Achieving equity in healthcare accessibility requires lightweight yet high-performance solutions for medical image segmentation, particularly in resource-limited settings. Existing methods like U-Net and its variants often suffer from limited global Effective Receptive Fields (ERFs), hindering their ability to capture long-range dependencies. To address this, we propose U-RWKV, a novel framework leveraging the Recurrent Weighted Key-Value(RWKV) architecture, which achieves efficient long-range modeling at O(N) computational cost. The framework introduces two key innovations: the Direction-Adaptive RWKV Module(DARM) and the Stage-Adaptive Squeeze-and-Excitation Module(SASE). DARM employs Dual-RWKV and QuadScan mechanisms to aggregate contextual cues across images, mitigating directional bias while preserving global context and maintaining high computational efficiency. SASE dynamically adapts its architecture to different feature extraction stages, balancing high-resolution detail preservation and semantic relationship capture. Experiments demonstrate that U-RWKV achieves state-of-the-art segmentation performance with high computational efficiency, offering a practical solution for democratizing advanced medical imaging technologies in resource-constrained environments. The code is available at https://github.com/hbyecoding/U-RWKV.

Attributed graph clustering, which aims to group the nodes of an attributed graph into disjoint clusters, has made promising advancements in recent years. However, most existing methods face challenges when applied to large graphs due to the expensive computational cost and high memory usage. In this paper, we introduce Scalable and Adaptive Spectral Embedding (SASE), a simple attributed graph clustering method devoid of parameter learning. SASE comprises three main components: node features smoothing via $k$-order simple graph convolution, scalable spectral clustering using random Fourier features, and adaptive order selection. With these designs, SASE not only effectively captures global cluster structures but also exhibits linear time and space complexity relative to the graph size. Empirical results demonstrate the superiority of SASE. For example, on the ArXiv dataset with 169K nodes and 1.17M edges, SASE achieves a 6.9\% improvement in ACC and a $5.87\times$ speedup compared to the runner-up, S3GC.

Palo Alto Networks announced new capabilities to boost its single-vendor SASE solution enabling organizations to automate their increasingly complex IT and network operations center (NOC) functions. Additionally, the company announced features to secure IoT and automate branch management. With new AI-powered capabilities, organizations can confidently rely on Prisma SASE to generate better security outcomes and unlock operational efficiencies. According to the Gartner 2022 Roadmap for SASE Convergence report1, by 2025, 80% of enterprises will have adopted a strategy to unify web, cloud services and private application access using a SASE/SSE architecture, up from 20% in 2021. "With so many organizations adopting SASE, it is important to understand that in order to reap the full benefits, they need to move towards a single-vendor SASE approach. A mix-and-match approach increases complexity and makes it challenging to be proactive or isolate issues," said Kumar Ramachandran, senior vice president for Products, SASE.

Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention (MHSA) in the Transformer model so powerful, this paper proposes to extend the widely adopted light-weight Squeeze-Excitation (SE) module to be spatially-adaptive to reinforce its data specificity, as a convolutional alternative of the MHSA, while retaining the efficiency of SE and the inductive basis of convolution. It presents two designs of spatially-adaptive squeeze-excitation (SASE) modules for image synthesis and image recognition respectively. For image synthesis tasks, the proposed SASE is tested in both low-shot and one-shot learning tasks. It shows better performance than prior arts. For image recognition tasks, the proposed SASE is used as a drop-in replacement for convolution layers in ResNets and achieves much better accuracy than the vanilla ResNets, and slightly better than the MHSA counterparts such as the Swin-Transformer and Pyramid-Transformer in the ImageNet-1000 dataset, with significantly smaller models.

As we turn the calendar page on 2021, what has been a challenging two years in the midst of the pandemic is finally giving way to hope and promise for the new year. As the pandemic greatly accelerated companies' digital transformations and their use of innovative technologies, the new normal will see businesses needing to innovate just as fast without being forced to. With an eye to the next year, leading analyst firm Gartner recently released its "Top Strategic Technology Trends for 2022," and while I agree with all of them, I have added a few of my own areas of innovation and new technologies that will help organizations of all sizes capture new efficiencies, reduce costs, maintain greater control over their operations and delight their customers and employees. Here are my top 10 predictions. While more organizations are expected to return to the office this year, the distributed or hybrid model will continue to endure, especially since it has clear key benefits, such as access to a wider pool of talent, increased productivity and employee morale.

AIOps (AI for IT operations) adoption is on the rise as organizations invest in AI to make their IT ops smarter, faster, and more secure. Those who have adopted AIOps view the technology as no longer a nice-to-have but a necessity in the post-pandemic, work-from-home era. IT leaders are tasked with managing third-party cloud applications from devices and remote workers scattered across numerous locations in this new era. The insights come from a recently published State of AIOps Study, conducted by ZK Research, sponsored by Masergy, a software-defined networking (SD-WAN) services company. In August 2021, ZK Research surveyed more than 500 IT decision-makers in the U.S. across seven industries. IT decision-makers believe AIOps offers their organization several business benefits, including improved productivity, cloud application performance, and security.

Prior the pandemic, you could ask a dozen people what "the future of work" meant and get 13 different answers. Some insisted it was about distributing discrete responsibilities among two-pizza teams, while others preached about robots eliminating jobs and the need for universal basic income as compensation. Then COVID-19 pressed the fast-forward button, and we learned about the immediate, practical future of work in a hurry. The most obvious lesson – you don't need to be at the office to get stuff done – was already understood in tech, just never proven at scale. We're only starting to grasp the implications of that real-world confirmation.

The year 2020 has inarguably been an unprecedented year for humanity. With a global pandemic upending people's lives, the cyber world has been no less affected. On the upside, the virus-enforced digital transition in nearly all aspects of our lives has created massive momentum and scale for the uptake of cyber technologies. However, the downside is the increased opportunities this creates for unethical hackers and cyber criminals. In this backdrop, how is the cyber security landscape going to unfold this year?

Planning as satisfiability is a principal approach to planning with many eminent advantages. The existing planning as satisfiability techniques usually use encodings compiled from STRIPS. We introduce a novel SAT encoding scheme (SASE) based on the SAS+ formalism. The new scheme exploits the structural information in SAS+, resulting in an encoding that is both more compact and efficient for planning. We prove the correctness of the new encoding by establishing an isomorphism between the solution plans of SASE and that of STRIPS based encodings. We further analyze the transition variables newly introduced in SASE to explain why it accommodates modern SAT solving algorithms and improves performance. We give empirical statistical results to support our analysis. We also develop a number of techniques to further reduce the encoding size of SASE, and conduct experimental studies to show the strength of each individual technique. Finally, we report extensive experimental results to demonstrate significant improvements of SASE over the state-of-the-art STRIPS based encoding schemes in terms of both time and memory efficiency.

Planning as satisfiability is a principal approach to planning with many eminent advantages. The existing planning as satisfiability techniques usually use encodings compiled from the STRIPS formalism. We introduce a novel SAT encoding scheme based on the SAS+ formalism. It exploits the structural information in the SAS+ formalism, resulting in more compact SAT instances and reducing the number of clauses by up to 50 fold. Our results show that this encoding scheme improves upon the STRIPS-based encoding, in terms of both time and memory efficiency.