocation for these domains is typically determined through small-scale simulations of the problem, which can be time-consuming for researchers and must be repeated anytime a problem input is changed. We propose a Transformer model with a unique 3D input embedding, and input representations designed for domain-decomposed neutron transport problems, which can predict the subdomain computation loads generated by small-scale simulations. We demonstrate that such a model trained on domain-decomposed Small Modular Reactor (SMR) simulations achieves 98.2% accuracy while being able to skip the small-scale simulation step entirely. Tests of the model's robustness on variant fuel assemblies, other problem geometries, and changes in simulation parameters are also discussed.