The evolution of artificial intelligence (AI) and neural network theories has revolutionized the way software is programmed, shifting from a hard-coded series of codes to a vast neural network. However, this transition in engineering software has faced challenges such as data scarcity, multi-modality of data, low model accuracy, and slow inference. Here, we propose a new network based on interpolation theories and tensor decomposition, the interpolating neural network (INN). Instead of interpolating training data, a common notion in computer science, INN interpolates interpolation points in the physical space whose coordinates and values are trainable. It can also extrapolate if the interpolation points reside outside of the range of training data and the interpolation functions have a larger support domain. INN features orders of magnitude fewer trainable parameters, faster training, a smaller memory footprint, and higher model accuracy compared to feed-forward neural networks (FFNN) or physics-informed neural networks (PINN). INN is poised to usher in Engineering Software 2.0, a unified neural network that spans various domains of space, time, parameters, and initial/boundary conditions. This has previously been computationally prohibitive due to the exponentially growing number of trainable parameters, easily exceeding the parameter size of ChatGPT, which is over 1 trillion. INN addresses this challenge by leveraging tensor decomposition and tensor product, with adaptable network architecture.

While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve state-of-the-art results through fine-tuning but struggle with extending to few-shot and zero-shot settings due to their architectural constraints. Hence, we propose Statement-Tuning, a technique that models discriminative tasks as a set of finite statements and trains an Encoder model to discriminate between the potential statements to determine the label. We do Statement-Tuning on multiple tasks to enable cross-task generalization. Experimental results demonstrate that Statement Tuning achieves competitive performance compared to state-of-the-art LLMs with significantly fewer parameters. Moreover, the study investigates the impact of several design choices on few-shot and zero-shot generalization, revealing that Statement Tuning can achieve sufficient performance with modest training data and benefits from task and statement diversity for unseen task generalizability.

Zero-shot cross-lingual knowledge transfer enables a multilingual pretrained language model, finetuned on a task in one language, make predictions for this task in other languages. While being broadly studied for natural language understanding tasks, the described setting is understudied for generation. Previous works notice a frequent problem of generation in a wrong language and propose approaches to address it, usually using mT5 as a backbone model. In this work we compare various approaches proposed from the literature in unified settings, also including alternative backbone models, namely mBART and NLLB-200. We first underline the importance of tuning learning rate used for finetuning, which helps to substantially alleviate the problem of generation in the wrong language. Then, we show that with careful learning rate tuning, the simple full finetuning of the model acts as a very strong baseline and alternative approaches bring only marginal improvements. Finally, we find that mBART performs similarly to mT5 of the same size, and NLLB-200 can be competitive in some cases. Our final zero-shot models reach the performance of the approach based on data translation which is usually considered as an upper baseline for zero-shot cross-lingual transfer in generation.

We present the first self-supervised multilingual speech model trained exclusively on African speech. The model learned from nearly 60 000 hours of unlabeled speech segments in 21 languages and dialects spoken in sub-Saharan Africa. On the SSA subset of the FLEURS-102 dataset, our approach based on a HuBERT$_{base}$ (0.09B) architecture shows competitive results, for ASR downstream task, compared to the w2v-bert-51 (0.6B) pre-trained model proposed in the FLEURS benchmark, while being more efficient by using 7x less data and 6x less parameters. Furthermore, in the context of a LID downstream task, our approach outperforms FLEURS baselines accuracy by over 22\%.

With the advancements of Artifical Intelligence (AI) and Natural Language Processing (NLP) in the past decades, especially the rising of Large Language Model (LLM) and multimodality learning, softwrare engineering fields welcome AI techniques to be employed to every aspects of software cycles. Meanwhile, the research of intelligent applications has continuously been a hotspot (Zhao et al., 2021) because of the increasing amount of data of multimodalities generated in various domains. This type of software is designed to adapt to constantly changing scenarios of rich context (Zhao et al., 2021; Yue and Smith, 2021), and some examples are listed in part C of figure 1. One primary characteristic of those applications is that a great portion of their system behaviors is learned from continuous interaction with the users and environment involving detection and analysis of states and activities (Tzafestas, 2012; Yang and Newman, 2013; Cassavia et al., 2017), unlike applications of banking or insurance with more matured and stable business logic. The rapid evolution of hardware and software wheels bring more capabilities to intelligent applications meanwhile making the creation and maintenance of that software more intricate (Chu et al., 2021; Zheng et al., 2023), both fields of software engineering and intelligent applications are eager for breakthroughs in higher-level automation (HLA) - collaboratively resolving the challenges by benefiting from AI techniques.

We have developed the world's first canopy height map of the distribution area of world-level giant trees. This mapping is crucial for discovering more individual and community world-level giant trees, and for analyzing and quantifying the effectiveness of biodiversity conservation measures in the Yarlung Tsangpo Grand Canyon (YTGC) National Nature Reserve. We proposed a method to map the canopy height of the primeval forest within the world-level giant tree distribution area by using a spaceborne LiDAR fusion satellite imagery (Global Ecosystem Dynamics Investigation (GEDI), ICESat-2, and Sentinel-2) driven deep learning modeling. And we customized a pyramid receptive fields depth separable CNN (PRFXception). PRFXception, a CNN architecture specifically customized for mapping primeval forest canopy height to infer the canopy height at the footprint level of GEDI and ICESat-2 from Sentinel-2 optical imagery with a 10-meter spatial resolution. We conducted a field survey of 227 permanent plots using a stratified sampling method and measured several giant trees using UAV-LS. The predicted canopy height was compared with ICESat-2 and GEDI validation data (RMSE =7.56 m, MAE=6.07 m, ME=-0.98 m, R^2=0.58 m), UAV-LS point clouds (RMSE =5.75 m, MAE =3.72 m, ME = 0.82 m, R^2= 0.65 m), and ground survey data (RMSE = 6.75 m, MAE = 5.56 m, ME= 2.14 m, R^2=0.60 m). We mapped the potential distribution map of world-level giant trees and discovered two previously undetected giant tree communities with an 89% probability of having trees 80-100 m tall, potentially taller than Asia's tallest tree. This paper provides scientific evidence confirming southeastern Tibet--northwestern Yunnan as the fourth global distribution center of world-level giant trees initiatives and promoting the inclusion of the YTGC giant tree distribution area within the scope of China's national park conservation.

We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. Though we find evidence of data contamination with Claude on FLORES-200, we curate new benchmarks that corroborate the effectiveness of Claude for low-resource machine translation into English. We find that Claude has remarkable \textit{resource efficiency} -- the degree to which the quality of the translation model depends on a language pair's resource level. Finally, we show that advancements in LLM translation can be compressed into traditional neural machine translation (NMT) models. Using Claude to generate synthetic data, we demonstrate that knowledge distillation advances the state-of-the-art in Yoruba-English translation, meeting or surpassing strong baselines like NLLB-54B and Google Translate.

In the last year or so (and going back many decades) there has been extensive claims by major computational scientists, engineers, and others that AGI (artificial general intelligence) is 5 or 10 years away, but without a scintilla of scientific evidence, for a broad body of these claims: Computers will become conscious, have a "theory of mind," think and reason, will become more intelligent than humans, and so on. But the claims are science fiction, not science. This article reviews evidence for the following three (3) propositions using extensive body of scientific research and related sources from the cognitive and neurosciences; evolutionary evidence; linguistics; data science; comparative psychology; self-driving cars, and robotics; and the learning sciences.

Multifidelity surrogate modelling combines data of varying accuracy and cost from different sources. It strategically uses low-fidelity models for rapid evaluations, saving computational resources, and high-fidelity models for detailed refinement. It improves decision-making by addressing uncertainties and surpassing the limits of single-fidelity models, which either oversimplify or are computationally intensive. Blending high-fidelity data for detailed responses with frequent low-fidelity data for quick approximations facilitates design optimisation in various domains. Despite progress in interpolation, regression, enhanced sampling, error estimation, variable fidelity, and data fusion techniques, challenges persist in selecting fidelity levels and developing efficient data fusion methods. This study proposes a new fusion approach to construct multi-fidelity surrogate models by constructing gradient-only surrogates that use only gradients to construct regression surfaces. Results are demonstrated on foundational example problems that isolate and illustrate the fusion approach's efficacy, avoiding the need for complex examples that obfuscate the main concept.

This work is motivated by recent developments in Deep Neural Networks, particularly the Transformer architectures underlying applications such as ChatGPT, and the need for performing inference on mobile devices. Focusing on emerging transformers (specifically the ones with computationally efficient Swin-like architectures) and large models (e.g., Stable Diffusion and LLMs) based on transformers, we observe that layout transformations between the computational operators cause a significant slowdown in these applications. This paper presents SmartMem, a comprehensive framework for eliminating most layout transformations, with the idea that multiple operators can use the same tensor layout through careful choice of layout and implementation of operations. Our approach is based on classifying the operators into four groups, and considering combinations of producer-consumer edges between the operators. We develop a set of methods for searching such layouts. Another component of our work is developing efficient memory layouts for 2.5 dimensional memory commonly seen in mobile devices. Our experimental results show that SmartMem outperforms 5 state-of-the-art DNN execution frameworks on mobile devices across 18 varied neural networks, including CNNs, Transformers with both local and global attention, as well as LLMs. In particular, compared to DNNFusion, SmartMem achieves an average speedup of 2.8$\times$, and outperforms TVM and MNN with speedups of 6.9$\times$ and 7.9$\times$, respectively, on average.