Highly accurate force fields are a mandatory requirement to generate predictive simulations. In this regard, Machine Learning Force Fields (MLFFs) have emerged as a revolutionary approach in computational chemistry and materials science, combining the accuracy of quantum mechanical methods with computational efficiency orders of magnitude superior to ab-initio methods. This chapter provides an introduction of the fundamentals of learning and how it is applied to construct MLFFs, detailing key methodologies such as neural network potentials and kernel-based models. Emphasis is placed on the construction of SchNet model, as one of the most elemental neural network-based force fields that are nowadays the basis of modern architectures. Additionally, the GDML framework is described in detail as an example of how the elegant formulation of kernel methods can be used to construct mathematically robust and physics-inspired MLFFs. The ongoing advancements in MLFF development continue to expand their applicability, enabling precise simulations of large and complex systems that were previously beyond reach. This chapter concludes by highlighting the transformative impact of MLFFs on scientific research, underscoring their role in driving future discoveries in the fields of chemistry, physics, and materials science.

Rapid advances in AI are beginning to reshape national security. Destabilizing AI developments could rupture the balance of power and raise the odds of great-power conflict, while widespread proliferation of capable AI hackers and virologists would lower barriers for rogue actors to cause catastrophe. Superintelligence -- AI vastly better than humans at nearly all cognitive tasks -- is now anticipated by AI researchers. Just as nations once developed nuclear strategies to secure their survival, we now need a coherent superintelligence strategy to navigate a new period of transformative change. We introduce the concept of Mutual Assured AI Malfunction (MAIM): a deterrence regime resembling nuclear mutual assured destruction (MAD) where any state's aggressive bid for unilateral AI dominance is met with preventive sabotage by rivals. Given the relative ease of sabotaging a destabilizing AI project -- through interventions ranging from covert cyberattacks to potential kinetic strikes on datacenters -- MAIM already describes the strategic picture AI superpowers find themselves in. Alongside this, states can increase their competitiveness by bolstering their economies and militaries through AI, and they can engage in nonproliferation to rogue actors to keep weaponizable AI capabilities out of their hands. Taken together, the three-part framework of deterrence, nonproliferation, and competitiveness outlines a robust strategy to superintelligence in the years ahead.

Unlike traditional methods that focus on evaluating single state-action pairs or apply action chunking in the actor network, this approach feeds chunked actions directly into the critic. Leveraging the Transformer's strength in processing sequential data, the proposed architecture achieves more robust value estimation. Empirical evaluations demonstrate that this method leads to efficient and stable training, particularly excelling in environments with sparse rewards or Multi-Phase tasks.Contribution(s) 1. We present a novel critic architecture for SAC that leverages Transformers to process sequential information, resulting in more accurate value estimations. Context: Transformer-Based Critic Network 2. We introduce a method for incorporating N-Step returns into the critic network in a stable and efficient manner, effectively mitigating the common challenges of variance and importance sampling associated with N-returns. Context: Stable Integration of N-Returns 3. We shift action chunking from the actor to the critic, demonstrating that enhanced temporal reasoning at the critic level--beyond traditional actor-side exploration--drives performance improvements in sparse and multi-phase tasks. Context: Unlike previous approaches that focus on actor-side chunking for exploration, our Transformer-based critic network produces a smooth value surface that is highly responsive to dataset variations, eliminating the need for additional exploration enhancements.

The rise of generative artificial intelligence (AI) as a novel frontier that uniquely merges advanced levels of intelligence with revolutionary user experiences is redefining the AI landscape for future cellular networks. In particular, the transition towards 6G systems has introduced a myriad of challenges inherent to their AI-native network design, requiring innovative solutions to enable real-time network orchestration, intelligent decision-making, and adaptive dynamic configurations. Meanwhile, the envisioned user experiences for 6G are growing increasingly complex, exceeding the capabilities offered by vintage wireless technologies and conventional AI solutions to satisfy their advanced demands. With its disruptive impact evident across diverse fields, generative AI possesses immense potential to tackle these challenges, leveraging its exceptional capabilities to manage complex tasks, operate autonomously, and adapt seamlessly to scenarios beyond its training domain. Remarkably, generative AI provides a transformative opportunity for telecom and cellular networks to bridge this defined gap in 6G systems, thereby shifting towards a new era with cutting-edge AI innovations across the different system and user levels.

The main advantage of this ansatz over previous alternatives is that it is bi-Lipschitz with respect to a naturally defined metric. As a result, we are able to obtain quantitative approximation results for approximation of Lipschitz continuous antisymmetric functions. Moreover, we provide preliminary experimental evidence to the improved performance of this ansatz for learning antisymmetric functions. The search for an ansatz for quantum many-body wave functions dates back to the early days of quantum mechanics [Sla29], and has been a central task in quantum chemistry [SO96]. In recent years, it has received renewed excitement primarily due to the advances of neural network-based ansatz.

Manipulation of Elasto-Flexible Cables with Single or Multiple UA Vs Chiara Gabellieri 1, Lars Teeuwen 1, Y aolei Shen 1, Antonio Franchi 1, 2 Abstract -- This work considers a large class of systems composed of multiple quadrotors manipulating deformable and extensible cables. The cable is described via a discretized representation, which decomposes it into linear springs interconnected through lumped-mass passive spherical joints. Sets of flat outputs are found for the systems. Numerical simulations support the findings by showing cable manipulation relying on flatness-based trajectories. Eventually, we present an experimental validation of the effectiveness of the proposed discretized cable model for a two-robot example. Moreover, a closed-loop controller based on the identified model and using cable-output feedback is experimentally tested. I NTRODUCTION AND R ELATEDW ORK Deformable object manipulation is an important recent development in aerial robotics with potential applications ranging from fire fighting [1], and in general the manipulation of fluid conduits [2], to waterway maintenance [3], e.g., in case of oil-spill events [4]. Y et, for the challenges it involves [5], deformable object manipulation is still regarded as an open problem.

Energy consumption in robotic arms is a significant concern in industrial automation due to rising operational costs and environmental impact. This study investigates the use of a local reduction method to optimize energy efficiency in robotic systems without compromising performance. The approach refines movement parameters, minimizing energy use while maintaining precision and operational reliability. A three-joint robotic arm model was tested using simulation over a 30-second period for various tasks, including pick-and-place and trajectory-following operations. The results revealed that the local reduction method reduced energy consumption by up to 25% compared to traditional techniques such as Model Predictive Control (MPC) and Genetic Algorithms (GA). Unlike MPC, which requires significant computational resources, and GA, which has slow convergence rates, the local reduction method demonstrated superior adaptability and computational efficiency in real-time applications. The study highlights the scalability and simplicity of the local reduction approach, making it an attractive option for industries seeking sustainable and cost-effective solutions. Additionally, this method can integrate seamlessly with emerging technologies like Artificial Intelligence (AI), further enhancing its application in dynamic and complex environments. This research underscores the potential of the local reduction method as a practical tool for optimizing robotic arm operations, reducing energy demands, and contributing to sustainability in industrial automation. Future work will focus on extending the approach to real-world scenarios and incorporating AI-driven adjustments for more dynamic adaptability.

Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly effective strategy, it does not leverage external feedback signals for refinement, which are often available in tasks like coding. In this work, we propose Adaptive Branching Monte Carlo Tree Search (AB-MCTS), a novel inference-time framework that generalizes repeated sampling with principled multi-turn exploration and exploitation. At each node in the search tree, AB-MCTS dynamically decides whether to "go wider" by expanding new candidate responses or "go deeper" by revisiting existing ones based on external feedback signals. We evaluate our method on complex coding and engineering tasks using frontier models. Empirical results show that AB-MCTS consistently outperforms both repeated sampling and standard MCTS, underscoring the importance of combining the response diversity of LLMs with multi-turn solution refinement for effective inference-time scaling. Recent work (Li et al., 2022; Lewkowycz et al., 2022; Brown et al., 2024; Wu et al., 2025) has begun to reveal that scaling inference-time computation can significantly boost the performance of large language models (LLMs) on complex tasks. Traditionally, LLM performance improvements have stemmed from training-time scaling--namely, increasing the size of training datasets, model parameters, and computational resources at training (Kaplan et al., 2020; Hoffmann et al., 2022). In contrast, inference-time scaling seeks to improve the performance of an LLM by allocating more computational resources at inference. As we outline in Section 2, there are broadly three types of approaches to achieve inference-time scaling: post-training tuning, reward-guided CoT (Chain-of-Thought), and multiple answer generation.

While state-of-the-art language models achieve impressive results through next-token prediction, they have inherent limitations such as the inability to revise already generated tokens. This has prompted exploration of alternative approaches such as discrete diffusion. However, masked diffusion, which has emerged as a popular choice due to its simplicity and effectiveness, reintroduces this inability to revise words. To overcome this, we generalize masked diffusion and derive the theoretical backbone of a family of general interpolating discrete diffusion (GIDD) processes offering greater flexibility in the design of the noising processes. Leveraging a novel diffusion ELBO, we achieve compute-matched state-of-the-art performance in diffusion language modeling. Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality and unlocking the ability for the model to correct its own mistakes, an area where autoregressive models notoriously have struggled. Our code and models are open-source: https://github.com/dvruette/gidd/

Ensuring safety and motion consistency for robot navigation in occluded, obstacle-dense environments is a critical challenge. In this context, this study presents an occlusion-aware Consistent Model Predictive Control (CMPC) strategy. To account for the occluded obstacles, it incorporates adjustable risk regions that represent their potential future locations. Subsequently, dynamic risk boundary constraints are developed online to ensure safety. The CMPC then constructs multiple locally optimal trajectory branches (each tailored to different risk regions) to balance between exploitation and exploration. A shared consensus trunk is generated to ensure smooth transitions between branches without significant velocity fluctuations, further preserving motion consistency. To facilitate high computational efficiency and ensure coordination across local trajectories, we use the alternating direction method of multipliers (ADMM) to decompose the CMPC into manageable sub-problems for parallel solving. The proposed strategy is validated through simulation and real-world experiments on an Ackermann-steering robot platform. The results demonstrate the effectiveness of the proposed CMPC strategy through comparisons with baseline approaches in occluded, obstacle-dense environments.