We introduce and train distributed neural architectures (DNA) in vision and language domains. DNAs are initialized with a proto-architecture that consists of (transformer, MLP, attention, etc.) modules and routers. Any token (or patch) can traverse any series of modules in any order. DNAs are a natural generalization of the sparse methods such as Mixture-of-Experts, Mixture-of-Depths, parameter sharing, etc. Computation and communication patterns of DNA modules are learnt end-to-end during training and depend on the content and context of each token (or patch). These patterns can be shaped by further requirements added to the optimization objective such as compute/memory efficiency or load balancing. We empirically show that (i) trained DNAs are competitive with the dense baselines in both domains and (ii) compute efficiency/parameter sharing can be learnt from data. Next, we analyze the emergent connectivity and computation patterns in the trained DNAs. We find that the paths that tokens take through the models are themselves distributed according to a power-law. We show that some paths (or, equivalently, groups of modules) show emergent specialization. Finally, we demonstrate that models learn to allocate compute and active parameters in an interpretable way.

Hearables are wearable computers that are worn on the ear. Bone conduction microphones (BCMs) are used with air conduction microphones (ACMs) in hearables as a supporting modality for multimodal speech enhancement (SE) in noisy conditions. However, existing works don't consider the following practical aspects for low-power implementations on hearables: (i) They do not explore how lowering the sampling frequencies and bit resolutions in analog-to-digital converters (ADCs) of hearables jointly impact low-power processing and multimodal SE in terms of speech quality and intelligibility. (ii) They don't discuss how GAN-like audio quality can be achieved without using actual GAN discriminators. And (iii) They don't process signals from ACMs/BCMs at sub-Nyquist sampling rate because, in their frameworks, they lack a wideband reconstruction methodology from their narrowband parts. We propose SUBARU (\textbf{Sub}-Nyquist \textbf{A}udio \textbf{R}esolution \textbf{U}psampling), which achieves the following: SUBARU (i) intentionally uses sub-Nyquist sampling and low bit resolution in ADCs, achieving a 3.31x reduction in power consumption; (ii) introduces novel multi-scale and multi-period virtual discriminators, which achieve GAN-like audio quality without using GANs' adversarial training; and (iii) achieves streaming operations on mobile platforms and SE in in-the-wild noisy conditions with an inference time of 1.74ms and a memory footprint of less than 13.77MB.

Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images acquired by improving sensing and imaging technologies become available. However, accurate semantic segmentation of such FRRS images is greatly affected by substantial class disparities, the invisibility of key ground objects due to occlusion, and object size variation. Despite the extraordinary potential in deep convolutional neural networks (DCNNs) in image feature learning and representation, extracting sufficient features from FRRS images for accurate semantic segmentation is still challenging. These challenges demand the deep learning models to learn robust features and generate sufficient feature descriptors. Specifically, learning multi-contextual features to guarantee adequate coverage of varied object sizes from the ground scene and harnessing global-local contexts to overcome class disparities challenge even profound networks. Deeper networks significantly lose spatial details due to gradual downsampling processes resulting in poor segmentation results and coarse boundaries. This article presents a stacked deep residual network (SDRNet) for semantic segmentation from FRRS images. The proposed framework utilizes two stacked encoder-decoder networks to harness long-range semantics yet preserve spatial information and dilated residual blocks (DRB) between each encoder and decoder network to capture sufficient global dependencies thus improving segmentation performance. Our experimental results obtained using the ISPRS Vaihingen and Potsdam datasets demonstrate that the SDRNet performs effectively and competitively against current DCNNs in semantic segmentation.

With the rapid development of the low-altitude economy, air-ground integrated multi-access edge computing (MEC) systems are facing increasing demands for real-time and intelligent task scheduling. In such systems, task offloading and resource allocation encounter multiple challenges, including node heterogeneity, unstable communication links, and dynamic task variations. To address these issues, this paper constructs a three-layer heterogeneous MEC system architecture for low-altitude economic networks, encompassing aerial and ground users as well as edge servers. The system is systematically modeled from the perspectives of communication channels, computational costs, and constraint conditions, and the joint optimization problem of offloading decisions and resource allocation is uniformly abstracted into a graph-structured modeling task. On this basis, we propose a graph attention diffusion-based solution generator (GADSG). This method integrates the contextual awareness of graph attention networks with the solution distribution learning capability of diffusion models, enabling joint modeling and optimization of discrete offloading variables and continuous resource allocation variables within a high-dimensional latent space. We construct multiple simulation datasets with varying scales and topologies. Extensive experiments demonstrate that the proposed GADSG model significantly outperforms existing baseline methods in terms of optimization performance, robustness, and generalization across task structures, showing strong potential for efficient task scheduling in dynamic and complex low-altitude economic network environments.

Laser powder bed fusion (L-PBF) is a widely recognized additive manufacturing technology for producing intricate metal components with exceptional accuracy. A key challenge in L-PBF is the formation of complex microstructures affecting product quality. We propose a physics-guided, machine-learning approach to optimize scan paths for desired microstructure outcomes, such as equiaxed grains. We utilized a phase-field method (PFM) to model crystalline grain structure evolution. To reduce computational costs, we trained a surrogate machine learning model, a 3D U-Net convolutional neural network, using single-track phase-field simulations with various laser powers to predict crystalline grain orientations based on initial microstructure and thermal history. We investigated three scanning strategies across various hatch spacings within a square domain, achieving a two-orders-of-magnitude speedup using the surrogate model. To reduce trial and error in designing laser scan toolpaths, we used deep reinforcement learning (DRL) to generate optimized scan paths for target microstructure. Results from three cases demonstrate the DRL approach's effectiveness. We integrated the surrogate 3D U-Net model into our DRL environment to accelerate the reinforcement learning training process. The reward function minimizes both aspect ratio and grain volume of the predicted microstructure from the agent's scan path. The reinforcement learning algorithm was benchmarked against conventional zigzag approach for smaller and larger domains, showing machine learning methods' potential to enhance microstructure control and computational efficiency in L-PBF optimization.

Graph foundation models using graph neural networks promise sustainable, efficient atomistic modeling. To tackle challenges of processing multi-source, multi-fidelity data during pre-training, recent studies employ multi-task learning, in which shared message passing layers initially process input atomistic structures regardless of source, then route them to multiple decoding heads that predict data-specific outputs. This approach stabilizes pre-training and enhances a model's transferability to unexplored chemical regions. Preliminary results on approximately four million structures are encouraging, yet questions remain about generaliz-ability to larger, more diverse datasets and scalability on supercomputers. We propose a multi-task parallelism method that distributes each head across computing resources with GPU acceleration. Implemented in the open-source HydraGNN architecture, our method was trained on over 24 million structures from five datasets and tested on the Perlmut-ter, Aurora, and Frontier supercomputers, demonstrating efficient scaling on all three highly heterogeneous super-computing architectures. Keywords: Graph Neural Networks Distributed Data Parallelism Model Parallelism Multi-Fidelity Data Atomistic Modeling.

Evaluation benchmark characteristics may distort the true benefits of domain adaptation in retrieval models. This creates misleading assessments that influence deployment decisions in specialized domains. We show that two benchmarks with drastically different features such as topic diversity, boundary overlap, and semantic complexity can influence the perceived benefits of fine-tuning. Using environmental regulatory document retrieval as a case study, we fine-tune ColBERTv2 model on Environmental Impact Statements (EIS) from federal agencies. We evaluate these models across two benchmarks with different semantic structures. Our findings reveal that identical domain adaptation approaches show very different perceived benefits depending on evaluation methodology. On one benchmark, with clearly separated topic boundaries, domain adaptation shows small improvements (maximum 0.61% NDCG gain). However, on the other benchmark with overlapping semantic structures, the same models demonstrate large improvements (up to 2.22% NDCG gain), a 3.6-fold difference in the performance benefit. We compare these benchmarks through topic diversity metrics, finding that the higher-performing benchmark shows 11% higher average cosine distances between contexts and 23% lower silhouette scores, directly contributing to the observed performance difference. These results demonstrate that benchmark selection strongly determines assessments of retrieval system effectiveness in specialized domains. Evaluation frameworks with well-separated topics regularly underestimate domain adaptation benefits, while those with overlapping semantic boundaries reveal improvements that better reflect real-world regulatory document complexity. Our findings have important implications for developing and deploying AI systems for interdisciplinary domains that integrate multiple topics.

The sixth generation of Fairphone arrived this week, featuring a modular design built to last from ethically sourced components in a climate-conscious way. It has been a couple of years since its predecessor, the Fairphone 5, and the Fairphone 6 is refreshingly smaller and lighter. It boasts a 6.3-inch OLED screen with a 120-Hz adaptive refresh rate, a Qualcomm Snapdragon 7s Gen 3 processor, and a 4,415 mAh battery that Fairphone says is good for up to two days. You also get a 50-megapixel main camera with a 13-MP ultrawide lens and a 32-MP selfie camera. Fairphone says the new device is made with more than 50 percent fair and recycled materials, including cobalt sourced through the Fair Cobalt Alliance, fair gold, silver, and tungsten, and recycled aluminum and rare earth metals.

Google's carbon emissions have soared by 51% since 2019 as artificial intelligence hampers the tech company's efforts to go green. While the corporation has invested in renewable energy and carbon removal technology, it has failed to curb its scope 3 emissions, which are those further down the supply chain, and are in large part influenced by a growth in datacentre capacity required to power artificial intelligence. The company reported a 27% increase in year-on-year electricity consumption as it struggles to decarbonise as quickly as its energy needs increase. Datacentres play a crucial role in training and operating the models that underpin AI models such as Google's Gemini and OpenAI's GPT-4, which powers the ChatGPT chatbot. The International Energy Agency estimates that datacentres' total electricity consumption could double from 2022 levels to 1,000TWh (terawatt hours) in 2026, approximately Japan's level of electricity demand.

I put a bird feeder outside my window a few years ago and it was a fantastic decision. I can look out there and see a wide variety of feathered friends chowing down on the regionally appropriate bird food I provide for them. I also get to see squirrels acting foolish. Right now, Amazon has the Birdfy smart bird feeders on deep discount well before the Prime Day shopping holiday rolls around in early July. This is the easiest possible way to bird watch.