Foundation models rely on large-scale web-crawled datasets, which frequently contain noisy data, biases, and irrelevant content. Existing data selection techniques typically use human heuristics, downstream evaluation datasets, or specialized scoring models, and can overlook samples' utility in the training process. Instead, we propose a new approach, Mimic Score, a data quality metric that uses a pretrained reference model as a guide to assess the usefulness of data samples for training a new model. It relies on the alignment between the gradient of the new model parameters and the vector pointing toward the reference model in weight space. Samples that misalign with this direction are considered low-value and can be filtered out. Motivated by the Mimic score, we develop Grad-Mimic, a data selection framework that identifies and prioritizes useful samples, automating the selection process to create effective filters. Empirically, using Mimic scores to guide model training results in consistent performance gains across six image datasets and enhances the performance of CLIP models. Moreover, Mimic scores and their associated filters improve upon existing filtering methods and offer accurate estimation of dataset quality.

Data imputation is crucial for addressing challenges posed by missing values in multivariate time series data across various fields, such as healthcare, traffic, and economics, and has garnered significant attention. Among various methods, diffusion model-based approaches show notable performance improvements. However, existing methods often cause disharmonious boundaries between missing and known regions and overlook long-range dependencies in missing data estimation, leading to suboptimal results. To address these issues, we propose a Diffusion-based time Series Data Imputation (DSDI) framework. We develop a weight-reducing injection strategy that incorporates the predicted values of missing points with reducing weights into the reverse diffusion process to mitigate boundary inconsistencies. Further, we introduce a multi-scale S4-based U-Net, which combines hierarchical information from different levels via multi-resolution integration to capture long-term dependencies. Experimental results demonstrate that our model outperforms existing imputation methods.

Prospective students face the challenging task of selecting a university program that will shape their academic and professional careers. For decision-makers and support services, it is often time-consuming and extremely difficult to match personal interests with suitable programs due to the vast and complex catalogue information available. This paper presents the first information system that provides students with efficient recommendations based on both program content and personal preferences. BERTopic, a powerful topic modeling algorithm, is used that leverages text embedding techniques to generate topic representations. It enables us to mine interest topics from all course descriptions, representing the full body of knowledge taught at the institution. Underpinned by the student's individual choice of topics, a shortlist of the most relevant programs is computed through statistical backtracking in the knowledge map, a novel characterization of the program-course relationship. This approach can be applied to a wide range of educational settings, including professional and vocational training. A case study at a post-secondary school with 80 programs and over 5,000 courses shows that the system provides immediate and effective decision support. The presented interest topics are meaningful, leading to positive effects such as serendipity, personalization, and fairness, as revealed by a qualitative study involving 65 students. Over 98% of users indicated that the recommendations aligned with their interests, and about 94% stated they would use the tool in the future. Quantitative analysis shows the system can be configured to ensure fairness, achieving 98% program coverage while maintaining a personalization score of 0.77. These findings suggest that this real-time, user-centered, data-driven system could improve the program selection process.

Self-supervised speech models (S3Ms) have become a common tool for the speech processing community, leveraging representations for downstream tasks. Clustering S3M representations yields discrete speech units (DSUs), which serve as compact representations for speech signals. DSUs are typically obtained by k-means clustering. Using DSUs often leads to strong performance in various tasks, including automatic speech recognition (ASR). However, even with the high dimensionality and redundancy of S3M representations, preprocessing S3M representations for better clustering remains unexplored, even though it can affect the quality of DSUs. In this paper, we investigate the potential of linear preprocessing methods for extracting DSUs. We evaluate standardization, principal component analysis, whitening, and independent component analysis (ICA) on DSU-based ASR benchmarks and demonstrate their effectiveness as preprocessing for k-means. We also conduct extensive analyses of their behavior, such as orthogonality or interpretability of individual components of ICA.

Artificial Intelligent transformed industries, like engineering, medicine, finance. Predictive models use supervised learning, a vital Machine learning subset. Crucial for model evaluation, cross-validation includes re-substitution, hold-out, and K-fold. This study focuses on improving the accuracy of ML algorithms across three different datasets. To evaluate Hold-out, Hold-out with iteration, and K-fold Cross-Validation techniques, we created a flexible Python program. By modifying parameters like test size, Random State, and 'k' values, we were able to improve accuracy assessment. The outcomes demonstrate the Hold-out validation method's persistent superiority, particularly with a test size of 10%. With iterations and Random State settings, hold-out with iteration shows little accuracy variance. It suggests that there are variances according to algorithm, with Decision Tree doing best for Framingham and Naive Bayes and K Nearest Neighbors for COVID-19. Different datasets require different optimal K values in K-Fold Cross Validation, highlighting these considerations. This study challenges the universality of K values in K-Fold Cross Validation and suggests a 10% test size and 90% training size for better outcomes. It also emphasizes the contextual impact of dataset features, sample size, feature count, and selected methodologies. Researchers can adapt these codes for their dataset to obtain highest accuracy with specific evaluation.

This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold cross-validation, to address class imbalance in the PROMISE dataset. This dataset comprises 969 categorized requirements, classified into functional and non-functional types. The proposed approach enhances the representation of minority classes while maintaining the integrity of validation folds, leading to a notable improvement in classification accuracy. Logistic regression achieved 76.16\%, significantly surpassing the baseline of 58.31\%. These results highlight the applicability and efficiency of machine learning models as scalable and interpretable solutions.

Recent successes of artificial intelligence and deep learning often depend on the well-collected training dataset which is assumed to have an identical distribution with the test dataset. However, this assumption, which is called closed-set learning, is hard to meet in realistic scenarios for deploying deep learning models. As one of the solutions to mitigate this assumption, research on out-of-distribution (OOD) detection has been actively explored in various domains. In OOD detection, we assume that we are given the data of a new class that was not seen in the training phase, i.e., outlier, at the evaluation phase. The ultimate goal of OOD detection is to detect and classify such unseen outlier data as a novel "unknown" class. Among various research branches for OOD detection, generating a virtual outlier during the training phase has been proposed. However, conventional generation-based methodologies utilize in-distribution training dataset to imitate outlier instances, which limits the quality of the synthesized virtual outlier instance itself. In this paper, we propose a novel methodology for OOD detection named Auxiliary Range Expansion for Outlier Synthesis, or ARES. ARES models the region for generating out-of-distribution instances by escaping from the given in-distribution region; instead of remaining near the boundary of in-distribution region. Various stages consists ARES to ultimately generate valuable OOD-like virtual instances. The energy score-based discriminator is then trained to effectively separate in-distribution data and outlier data. Quantitative experiments on broad settings show the improvement of performance by our method, and qualitative results provide logical explanations of the mechanism behind it.

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quantization in separate and disjointed stages, while incurring no statistically word error rate (WER) increase over the 32-bit full-precision models. The system compression time of wav2vec2.0-base and HuBERT-large models is reduced by up to 1.9 and 1.5 times over the two-stage mixed-precision baselines, while both produce lower WERs. The best-performing 3.5-bit mixed-precision quantized HuBERT-large model produces a lossless compression ratio of 8.6x over the 32-bit full-precision system.

Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conflicts by sparsifying task vectors or promoting orthogonality among them. However, they overlook the fundamental requirement of model merging: ensuring the merged model performs comparably to task-specific models on respective tasks. We find these methods inevitably discard task-specific information that, while causing conflicts, is crucial for performance. Based on our findings, we frame model merging as a constrained optimization problem ($\textit{i.e.}$, minimizing the gap between the merged model and individual models, subject to the constraint of retaining shared knowledge) and solve it via adaptive projective gradient descent. Specifically, we align the merged model with individual models by decomposing and reconstituting the loss function, alleviating conflicts through $\textit{data-free}$ optimization of task vectors. To retain shared knowledge, we optimize this objective by projecting gradients within a $\textit{shared subspace}$ spanning all tasks. Moreover, we view merging coefficients as adaptive learning rates and propose a task-aware, training-free strategy. Experiments show that our plug-and-play approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.

The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. We introduce GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms are translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset's quality is benchmarked against existing resources, demonstrating superior translation accuracy through crowdsourced evaluation. GIST is integrated into translation workflows using post-translation refinement methods that require no retraining, where LLM prompting consistently improves BLEU and COMET scores. A web demonstration on the ACL Anthology platform highlights its practical application, showcasing improved accessibility for non-English speakers. This work aims to address critical gaps in AI terminology resources and fosters global inclusivity and collaboration in AI research.