In biomedical research and other fields, it is now common to generate high content data that are both multi-source and multi-way. Multi-source data are collected from different high-throughput technologies while multi-way data are collected over multiple dimensions, yielding multiple tensor arrays. Integrative analysis of these data sets is needed, e.g., to capture and synthesize different facets of complex biological systems. However, despite growing interest in multi-source and multi-way factorization techniques, methods that can handle data that are both multi-source and multi-way are limited. In this work, we propose a Multiple Linked Tensors Factorization (MULTIFAC) method extending the CANDECOMP/PARAFAC (CP) decomposition to simultaneously reduce the dimension of multiple multi-way arrays and approximate underlying signal. We first introduce a version of the CP factorization with L2 penalties on the latent factors, leading to rank sparsity. When extended to multiple linked tensors, the method automatically reveals latent components that are shared across data sources or individual to each data source. We also extend the decomposition algorithm to its expectation-maximization (EM) version to handle incomplete data with imputation. Extensive simulation studies are conducted to demonstrate MULTIFAC's ability to (i) approximate underlying signal, (ii) identify shared and unshared structures, and (iii) impute missing data. The approach yields an interpretable decomposition on multi-way multi-omics data for a study on early-life iron deficiency.

The analytic characterization of the high-dimensional behavior of optimization for Generalized Linear Models (GLMs) with Gaussian data has been a central focus in statistics and probability in recent years. While convex cases, such as the LASSO, ridge regression, and logistic regression, have been extensively studied using a variety of techniques, the non-convex case remains far less understood despite its significance. A non-rigorous statistical physics framework has provided remarkable predictions for the behavior of high-dimensional optimization problems, but rigorously establishing their validity for non-convex problems has remained a fundamental challenge. In this work, we address this challenge by developing a systematic framework that rigorously proves replica-symmetric formulas for non-convex GLMs and precisely determines the conditions under which these formulas are valid. Remarkably, the rigorous replica-symmetric predictions align exactly with the conjectures made by physicists, and the so-called replicon condition. The originality of our approach lies in connecting two powerful theoretical tools: the Gaussian Min-Max Theorem, which we use to provide precise lower bounds, and Approximate Message Passing (AMP), which is shown to achieve these bounds algorithmically. We demonstrate the utility of this framework through significant applications: (i) by proving the optimality of the Tukey loss over the more commonly used Huber loss under a $\varepsilon$ contaminated data model, (ii) establishing the optimality of negative regularization in high-dimensional non-convex regression and (iii) characterizing the performance limits of linearized AMP algorithms. By rigorously validating statistical physics predictions in non-convex settings, we aim to open new pathways for analyzing increasingly complex optimization landscapes beyond the convex regime.

--T ext-to-audio (TT A), which generates audio signals from textual descriptions, has received huge attention in recent years. However, recent works focused on text to monaural audio only. As we know, spatial audio provides more immersive auditory experience than monaural audio, e.g. in virtual reality. T o address this issue, we propose a text-to-spatial-audio (TTSA) generation framework named DualSpec.Specifically, it first trains variational autoencoders (V AEs) for extracting the latent acoustic representations from sound event audio. Then, given text that describes sound events and event directions, the proposed method uses the encoder of a pretrained large language model to transform the text into text features. Finally, it trains a diffusion model from the latent acoustic representations and text features for the spatial audio generation. In the inference stage, only the text description is needed to generate spatial audio. Particularly, to improve the synthesis quality and azimuth accuracy of the spatial sound events simultaneously, we propose to use two kinds of acoustic features. One is the Mel spectrograms which is good for improving the synthesis quality, and the other is the short-time Fourier transform spectrograms which is good at improving the azimuth accuracy. We provide a pipeline of constructing spatial audio dataset with text prompts, for the training of the V AEs and diffusion model. We also introduce new spatial-aware evaluation metrics to quantify the azimuth errors of the generated spatial audio recordings. Experimental results demonstrate that the proposed method can generate spatial audio with high directional and event consistency.

Much of the success of multi-agent debates depends on carefully choosing the right parameters. Among them, the decision-making protocol stands out. Systematic comparison of decision protocols is difficult because studies alter multiple discussion parameters beyond the protocol. So far, it has been largely unknown how decision-making addresses the challenges of different tasks. This work systematically evaluates the impact of seven decision protocols (e.g., majority voting, unanimity consensus). We change only one variable at a time (i.e., decision protocol) to analyze how different methods affect the collaboration between agents and test different protocols on knowledge (MMLU, MMLU-Pro, GPQA) and reasoning datasets (StrategyQA, MuSR, SQuAD 2.0). Our results show that voting protocols improve performance by 13.2% in reasoning tasks and consensus protocols by 2.8% in knowledge tasks over the other decision protocol. Increasing the number of agents improves performance, while more discussion rounds before voting reduces it. To improve decision-making by increasing answer diversity, we propose two new methods, All-Agents Drafting (AAD) and Collective Improvement (CI). Our methods improve task performance by up to 3.3% with AAD and up to 7.4% with CI. This work demonstrates the importance of decision-making in multi-agent debates beyond scaling.

This paper presents a performance comparison among four Convolutional Neural Network architectures (EfficientNet-B3, InceptionV3, ResNet50, and VGG16) for classifying cassava disease images. The images were sourced from an imbalanced dataset from a competition. Appropriate metrics were employed to address class imbalance. The results indicate that EfficientNet-B3 achieved on this task accuracy of 87.7%, precision of 87.8%, revocation of 87.8% and F1-Score of 87.7%. These findings suggest that EfficientNet-B3 could be a valuable tool to support Digital Agriculture.

Whether and how to regulate AI is one of the defining questions of our times - a question that is being debated locally, nationally, and internationally. We argue that much of this debate is proceeding on a false premise. Specifically, our article challenges the prevailing academic consensus that the European Union's AI regulatory framework is fundamentally rights-driven and the correlative presumption that other rights-regarding nations should therefore follow Europe's lead in AI regulation. Rather than taking rights language in EU rules and regulations at face value, we show how EU AI regulation is the logical outgrowth of a particular cultural, political, and historical context. We show that although instruments like the General Data Protection Regulation (GDPR) and the AI Act invoke the language of fundamental rights, these rights are instrumentalized - used as rhetorical cover for governance tools that address systemic risks and maintain institutional stability. As such, we reject claims that the EU's regulatory framework and the substance of its rules should be adopted as universal imperatives and transplanted to other liberal democracies. To add weight to our argument from historical context, we conduct a comparative analysis of AI regulation in five contested domains: data privacy, cybersecurity, healthcare, labor, and misinformation. This EU-US comparison shows that the EU's regulatory architecture is not meaningfully rights-based. Our article's key intervention in AI policy debates is not to suggest that the current American regulatory model is necessarily preferable but that the presumed legitimacy of the EU's AI regulatory approach must be abandoned.

We present a novel form of scalable knowledge representation about agents in a simulated democracy, e-polis, where real users respond to social challenges associated with democratic institutions, structured as Smart Spatial Types, a new type of Smart Building that changes architectural form according to the philosophical doctrine of a visitor. At the end of the game players vote on the Smart City that results from their collective choices. Our approach uses deductive systems in an unusual way: by integrating a model of democracy with a model of a Smart City we are able to prove quality aspects of the simulated democracy in different urban and social settings, while adding ease and flexibility to the development. Second, we can infer and reason with abstract knowledge, which is a limitation of the Unity platform; third, our system enables real-time decision-making and adaptation of the game flow based on the player's abstract state, paving the road to explainability. Scalability is achieved by maintaining a dual-layer knowledge representation mechanism for reasoning about the simulated democracy that functions in a similar way to a two-level cache. The lower layer knows about the current state of the game by continually processing a high rate of events produced by the in-built physics engine of the Unity platform, e.g., it knows of the position of a player in space, in terms of his coordinates x,y,z as well as their choices for each challenge. The higher layer knows of easily-retrievable, user-defined abstract knowledge about current and historical states, e.g., it knows of the political doctrine of a Smart Spatial Type, a player's philosophical doctrine, and the collective philosophical doctrine of a community players with respect to current social issues.

Large Language Models (LLMs) have shown remarkable capabilities across various domains, but their potential for solving combinatorial optimization problems remains largely unexplored. In this paper, we investigate the applicability of LLMs to the Job Shop Scheduling Problem (JSSP), a classic challenge in combinatorial optimization that requires efficient job allocation to machines to minimize makespan. To this end, we introduce Starjob, the first supervised dataset for JSSP, comprising 130k instances specifically designed for training LLMs. Leveraging this dataset, we fine-tune the LLaMA 8B 4-bit quantized model with the LoRA method to develop an end-to-end scheduling approach. Our evaluation on standard benchmarks demonstrates that the proposed LLM-based method not only surpasses traditional Priority Dispatching Rules (PDRs) but also achieves notable improvements over state-of-the-art neural approaches like L2D, with an average improvement of 15.36% on DMU and 7.85% on Taillard benchmarks. These results highlight the untapped potential of LLMs in tackling combinatorial optimization problems, paving the way for future advancements in this area.

Facial recognition systems have mostly been employed for gender classification in computer vision over the years. The development of advance tools and concepts in deep learning and computer vision, especially with developing convolutional neural networks t o construct maps of facial features or utilizing transfer learning of models pretrained on huge volume of data, has overtime, further enhanced the credibility and resultant reliability of using facial recognition techniques for many forms of attribute iden tification in computer vision. However, the use of facial recognition for attributes identification and classification are not without pitfalls as most facial recognition techniques require clear images and high - quality videos of clearly defined facial features to be effective [5] . In real life situations, facial images, especially when obtained under non ideal situations, are often distorted, blurred or concentrated on positions that are not appropriate for proper feature detection by facial recognition techniques. For example, co mmon f acial recognition techniques are often unable to detect facial features on images where the face is inside view, taken from distance, partially covered or even blurred. While new innovative techniques, like Google's Mediapipe facial recognition system are addressing some of these limitations, these are still valid problems today for most facial recognition techniques such as the OpenCV Facial Cascades.

In today's competitive marketing landscape, effective complaint management is crucial for customer service and business success. Video complaints, integrating text and image content, offer invaluable insights by addressing customer grievances and delineating product benefits and drawbacks. However, comprehending nuanced complaint aspects within vast daily multimodal financial data remains a formidable challenge. Addressing this gap, we have curated a proprietary multimodal video complaint dataset comprising 433 publicly accessible instances. Each instance is meticulously annotated at the utterance level, encompassing five distinct categories of financial aspects and their associated complaint labels. To support this endeavour, we introduce Solution 3.0, a model designed for multimodal aspect-based complaint identification task. Solution 3.0 is tailored to perform three key tasks: 1) handling multimodal features ( audio and video), 2) facilitating multilabel aspect classification, and 3) conducting multitasking for aspect classifications and complaint identification parallelly. Solution 3.0 utilizes a CLIP-based dual frozen encoder with an integrated image segment encoder for global feature fusion, enhanced by contextual attention (ISEC) to improve accuracy and efficiency. Our proposed framework surpasses current multimodal baselines, exhibiting superior performance across nearly all metrics by opening new ways to strengthen appropriate customer care initiatives and effectively assisting individuals in resolving their problems.