When I meet Sam Altman, the chief executive of AI research laboratory OpenAI, he is in the middle of a world tour. He is preaching that the very AI systems he and his competitors are building could pose an existential risk to the future of humanity – unless governments work together now to establish guide rails, ensuring responsible development over the coming decade. In the subsequent days, he and hundreds of tech leaders, including scientists and "godfathers of AI", Geoffrey Hinton and Yoshua Bengio, as well as Google's DeepMind CEO, Demis Hassabis, put out a statement saying that "mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war". It is an all-out effort to convince world leaders that they are serious when they say that "AI risk" needs concerted international effort. It must be an interesting position to be in – Altman, 38, is the daddy of AI chatbot ChatGPT, after all, and is leading the charge to create "artificial general intelligence", or AGI, an AI system capable of tackling any task a human can achieve.

Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. This seems to be true for both monolingual and multilingual models, although much less work has been done on the multilingual context. Why these outliers occur and how they affect the representations is still an active area of research. We investigate outlier dimensions and their relationship to anisotropy in multiple pre-trained multilingual language models. We focus on cross-lingual semantic similarity tasks, as these are natural tasks for evaluating multilingual representations. Specifically, we examine sentence representations. Sentence transformers which are fine-tuned on parallel resources (that are not always available) perform better on this task, and we show that their representations are more isotropic. However, we aim to improve multilingual representations in general. We investigate how much of the performance difference can be made up by only transforming the embedding space without fine-tuning, and visualise the resulting spaces. We test different operations: Removing individual outlier dimensions, cluster-based isotropy enhancement, and ZCA whitening. We publish our code for reproducibility.

Entailment Graphs (EGs) have been constructed based on extracted corpora as a strong and explainable form to indicate context-independent entailment relations in natural languages. However, EGs built by previous methods often suffer from the severe sparsity issues, due to limited corpora available and the long-tail phenomenon of predicate distributions. In this paper, we propose a multi-stage method, Typed Predicate-Entailment Graph Generator (TP-EGG), to tackle this problem. Given several seed predicates, TP-EGG builds the graphs by generating new predicates and detecting entailment relations among them. The generative nature of TP-EGG helps us leverage the recent advances from large pretrained language models (PLMs), while avoiding the reliance on carefully prepared corpora. Experiments on benchmark datasets show that TP-EGG can generate high-quality and scale-controllable entailment graphs, achieving significant in-domain improvement over state-of-the-art EGs and boosting the performance of down-stream inference tasks.

Solving inverse problems, where we find the input values that result in desired values of outputs, can be challenging. The solution process is often computationally expensive and it can be difficult to interpret the solution in high-dimensional input spaces. In this paper, we use a problem from additive manufacturing to address these two issues with the intent of making it easier to solve inverse problems and exploit their results. First, focusing on Gaussian process surrogates that are used to solve inverse problems, we describe how a simple modification to the idea of tapering can substantially speed up the surrogate without losing accuracy in prediction. Second, we demonstrate that Kohonen self-organizing maps can be used to visualize and interpret the solution to the inverse problem in the high-dimensional input space. For our data set, as not all input dimensions are equally important, we show that using weighted distances results in a better organized map that makes the relationships among the inputs obvious.

The shapes and morphological features of grains in sand assemblies have far-reaching implications in many engineering applications, such as geotechnical engineering, computer animations, petroleum engineering, and concentrated solar power. Yet, our understanding of the influence of grain geometries on macroscopic response is often only qualitative, due to the limited availability of high-quality 3D grain geometry data. In this paper, we introduce a denoising diffusion algorithm that uses a set of point clouds collected from the surface of individual sand grains to generate grains in the latent space. By employing a point cloud autoencoder, the three-dimensional point cloud structures of sand grains are first encoded into a lower-dimensional latent space. A generative denoising diffusion probabilistic model is trained to produce synthetic sand that maximizes the log-likelihood of the generated samples belonging to the original data distribution measured by a Kullback-Leibler divergence. Numerical experiments suggest that the proposed method is capable of generating realistic grains with morphology, shapes and sizes consistent with the training data inferred from an F50 sand database. We then use a rigid contact dynamic simulator to pour the synthetic sand in a confined volume to form granular assemblies in a static equilibrium state with targeted distribution properties. To ensure third-party validation, 50,000 synthetic sand grains and the 1,542 real synchrotron microcomputed tomography (SMT) scans of the F50 sand, as well as the granular assemblies composed of synthetic sand grains are made available in an open-source repository.

Tropical Cyclones (TCs) are counted among the most destructive phenomena that can be found in nature. Every year, globally an average of 90 TCs occur over tropical waters, and global warming is making them stronger, larger and more destructive. The accurate detection and tracking of such phenomena have become a relevant and interesting area of research in weather and climate science. Traditionally, TCs have been identified in large climate datasets through the use of deterministic tracking schemes that rely on subjective thresholds. Machine Learning (ML) models can complement deterministic approaches due to their ability to capture the mapping between the input climatic drivers and the geographical position of the TC center from the available data. This study presents a ML ensemble approach for locating TC center coordinates, embedding both TC classification and localization in a single end-to-end learning task. The ensemble combines TC center estimates of different ML models that agree about the presence of a TC in input data. ERA5 reanalysis were used for model training and testing jointly with the International Best Track Archive for Climate Stewardship records. Results showed that the ML approach is well-suited for TC detection providing good generalization capabilities on out of sample data. In particular, it was able to accurately detect lower TC categories than those used for training the models. On top of this, the ensemble approach was able to further improve TC localization performance with respect to single model TC center estimates, demonstrating the good capabilities of the proposed approach.

A new class of tools, colloquially called generative AI, can produce high-quality artistic media for visual arts, concept art, music, fiction, literature, video, and animation. The generative capabilities of these tools are likely to fundamentally alter the creative processes by which creators formulate ideas and put them into production. As creativity is reimagined, so too may be many sectors of society. Understanding the impact of generative AI - and making policy decisions around it - requires new interdisciplinary scientific inquiry into culture, economics, law, algorithms, and the interaction of technology and creativity. We argue that generative AI is not the harbinger of art's demise, but rather is a new medium with its own distinct affordances. In this vein, we consider the impacts of this new medium on creators across four themes: aesthetics and culture, legal questions of ownership and credit, the future of creative work, and impacts on the contemporary media ecosystem. Across these themes, we highlight key research questions and directions to inform policy and beneficial uses of the technology.

Due to data's unavailability or large size, and the high computational and human labor costs of training machine learning models, it is a common practice to rely on open source pre-trained models whenever possible. However, this practice is worry some from the security perspective. Pre-trained models can be infected with Trojan attacks, in which the attacker embeds a trigger in the model such that the model's behavior can be controlled by the attacker when the trigger is present in the input. In this paper, we present our preliminary work on a novel method for Trojan model detection. Our method creates a signature for a model based on activation optimization. A classifier is then trained to detect a Trojan model given its signature. Our method achieves state of the art performance on two public datasets.

Recent studies have revealed that NLP predictive models are vulnerable to adversarial attacks. Most existing studies focused on designing attacks to evaluate the robustness of NLP models in the English language alone. Literature has seen an increasing need for NLP solutions for other languages. We, therefore, ask one natural question: whether state-of-the-art (SOTA) attack methods generalize to other languages. This paper investigates how to adapt SOTA adversarial attack algorithms in English to the Chinese language. Our experiments show that attack methods previously applied to English NLP can generate high-quality adversarial examples in Chinese when combined with proper text segmentation and linguistic constraints. In addition, we demonstrate that the generated adversarial examples can achieve high fluency and semantic consistency by focusing on the Chinese language's morphology and phonology, which in turn can be used to improve the adversarial robustness of Chinese NLP models.

An important aspect of developing reliable deep learning systems is devising strategies that make these systems robust to adversarial attacks. There is a long line of work that focuses on developing defenses against these attacks, but recently, researchers have began to study ways to reverse engineer the attack process. This allows us to not only defend against several attack models, but also classify the threat model. However, there is still a lack of theoretical guarantees for the reverse engineering process. Current approaches that give any guarantees are based on the assumption that the data lies in a union of linear subspaces, which is not a valid assumption for more complex datasets. In this paper, we build on prior work and propose a novel framework for reverse engineering of deceptions which supposes that the clean data lies in the range of a GAN. To classify the signal and attack, we jointly solve a GAN inversion problem and a block-sparse recovery problem. For the first time in the literature, we provide deterministic linear convergence guarantees for this problem. We also empirically demonstrate the merits of the proposed approach on several nonlinear datasets as compared to state-of-the-art methods.