The tremendous success of chat-based AI systems like ChatGPT, Claude, and Gemini stems from Large Language Models (LLMs) trained on vast amount of datasets. However, acquiring high-quality, diverse, and ethically sourced training data remains a significant challenge. We introduce the Open Artificial Knowledge (OAK) dataset, a large-scale resource of over 500 million tokens (at the moment of writing) designed to address this issue. OAK leverages an ensemble of state-of-the-art LLMs, including GPT4o, LLaMa3-70B, LLaMa3-8B, Mixtral-8x7B, Gemma-7B, and Gemma-2-9B , to generate high-quality text across diverse domains, guided by Wikipedia's main categories. Our methodology ensures broad knowledge coverage while maintaining coherence and factual accuracy. The OAK dataset aims to foster the development of more capable and aligned language models while addressing critical issues of data scarcity and privacy in LLM training, and it is freely available on www.oakdataset.org.

Remarkable progress in the development of Deep Learning Weather Prediction (DLWP) models positions them to become competitive with traditional numerical weather prediction (NWP) models. Indeed, a wide number of DLWP architectures -- based on various backbones, including U-Net, Transformer, Graph Neural Network (GNN), and Fourier Neural Operator (FNO) -- have demonstrated their potential at forecasting atmospheric states. However, due to differences in training protocols, forecast horizons, and data choices, it remains unclear which (if any) of these methods and architectures are most suitable for weather forecasting and for future model development. Here, we step back and provide a detailed empirical analysis, under controlled conditions, comparing and contrasting the most prominent DLWP models, along with their backbones. We accomplish this by predicting synthetic two-dimensional incompressible Navier-Stokes and real-world global weather dynamics. In terms of accuracy, memory consumption, and runtime, our results illustrate various tradeoffs. For example, on synthetic data, we observe favorable performance of FNO; and on the real-world WeatherBench dataset, our results demonstrate the suitability of ConvLSTM and SwinTransformer for short-to-mid-ranged forecasts. For long-ranged weather rollouts of up to 365 days, we observe superior stability and physical soundness in architectures that formulate a spherical data representation, i.e., GraphCast and Spherical FNO. In addition, we observe that all of these model backbones ``saturate,'' i.e., none of them exhibit so-called neural scaling, which highlights an important direction for future work on these and related models.

Star scientists are highly influential researchers who have made significant contributions to their field, gained widespread recognition, and often attracted substantial research funding. They are critical for the advancement of science and innovation, and they have a significant influence on the transfer of knowledge and technology to industry. Identifying potential star scientists before their performance becomes outstanding is important for recruitment, collaboration, networking, or research funding decisions. Using machine learning techniques, this study proposes a model to predict star scientists in the field of artificial intelligence while highlighting features related to their success. Our results confirm that rising stars follow different patterns compared to their non-rising stars counterparts in almost all the early-career features. We also found that certain features such as gender and ethnic diversity play important roles in scientific collaboration and that they can significantly impact an author's career development and success. The most important features in predicting star scientists in the field of artificial intelligence were the number of articles, group discipline diversity, and weighted degree centrality. The proposed approach offers valuable insights for researchers, practitioners, and funding agencies interested in identifying and supporting talented researchers.

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can benefit reinforcement learning from human feedback (RLHF) on language models (LMs). In this work, we propose training reward models (RMs) in a contrastive, $\textit{goal-conditioned}$ fashion by increasing the representation similarity of future states along sampled preferred trajectories and decreasing the similarity along randomly sampled dispreferred trajectories. This objective significantly improves RM performance by up to 0.09 AUROC across challenging benchmarks, such as MATH and GSM8k. These findings extend to general alignment as well -- on the Helpful-Harmless dataset, we observe $2.3\%$ increase in accuracy. Beyond improving reward model performance, we show this way of training RM representations enables improved $\textit{steerability}$ because it allows us to evaluate the likelihood of an action achieving a particular goal-state (e.g., whether a solution is correct or helpful). Leveraging this insight, we find that we can filter up to $55\%$ of generated tokens during majority voting by discarding trajectories likely to end up in an "incorrect" state, which leads to significant cost savings. We additionally find that these representations can perform fine-grained control by conditioning on desired future goal-states. For example, we show that steering a Llama 3 model towards helpful generations with our approach improves helpfulness by $9.6\%$ over a supervised-fine-tuning trained baseline. Similarly, steering the model towards complex generations improves complexity by $21.6\%$ over the baseline. Overall, we find that training RMs in this contrastive, goal-conditioned fashion significantly improves performance and enables model steerability.

Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization (DPO) to mitigate gender, racial, and religious biases in LLM-generated English text. By developing a loss function that favors less biased over biased completions, our approach cultivates a preference for respectful and non-discriminatory language in LLMs. We also contribute a manually designed dataset for training LLMs to recognize and correct biases. This dataset encompasses a diverse range of prompts paired with both biased and unbiased completions. Implementing this approach on the Microsoft Phi-2 model, we demonstrate substantial reductions in biased outputs as our model outperforms the baseline model on almost all bias benchmarks. Our model also achieves better performance compared to other open-source models on most benchmarks. By reducing biases in the language generated by the model, our study marks a significant step towards developing more ethical and socially responsible LLMs. We publicly release BiasDPO dataset on HuggingFace.

Medical imaging technologies have undergone extensive development, enabling non-invasive visualization of clinical information. The traditional review of medical images by clinicians remains subjective, time-consuming, and prone to human error. With the recent availability of medical imaging data, quantification have become important goals in the field. Radiomics, a methodology aimed at extracting quantitative information from imaging data, has emerged as a promising approach to uncover hidden biological information and support decision-making in clinical practice. This paper presents a review of the radiomic pipeline from the clinical neuroimaging perspective, providing a detailed overview of each step with practical advice. It discusses the application of handcrafted and deep radiomics in neuroimaging, stratified by neurological diagnosis. Although radiomics shows great potential for increasing diagnostic precision and improving treatment quality in neurology, several limitations hinder its clinical implementation. Addressing these challenges requires collaborative efforts, advancements in image harmonization methods, and the establishment of reproducible and standardized pipelines with transparent reporting. By overcoming these obstacles, radiomics can significantly impact clinical neurology and enhance patient care.

This study presents novel predictive models using Graph Neural Networks (GNNs) for simulating thermal dynamics in Laser Powder Bed Fusion (L-PBF) processes. By developing and validating Single-Laser GNN (SL-GNN) and Multi-Laser GNN (ML-GNN) surrogates, the research introduces a scalable data-driven approach that learns fundamental physics from small-scale Finite Element Analysis (FEA) simulations and applies them to larger domains. Achieving a Mean Absolute Percentage Error (MAPE) of 3.77% with the baseline SL-GNN model, GNNs effectively learn from high-resolution simulations and generalize well across larger geometries. The proposed models capture the complexity of the heat transfer process in L-PBF while significantly reducing computational costs. For example, a thermomechanical simulation for a 2 mm x 2 mm domain typically requires about 4 hours, whereas the SL-GNN model can predict thermal distributions almost instantly. Calibrating models to larger domains enhances predictive performance, with significant drops in MAPE for 3 mm x 3 mm and 4 mm x 4 mm domains, highlighting the scalability and efficiency of this approach. Additionally, models show a decreasing trend in Root Mean Square Error (RMSE) when tuned to larger domains, suggesting potential for becoming geometry-agnostic. The interaction of multiple lasers complicates heat transfer, necessitating larger model architectures and advanced feature engineering. Using hyperparameters from Gaussian process-based Bayesian optimization, the best ML-GNN model demonstrates a 46.4% improvement in MAPE over the baseline ML-GNN model. In summary, this approach enables more efficient and flexible predictive modeling in L-PBF additive manufacturing.

API call generation is the cornerstone of large language models' tool-using ability that provides access to the larger world. However, existing supervised and in-context learning approaches suffer from high training costs, poor data efficiency, and generated API calls that can be unfaithful to the API documentation and the user's request. To address these limitations, we propose an output-side optimization approach called FANTASE. Two of the unique contributions of FANTASE are its State-Tracked Constrained Decoding (SCD) and Reranking components. SCD dynamically incorporates appropriate API constraints in the form of Token Search Trie for efficient and guaranteed generation faithfulness with respect to the API documentation. The Reranking component efficiently brings in the supervised signal by leveraging a lightweight model as the discriminator to rerank the beam-searched candidate generations of the large language model. We demonstrate the superior performance of FANTASE in API call generation accuracy, inference efficiency, and context efficiency with DSTC8 and API Bank datasets.

As Artificial Intelligence (AI) increasingly integrates into our daily lives, fairness has emerged as a critical concern, particularly in medical AI, where datasets often reflect inherent biases due to social factors like the underrepresentation of marginalized communities and socioeconomic barriers to data collection. Traditional approaches to mitigating these biases have focused on data augmentation and the development of fairness-aware training algorithms. However, this paper argues that the architecture of neural networks, a core component of Machine Learning (ML), plays a crucial role in ensuring fairness. We demonstrate that addressing fairness effectively requires a holistic approach that simultaneously considers data, algorithms, and architecture. Utilizing Automated ML (AutoML) technology, specifically Neural Architecture Search (NAS), we introduce a novel framework, BiaslessNAS, designed to achieve fair outcomes in analyzing skin lesion datasets. BiaslessNAS incorporates fairness considerations at every stage of the NAS process, leading to the identification of neural networks that are not only more accurate but also significantly fairer. Our experiments show that BiaslessNAS achieves a 2.55% increase in accuracy and a 65.50% improvement in fairness compared to traditional NAS methods, underscoring the importance of integrating fairness into neural network architecture for better outcomes in medical AI applications.

This paper presents the contribution of our dzNLP team to the NADI 2024 shared task, specifically in Subtask 1 - Multi-label Country-level Dialect Identification (MLDID) (Closed Track). We explored various configurations to address the challenge: in Experiment 1, we utilized a union of n-gram analyzers (word, character, character with word boundaries) with different n-gram values; in Experiment 2, we combined a weighted union of Term Frequency-Inverse Document Frequency (TF-IDF) features with various weights; and in Experiment 3, we implemented a weighted major voting scheme using three classifiers: Linear Support Vector Classifier (LSVC), Random Forest (RF), and K-Nearest Neighbors (KNN). Our approach, despite its simplicity and reliance on traditional machine learning techniques, demonstrated competitive performance in terms of F1-score and precision. Notably, we achieved the highest precision score of 63.22% among the participating teams. However, our overall F1 score was approximately 21%, significantly impacted by a low recall rate of 12.87%. This indicates that while our models were highly precise, they struggled to recall a broad range of dialect labels, highlighting a critical area for improvement in handling diverse dialectal variations.