We introduce Reasoning Core, a new scalable environment for Reinforcement Learning with Verifiable Rewards (RLVR), designed to advance foundational symbolic reasoning in Large Language Models (LLMs). Unlike existing benchmarks that focus on games or isolated puzzles, Reasoning Core procedurally generates problems across core formal domains, including PDDL planning, first-order logic, context-free grammar parsing, causal reasoning, and system equation solving. The environment is built on key design principles of high-generality problem distributions, verification via external tools, and continuous difficulty control, which together provide a virtually infinite supply of novel training instances. Initial zero-shot evaluations with frontier LLMs confirm the difficulty of Reasoning Core's tasks, positioning it as a promising resource to improve the reasoning capabilities of future models.

Classical computers can simulate models of quantum computation with restricted input states. The identification of such states can sharpen the boundary between quantum and classical computations. Previous works describe simulable states of odd-dimensional systems. Here, we further our understanding of systems of qubits. We do so by casting a real-quantum-bit model of computation in terms of a Kirkwood-Dirac (KD) quasiprobability distribution. Algorithms, throughout which this distribution is a proper (positive) probability distribution can be simulated efficiently on a classical computer. We leverage recent results on the geometry of the set of KD-positive states to construct previously unknown classically-simulable (bound) states. Finally, we show that KD nonpositivity is a resource monotone for quantum computation, establishing KD nonpositivity as a necessary resource for computational quantum advantage.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

This SHREC 2025 track dedicated to protein surface shape retrieval involved 9 participating teams. We evaluated the performance in retrieval of 15 proposed methods on a large dataset of 11,555 protein surfaces with calculated electrostatic potential (a key molecular surface descriptor). The performance in retrieval of the proposed methods was evaluated through different metrics (Accuracy, Balanced accuracy, F1 score, Precision and Recall). The best retrieval performance was achieved by the proposed methods that used the electrostatic potential complementary to molecular surface shape. This observation was also valid for classes with limited data which highlights the importance of taking into account additional molecular surface descriptors.

Online continuous action recognition has emerged as a critical research area due to its practical implications in real-world applications, such as human-computer interaction, healthcare, and robotics. Among various modalities, skeleton-based approaches have gained significant popularity, demonstrating their effectiveness in capturing 3D temporal data while ensuring robustness to environmental variations. However, most existing works focus on segment-based recognition, making them unsuitable for real-time, continuous recognition scenarios. In this paper, we propose a novel online recognition system designed for real-time skeleton sequence streaming. Our approach leverages a hybrid architecture combining Spatial Graph Convolutional Networks (S-GCN) for spatial feature extraction and a Transformer-based Graph Encoder (TGE) for capturing temporal dependencies across frames. Additionally, we introduce a continual learning mechanism to enhance model adaptability to evolving data distributions, ensuring robust recognition in dynamic environments. We evaluate our method on the SHREC'21 benchmark dataset, demonstrating its superior performance in online hand gesture recognition. Our approach not only achieves state-of-the-art accuracy but also significantly reduces false positive rates, making it a compelling solution for real-time applications. The proposed system can be seamlessly integrated into various domains, including human-robot collaboration and assistive technologies, where natural and intuitive interaction is crucial.

We study the non-contextual multi-armed bandit problem in a transfer learning setting: before any pulls, the learner is given N'_k i.i.d. samples from each source distribution nu'_k, and the true target distributions nu_k lie within a known distance bound d_k(nu_k, nu'_k) <= L_k. In this framework, we first derive a problem-dependent asymptotic lower bound on cumulative regret that extends the classical Lai-Robbins result to incorporate the transfer parameters (d_k, L_k, N'_k). We then propose KL-UCB-Transfer, a simple index policy that matches this new bound in the Gaussian case. Finally, we validate our approach via simulations, showing that KL-UCB-Transfer significantly outperforms the no-prior baseline when source and target distributions are sufficiently close.

Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitating progress, evaluation, and reproducibility. The significance of benchmarks is underscored by the existence of numerous benchmark frameworks developed for various RL paradigms, including single-agent RL (e.g., Gymnasium), multi-agent RL (e.g., PettingZoo), and single-agent multi-objective RL (e.g., MO-Gymnasium). To support the advancement of the MOMARL field, we introduce MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.

Over the last few years, the complexity of web applications has increased to provide more dynamic web applications to users. The drawback of this complexity is the growing number of errors in the front-end applications. In this paper, we present an approach to provide self-healing for the web. We implemented this approach in two different tools: 1) BikiniProxy, an HTTP repair proxy, and 2) BugBlock, a browser extension. They use five self-healing strategies to rewrite the buggy HTML and Javascript code to handle errors in web pages. We evaluate BikiniProxy and BugBlock with a new benchmark of 555 reproducible Javascript errors of which 31.76% can be automatically self-healed by BikiniProxy and 15.67% by BugBlock.

Mean Field Games (MFGs) offer a powerful framework for studying large-scale multi-agent systems. Yet, learning Nash equilibria in MFGs remains a challenging problem, particularly when the initial distribution is unknown or when the population is subject to common noise. In this paper, we introduce an efficient deep reinforcement learning (DRL) algorithm designed to achieve population-dependent Nash equilibria without relying on averaging or historical sampling, inspired by Munchausen RL and Online Mirror Descent. The resulting policy is adaptable to various initial distributions and sources of common noise. Through numerical experiments on seven canonical examples, we demonstrate that our algorithm exhibits superior convergence properties compared to state-of-the-art algorithms, particularly a DRL version of Fictitious Play for population-dependent policies. The performance in the presence of common noise underscores the robustness and adaptability of our approach.

In dyadic interactions, a broad spectrum of human facial reactions might be appropriate for responding to each human speaker behaviour. Following the successful organisation of the REACT 2023 and REACT 2024 challenges, we are proposing the REACT 2025 challenge encouraging the development and benchmarking of Machine Learning (ML) models that can be used to generate multiple appropriate, diverse, realistic and synchronised human-style facial reactions expressed by human listeners in response to an input stimulus (i.e., audio-visual behaviours expressed by their corresponding speakers). As a key of the challenge, we provide challenge participants with the first natural and large-scale multi-modal MAFRG dataset (called MARS) recording 137 human-human dyadic interactions containing a total of 2856 interaction sessions covering five different topics. In addition, this paper also presents the challenge guidelines and the performance of our baselines on the two proposed sub-challenges: Offline MAFRG and Online MAFRG, respectively. The challenge baseline code is publicly available at this https URL

The race to train language models on vast, diverse, and inconsistently documented datasets has raised pressing concerns about the legal and ethical risks for practitioners. To remedy these practices threatening data transparency and understanding, we convene a multi-disciplinary effort between legal and machine learning experts to systematically audit and trace 1800+ text datasets. We develop tools and standards to trace the lineage of these datasets, from their source, creators, series of license conditions, properties, and subsequent use. Our landscape analysis highlights the sharp divides in composition and focus of commercially open vs closed datasets, with closed datasets monopolizing important categories: lower resource languages, more creative tasks, richer topic variety, newer and more synthetic training data. This points to a deepening divide in the types of data that are made available under different license conditions, and heightened implications for jurisdictional legal interpretations of copyright and fair use. We also observe frequent miscategorization of licenses on widely used dataset hosting sites, with license omission of 70%+ and error rates of 50%+. This points to a crisis in misattribution and informed use of the most popular datasets driving many recent breakthroughs. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire audit, with an interactive UI, the Data Provenance Explorer, which allows practitioners to trace and filter on data provenance for the most popular open source finetuning data collections: this http URL.

Face images processed by computer vision algorithms contain sensitive personal information that malicious actors can capture without consent. These privacy and security risks highlight the need for effective face anonymization methods. Current methods struggle to propose a good trade-off between a secure scheme with high-quality image generation and reversibility for later person authentication. Diffusion-based approaches produce high-quality anonymized images but lack the secret key mechanism to ensure that only authorized parties can reverse the process. In this paper, we introduce, to our knowledge, the first secure, high-quality reversible anonymization method based on a diffusion model. We propose to combine the secret key with the latent faces representation of the diffusion model. To preserve identity-irrelevant features, generation is constrained by a facial mask, maintaining high-quality images. By using a deterministic forward and backward diffusion process, our approach enforces that the original face can be recovered with the correct secret key. We also show that the proposed method produces anonymized faces that are less visually similar to the original faces, compared to other previous work.

Recent advancements in Artificial Intelligence (AI), driven by Neural Networks (NN), demand innovative neural architecture designs, particularly within the constrained environments of Internet of Things (IoT) systems, to balance performance and efficiency. HW-aware Neural Architecture Search (HW-aware NAS) emerges as an attractive strategy to automate the design of NN using multi-objective optimization approaches, such as evolutionary algorithms. However, the intricate relationship between NN design parameters and HW-aware NAS optimization objectives remains an underexplored research area, overlooking opportunities to effectively leverage this knowledge to guide the search process accordingly. Furthermore, the large amount of evaluation data produced during the search holds untapped potential for refining the optimization strategy and improving the approximation of the Pareto front. Addressing these issues, we propose SONATA, a self-adaptive evolutionary algorithm for HW-aware NAS. Our method leverages adaptive evolutionary operators guided by the learned importance of NN design parameters. Specifically, through tree-based surrogate models and a Reinforcement Learning agent, we aspire to gather knowledge on 'How' and 'When' to evolve NN architectures. Comprehensive evaluations across various NAS search spaces and hardware devices on the ImageNet-1k dataset have shown the merit of SONATA with up to 0.25% improvement in accuracy and up to 2.42x gains in latency and energy. Our SONATA has seen up to sim$93.6% Pareto dominance over the native NSGA-II, further stipulating the importance of self-adaptive evolution operators in HW-aware NAS.

Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle such an issue, this paper introduces multi-objective reinforcement learning based on decomposition (MORL/D), a novel methodology bridging the literature of RL and MOO. A comprehensive taxonomy for MORL/D is presented, providing a structured foundation for categorizing existing and potential MORL works. The introduced taxonomy is then used to scrutinize MORL research, enhancing clarity and conciseness through well-defined categorization. Moreover, a flexible framework derived from the taxonomy is introduced. This framework accommodates diverse instantiations using tools from both RL and MOO/D. Its versatility is demonstrated by implementing it in different configurations and assessing it on contrasting benchmark problems. Results indicate MORL/D instantiations achieve comparable performance to current state-of-the-art approaches on the studied problems. By presenting the taxonomy and framework, this paper offers a comprehensive perspective and a unified vocabulary for MORL. This not only facilitates the identification of algorithmic contributions but also lays the groundwork for novel research avenues in MORL.

Preference-based Pure Exploration (PrePEx) aims to identify with a given confidence level the set of Pareto optimal arms in a vector-valued (aka multi-objective) bandit, where the reward vectors are ordered via a (given) preference cone $\mathcal{C}$. Though PrePEx and its variants are well-studied, there does not exist a computationally efficient algorithm that can optimally track the existing lower bound for arbitrary preference cones. We successfully fill this gap by efficiently solving the minimisation and maximisation problems in the lower bound. First, we derive three structural properties of the lower bound that yield a computationally tractable reduction of the minimisation problem. Then, we deploy a Frank-Wolfe optimiser to accelerate the maximisation problem in the lower bound. Together, these techniques solve the maxmin optimisation problem in $\mathcal{O}(KL^{2})$ time for a bandit instance with $K$ arms and $L$ dimensional reward, which is a significant acceleration over the literature. We further prove that our proposed PrePEx algorithm, FraPPE, asymptotically achieves the optimal sample complexity. Finally, we perform numerical experiments across synthetic and real datasets demonstrating that FraPPE achieves the lowest sample complexities to identify the exact Pareto set among the existing algorithms.

Unregistered surface meshes, especially raw 3D scans, present significant challenges for automatic computation of plausible deformations due to the lack of established point-wise correspondences and the presence of noise in the data. In this paper, we propose a new, rig-free, data-driven framework for motion prediction and transfer on such body meshes. Our method couples a robust motion embedding network with a learned per-vertex feature field to generate a spatio-temporal deformation field, which drives the mesh deformation. Extensive evaluations, including quantitative benchmarks and qualitative visuals on tasks such as walking and running, demonstrate the effectiveness and versatility of our approach on challenging unregistered meshes.

Early experiments with software diversity in the mid 1970's investigated N-version programming and recovery blocks to increase the reliability of embedded systems. Four decades later, the literature about software diversity has expanded in multiple directions: goals (fault-tolerance, security, software engineering); means (managed or automated diversity) and analytical studies (quantification of diversity and its impact). Our paper contributes to the field of software diversity as the first paper that adopts an inclusive vision of the area, with an emphasis on the most recent advances in the field. This survey includes classical work about design and data diversity for fault tolerance, as well as the cybersecurity literature that investigates randomization at different system levels. It broadens this standard scope of diversity, to include the study and exploitation of natural diversity and the management of diverse software products. Our survey includes the most recent works, with an emphasis from 2000 to present. The targeted audience is researchers and practitioners in one of the surveyed fields, who miss the big picture of software diversity. Assembling the multiple facets of this fascinating topic sheds a new light on the field.

Multi-objective parametric optimization problem is presented for overwrapped composite pressure vessels under internal pressure for storage and heating water. It is solved using the developed iterative optimization algorithm. Optimal values of design parameters for the vessel are obtained by varying the set of parameters for composite layers, such as the thickness of layers and radii of polar openings, which influence the distribution of fiber angles along the vessel. The suggested optimization methodology is based on the mechanical solution for composite vessels and the satisfaction of the main failure criteria. An innovative approach lies in the possibility of using the developed optimization methodology for designing vessels with non-symmetrical filament winding, which have unequal polar openings on the domes. This became possible due to the development of a special numerical mechanical finite element model of a composite vessel. A specific Python program provides the creation of a model and controls the exchange of data between the modules of the iterative optimization process. The numerical model includes the determination of the distribution of fiber angles on the domes and cylindrical part of the vessel as well as changes in layer thicknesses. The optimization problem solution is provided using a Multi-Island Genetic Algorithm, this type of method showed its efficiency for such applications, by allowing to avoid local solutions. Thus, optimal parameters of a composite vessel were found by minimizing composite mass and thickness and maximizing the strain energy. Test solutions using the developed methodology are presented for three types of composite materials to evaluate their possibility for integration into the vessel design model.

We propose a metaheuristic algorithm enhanced with feature-based guidance that is designed to solve the Capacitated Vehicle Routing Problem (CVRP). To formulate the proposed guidance, we developed and explained a supervised Machine Learning (ML) model, that is used to formulate the guidance and control the diversity of the solution during the optimization process. We propose a metaheuristic algorithm combining neighborhood search and a novel mechanism of hybrid split and path relinking to implement the proposed guidance. The proposed guidance has proven to give a statistically significant improvement to the proposed metaheuristic algorithm when solving CVRP. Moreover, the proposed guided metaheuristic is also capable of producing competitive solutions among state-of-the-art metaheuristic algorithms.