Quantum computers represent a transformative frontier in computational technology, promising exponential speedups beyond classical computing limits. IBM Quantum has led significant advancements in both hardware and software, providing access to quantum hardware via IBM Cloud since 2016, achieving a milestone with the world's first accessible quantum computer. This article explores IBM's quantum computing journey, focusing on the development of practical quantum computers. We summarize the evolution and advancements of IBM Quantum's processors across generations, including their recent breakthrough surpassing the 1,000-qubit barrier. The paper reviews detailed performance metrics across various hardware, tracing their evolution over time and highlighting IBM Quantum's transition from the noisy intermediate-scale quantum (NISQ) computing era towards fault-tolerant quantum computing capabilities.

Deep learning (DL) [44] has advanced significantly in recent years, providing algorithms that can solve complex problems varying from image classification [12] to playing games such as Go [59] at a human level or even better. More recent advances include the development of Large Language Models (LLMs), which are substantial deep learning models (i.e., they usually have billions of parameters) such as ChatGPT [63, 21], and Llama [66] that have been trained on enormous data sets. Deep learning has naturally affected many scientific fields and has been applied to many complex problems. One such problem is the numerical solution of differential equations, where (deep) neural networks approximate the solution of partial or ordinary differential equations. The idea is not new since there are works from the 90s like Lee et al. [45] and Wang et al. [67] have relied on Hopfield neural networks [33] to solve differential equations using linear systems after discretizing them. Meade and Fernandez have proposed solvers for nonlinear differential equations based on combining neural networks and splines [48]. Lagaris et al. introduced in [42] an efficient method that relies on trial solutions and neural networks to solve boundary and initial values problems. They form a loss function using the differential operator of the problem, and a neural network approximates the solution by minimizing that loss function.

This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex architectures to address increasingly sophisticated tasks, the computational and energy costs have escalated significantly. We explore the necessity and impact of model size growth, highlighting the performance benefits as well as the computational challenges and environmental considerations. The core focus is on model quantization as a fundamental approach to mitigate these challenges by reducing model size and improving efficiency without substantially compromising accuracy. We delve into various quantization techniques, including both post-training quantization (PTQ) and quantization-aware training (QAT), and analyze several state-of-the-art algorithms such as LLM-QAT, PEQA(L4Q), ZeroQuant, SmoothQuant, and others. Through comparative analysis, we examine how these methods address issues like outliers, importance weighting, and activation quantization, ultimately contributing to more sustainable and accessible deployment of large-scale models.

One application area of long-term memory (LTM) capabilities with increasing traction is personal AI companions and assistants. With the ability to retain and contextualize past interactions and adapt to user preferences, personal AI companions and assistants promise a profound shift in how we interact with AI and are on track to become indispensable in personal and professional settings. However, this advancement introduces new challenges and vulnerabilities that require careful consideration regarding the deployment and widespread use of these systems. The goal of this paper is to explore the broader implications of building and deploying personal AI applications with LTM capabilities using a holistic evaluation approach. This will be done in three ways: 1) reviewing the technological underpinnings of LTM in Large Language Models, 2) surveying current personal AI companions and assistants, and 3) analyzing critical considerations and implications of deploying and using these applications.

In recent years, Light Detection and Ranging (LiDAR) technology, a critical sensor in robotics and autonomous systems, has seen significant advancements. These improvements include enhanced resolution of point clouds and the capability to provide 360{\deg} low-resolution images. These images encode various data such as depth, reflectivity, and near-infrared light within the pixels. However, an excessive density of points and conventional point cloud sampling can be counterproductive, particularly in applications such as LiDAR odometry, where misleading points and degraded geometry information may induce drift errors. Currently, extensive research efforts are being directed towards leveraging LiDAR-generated images to improve situational awareness. This paper presents a comprehensive review of current deep learning (DL) techniques, including colorization and super-resolution, which are traditionally utilized in conventional computer vision tasks. These techniques are applied to LiDAR-generated images and are analyzed qualitatively. Based on this analysis, we have developed a novel approach that selectively integrates the most suited colorization and super-resolution methods with LiDAR imagery to sample reliable points from the LiDAR point cloud. This approach aims to not only improve the accuracy of point cloud registration but also avoid mismatching caused by lacking geometry information, thereby augmenting the utility and precision of LiDAR systems in practical applications. In our evaluation, the proposed approach demonstrates superior performance compared to our previous work, achieving lower translation and rotation errors with a reduced number of points.

This paper introduces a Spiking Diffusion Policy (SDP) learning method for robotic manipulation by integrating Spiking Neurons and Learnable Channel-wise Membrane Thresholds (LCMT) into the diffusion policy model, thereby enhancing computational efficiency and achieving high performance in evaluated tasks. Specifically, the proposed SDP model employs the U-Net architecture as the backbone for diffusion learning within the Spiking Neural Network (SNN). It strategically places residual connections between the spike convolution operations and the Leaky Integrate-and-Fire (LIF) nodes, thereby preventing disruptions to the spiking states. Additionally, we introduce a temporal encoding block and a temporal decoding block to transform static and dynamic data with timestep $T_S$ into each other, enabling the transmission of data within the SNN in spike format. Furthermore, we propose LCMT to enable the adaptive acquisition of membrane potential thresholds, thereby matching the conditions of varying membrane potentials and firing rates across channels and avoiding the cumbersome process of manually setting and tuning hyperparameters. Evaluating the SDP model on seven distinct tasks with SNN timestep $T_S=4$, we achieve results comparable to those of the ANN counterparts, along with faster convergence speeds than the baseline SNN method. This improvement is accompanied by a reduction of 94.3\% in dynamic energy consumption estimated on 45nm hardware.

This paper presents an overview of the Volvo Discovery Challenge, held during the ECML-PKDD 2024 conference. The challenge's goal was to predict the failure risk of an anonymized component in Volvo trucks using a newly published dataset. The test data included observations from two generations (gen1 and gen2) of the component, while the training data was provided only for gen1. The challenge attracted 52 data scientists from around the world who submitted a total of 791 entries. We provide a brief description of the problem definition, challenge setup, and statistics about the submissions. In the section on winning methodologies, the first, second, and third-place winners of the competition briefly describe their proposed methods and provide GitHub links to their implemented code. The shared code can be interesting as an advanced methodology for researchers in the predictive maintenance domain. The competition was hosted on the Codabench platform.

The integration of tools in LLM-based agents overcame the difficulties of standalone LLMs and traditional agents' limited capabilities. However, the conjunction of these technologies and the proposed enhancements in several state-of-the-art works followed a non-unified software architecture resulting in a lack of modularity. Indeed, they focused mainly on functionalities and overlooked the definition of the component's boundaries within the agent. This caused terminological and architectural ambiguities between researchers which we addressed in this paper by proposing a unified framework that establishes a clear foundation for LLM-based agents' development from both functional and software architectural perspectives. Our framework, LLM-Agent-UMF (LLM-based Agent Unified Modeling Framework), clearly distinguishes between the different components of an agent, setting LLMs, and tools apart from a newly introduced element: the core-agent, playing the role of the central coordinator of the agent which comprises five modules: planning, memory, profile, action, and security, the latter often neglected in previous works. Differences in the internal structure of core-agents led us to classify them into a taxonomy of passive and active types. Based on this, we proposed different multi-core agent architectures combining unique characteristics of various individual agents. For evaluation purposes, we applied this framework to a selection of state-of-the-art agents, thereby demonstrating its alignment with their functionalities and clarifying the overlooked architectural aspects. Moreover, we thoroughly assessed four of our proposed architectures by integrating distinctive agents into hybrid active/passive core-agents' systems. This analysis provided clear insights into potential improvements and highlighted the challenges involved in the combination of specific agents.

The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and lack of a fairness baseline. SAGED(-Bias) is the first holistic benchmarking pipeline to address these problems. The pipeline encompasses five core stages: scraping materials, assembling benchmarks, generating responses, extracting numeric features, and diagnosing with disparity metrics. SAGED includes metrics for max disparity, such as impact ratio, and bias concentration, such as Max Z-scores. Noticing that assessment tool bias and contextual bias in prompts can distort evaluation, SAGED implements counterfactual branching and baseline calibration for mitigation. For demonstration, we use SAGED on G20 Countries with popular 8b-level models including Gemma2, Llama3.1, Mistral, and Qwen2. With sentiment analysis, we find that while Mistral and Qwen2 show lower max disparity and higher bias concentration than Gemma2 and Llama3.1, all models are notably biased against countries like Russia and (except for Qwen2) China. With further experiments to have models role-playing U.S. (vice-/former-) presidents, we see bias amplifies and shifts in heterogeneous directions. Moreover, we see Qwen2 and Mistral not engage in role-playing, while Llama3.1 and Gemma2 role-play Trump notably more intensively than Biden and Harris, indicating role-playing performance bias in these models.

The growing demand for accurate, efficient, and scalable solutions in computational mechanics highlights the need for advanced operator learning algorithms that can efficiently handle large datasets while providing reliable uncertainty quantification. This paper introduces a novel Gaussian Process (GP) based neural operator for solving parametric differential equations. The approach proposed leverages the expressive capability of deterministic neural operators and the uncertainty awareness of conventional GP. In particular, we propose a ``neural operator-embedded kernel'' wherein the GP kernel is formulated in the latent space learned using a neural operator. Further, we exploit a stochastic dual descent (SDD) algorithm for simultaneously training the neural operator parameters and the GP hyperparameters. Our approach addresses the (a) resolution dependence and (b) cubic complexity of traditional GP models, allowing for input-resolution independence and scalability in high-dimensional and non-linear parametric systems, such as those encountered in computational mechanics. We apply our method to a range of non-linear parametric partial differential equations (PDEs) and demonstrate its superiority in both computational efficiency and accuracy compared to standard GP models and wavelet neural operators. Our experimental results highlight the efficacy of this framework in solving complex PDEs while maintaining robustness in uncertainty estimation, positioning it as a scalable and reliable operator-learning algorithm for computational mechanics.