Large language models (LLMs) are often trained on extensive, temporally indiscriminate text corpora, reflecting the lack of datasets with temporal metadata. This approach is not aligned with the evolving nature of language. Conventional methods for creating temporally adapted language models often depend on further pre-training static models on time-specific data. This paper presents a new approach: a series of point-in-time LLMs called Time Machine GPT (TiMaGPT), specifically designed to be nonprognosticative. This ensures they remain uninformed about future factual information and linguistic changes. This strategy is beneficial for understanding language evolution and is of critical importance when applying models in dynamic contexts, such as time-series forecasting, where foresight of future information can prove problematic. We provide access to both the models and training datasets.

This paper presents a novel 3D myopic coverage path planning algorithm for lunar micro-rovers that can explore unknown environments with limited sensing and computational capabilities. The algorithm expands upon traditional non-graph path planning methods to accommodate the complexities of lunar terrain, utilizing global data with local topographic features into motion cost calculations. The algorithm also integrates localization and mapping to update the rover's pose and map the environment. The resulting environment map's accuracy is evaluated and tested in a 3D simulator. Outdoor field tests were conducted to validate the algorithm's efficacy in sim-to-real scenarios. The results showed that the algorithm could achieve high coverage with low energy consumption and computational cost, while incrementally exploring the terrain and avoiding obstacles. This study contributes to the advancement of path planning methodologies for space exploration, paving the way for efficient, scalable and autonomous exploration of lunar environments by small rovers.

There is growing interest in using machine learning (ML) methods for structural metamodeling due to the substantial computational cost of traditional simulations. Purely data-driven strategies often face limitations in model robustness, interpretability, and dependency on extensive data. To address these challenges, this paper introduces a novel physics-informed machine learning (PiML) method that integrates scientific principles and physical laws into deep neural networks to model seismic responses of nonlinear structures. The approach constrains the ML model's solution space within known physical bounds through three main features: dimensionality reduction via combined model order reduction and wavelet analysis, long short-term memory (LSTM) networks, and Newton's second law. Dimensionality reduction addresses structural systems' redundancy and boosts efficiency while extracting essential features through wavelet analysis. LSTM networks capture temporal dependencies for accurate time-series predictions. Manipulating the equation of motion helps learn system nonlinearities and confines solutions within physically interpretable results. These attributes allow for model training with sparse data, enhancing accuracy, interpretability, and robustness. Furthermore, a dataset of archetype steel moment resistant frames under seismic loading, available in the DesignSafe-CI Database [1], is considered for evaluation. The resulting metamodel handles complex data better than existing physics-guided LSTM models and outperforms other non-physics data-driven networks.

We present an approach called guaranteed block autoencoder that leverages Tensor Correlations (GBATC) for reducing the spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications. It uses a multidimensional block of tensors (spanning in space and time) for both input and output, capturing the spatiotemporal and interspecies relationship within a tensor. The tensor consists of species that represent different elements in a CFD simulation. To guarantee the error bound of the reconstructed data, principal component analysis (PCA) is applied to the residual between the original and reconstructed data. This yields a basis matrix, which is then used to project the residual of each instance. The resulting coefficients are retained to enable accurate reconstruction. Experimental results demonstrate that our approach can deliver two orders of magnitude in reduction while still keeping the errors of primary data under scientifically acceptable bounds. Compared to reduction-based approaches based on SZ, our method achieves a substantially higher compression ratio for a given error bound or a better error for a given compression ratio.

By integrating Artificial Intelligence (AI) with the Internet of Things (IoT), Artificial Intelligence of Things (AIoT) has revolutionized many fields. However, AIoT is facing the challenges of energy consumption and carbon emissions due to the continuous advancement of mobile technology. Fortunately, Generative AI (GAI) holds immense potential to reduce carbon emissions of AIoT due to its excellent reasoning and generation capabilities. In this article, we explore the potential of GAI for carbon emissions reduction and propose a novel GAI-enabled solution for low-carbon AIoT. Specifically, we first study the main impacts that cause carbon emissions in AIoT, and then introduce GAI techniques and their relations to carbon emissions. We then explore the application prospects of GAI in low-carbon AIoT, focusing on how GAI can reduce carbon emissions of network components. Subsequently, we propose a Large Language Model (LLM)-enabled carbon emission optimization framework, in which we design pluggable LLM and Retrieval Augmented Generation (RAG) modules to generate more accurate and reliable optimization problems. Furthermore, we utilize Generative Diffusion Models (GDMs) to identify optimal strategies for carbon emission reduction. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we insightfully provide open research directions for low-carbon AIoT.

Complex systems often show macroscopic coherent behavior due to the interactions of microscopic agents like molecules, cells, or individuals in a population with their environment. However, simulating such systems poses several computational challenges during simulation as the underlying dynamics vary and span wide spatiotemporal scales of interest. To capture the fast-evolving features, finer time steps are required while ensuring that the simulation time is long enough to capture the slow-scale behavior, making the analyses computationally unmanageable. This paper showcases how deep learning techniques can be used to develop a precise time-stepping approach for multiscale systems using the joint discovery of coordinates and flow maps. While the former allows us to represent the multiscale dynamics on a representative basis, the latter enables the iterative time-stepping estimation of the reduced variables. The resulting framework achieves state-of-the-art predictive accuracy while incurring lesser computational costs. We demonstrate this ability of the proposed scheme on the large-scale Fitzhugh Nagumo neuron model and the 1D Kuramoto-Sivashinsky equation in the chaotic regime.

For green AI, it is crucial to measure and reduce the carbon footprint emitted during the training of large language models. In NLP, performing pre-training on Transformer models requires significant computational resources. This pre-training involves using a large amount of text data to gain prior knowledge for performing downstream tasks. Thus, it is important that we select the correct data in the form of domain-specific data from this vast corpus to achieve optimum results aligned with our domain-specific tasks. While training on large unsupervised data is expensive, it can be optimized by performing a data selection step before pretraining. Selecting important data reduces the space overhead and the substantial amount of time required to pre-train the model while maintaining constant accuracy. We investigate the existing selection strategies and propose our own domain-adaptive data selection method - TextGram - that effectively selects essential data from large corpora. We compare and evaluate the results of finetuned models for text classification task with and without data selection. We show that the proposed strategy works better compared to other selection methods.

The Robot Operating System (ROS) pubsub model played a pivotal role in developing sophisticated robotic applications. However, the complexities and real-time demands of modern robotics necessitate more efficient communication solutions that are deterministic and isochronous. This article introduces a groundbreaking approach: embedding ROS 2 message-passing infrastructure directly onto a specialized hardware chip, significantly enhancing speed and efficiency in robotic communications. Our FPGA prototypes of the chip design can send or receive packages in less than 2.5 microseconds, accelerating networking communications by more than 62x on average and improving energy consumption by more than 500x when compared to traditional ROS 2 software implementations on modern CPUs. Additionally, it dramatically reduces maximum latency in ROS 2 networking communication by more than 30,000x. In situations of peak latency, our design guarantees an isochronous response within 11 microseconds, a stark improvement over the potential hundreds of milliseconds reported by modern CPU systems under similar conditions.

Recent language models use subwording mechanisms to handle Out-of-Vocabulary(OOV) words seen during test time and, their generation capacity is generally measured using perplexity, an intrinsic metric. It is known that increasing the subword granularity results in a decrease of perplexity value. However, the study of how subwording affects the understanding capacity of language models has been very few and only limited to a handful of languages. To reduce this gap we used 6 different tokenization schemes to pretrain relatively small language models in Nepali and used the representations learned to finetune on several downstream tasks. Although byte-level BPE algorithm has been used in recent models like GPT, RoBERTa we show that on average they are sub-optimal in comparison to algorithms such as SentencePiece in finetuning performances for Nepali. Additionally, similar recent studies have focused on the Bert-based language model. We, however, pretrain and finetune sequential transformer-based language models.

Land cover analysis using hyperspectral images (HSI) remains an open problem due to their low spatial resolution and complex spectral information. Recent studies are primarily dedicated to designing Transformer-based architectures for spatial-spectral long-range dependencies modeling, which is computationally expensive with quadratic complexity. Selective structured state space model (Mamba), which is efficient for modeling long-range dependencies with linear complexity, has recently shown promising progress. However, its potential in hyperspectral image processing that requires handling numerous spectral bands has not yet been explored. In this paper, we innovatively propose S$^2$Mamba, a spatial-spectral state space model for hyperspectral image classification, to excavate spatial-spectral contextual features, resulting in more efficient and accurate land cover analysis. In S$^2$Mamba, two selective structured state space models through different dimensions are designed for feature extraction, one for spatial, and the other for spectral, along with a spatial-spectral mixture gate for optimal fusion. More specifically, S$^2$Mamba first captures spatial contextual relations by interacting each pixel with its adjacent through a Patch Cross Scanning module and then explores semantic information from continuous spectral bands through a Bi-directional Spectral Scanning module. Considering the distinct expertise of the two attributes in homogenous and complicated texture scenes, we realize the Spatial-spectral Mixture Gate by a group of learnable matrices, allowing for the adaptive incorporation of representations learned across different dimensions. Extensive experiments conducted on HSI classification benchmarks demonstrate the superiority and prospect of S$^2$Mamba. The code will be available at: https://github.com/PURE-melo/S2Mamba.