The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are fundamentally inadequate to prevent misuse. Despite ongoing efforts to instill norms such as helpfulness, honesty, and harmlessness in LLMs through fine-tuning based on human preferences, they remain vulnerable to adversarial attacks that exploit conflicts between these norms. I argue that this vulnerability reflects a fundamental limitation of existing alignment methods: they reinforce shallow behavioral dispositions rather than endowing LLMs with a genuine capacity for normative deliberation. Drawing from on research in moral psychology, I show how humans' ability to engage in deliberative reasoning enhances their resilience against similar adversarial tactics. LLMs, by contrast, lack a robust capacity to detect and rationally resolve normative conflicts, leaving them susceptible to manipulation; even recent advances in reasoning-focused LLMs have not addressed this vulnerability. This ``shallow alignment'' problem carries significant implications for AI safety and regulation, suggesting that current approaches are insufficient for mitigating potential harms posed by increasingly capable AI systems.

Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decisions. We introduce CircuGraphRAG, a retrieval-augmented generation (RAG) framework that grounds LLMs outputs in a domain-specific knowledge graph for the circular economy. This graph connects 117,380 industrial and waste entities with classification codes and GWP100 emission data, enabling structured multi-hop reasoning. Natural language queries are translated into SPARQL and verified subgraphs are retrieved to ensure accuracy and traceability. Compared with Standalone LLMs and Naive RAG, CircuGraphRAG achieves superior performance in single-hop and multi-hop question answering, with ROUGE-L F1 scores up to 1.0, while baseline scores below 0.08. It also improves efficiency, halving the response time and reducing token usage by 16% in representative tasks. CircuGraphRAG provides fact-checked, regulatory-ready support for circular economy planning, advancing reliable, low-carbon resource decision making.

For limbless locomotion on flat surfaces, the absence of push points over the surface requires the coordination of body deformation and static friction to generate propulsive forces. The rhythmic contraction of earthworms' muscles produces p e ristaltic waves along their slender bodies [1] while friction - enhancing bristles on their skin, called setae, ensure a firm grip on the ground with each stride [2, 3] . The setae generate a directionally asymmetric friction that is easy to overcome in the direction of movement but strong enough to prevent sliding back . Thus, three fundamental elements of limbless locomotion on terrains with uniform roughness are large deformability, rhythmic contractions, and asymmetric friction . The limbless locomotion of earthworms has inspired the development of several crawling soft robots that replicate some of the ir morphological features, enabling them to crawl on uniform terrains [ 4, 5, 6 ], inside pipes [ 7, 8, 9 ], and through granular media [ 10, 11 ] . However, unifying all of these in a crawling robot remains unexplored. Additionally, many earthworm - inspired soft robots can only move in a straight line and do not possess steering capabilities, which limit s their applicability to unstructured real - world terrains. To replicat e body deformation, several researchers have developed worm - inspired soft robots powered by various actuation mechanisms.

Accurate short-term forecasting of hauling-fleet capacity is crucial in open-pit mining, where weather fluctuations, mechanical breakdowns, and variable crew availability introduce significant operational uncertainties. We propose a deep-learning framework that blends real-world operational records (high-resolution rainfall measurements, fleet performance telemetry) with synthetically generated mechanical-breakdown scenarios to enable the model to capture fluctuating high-impact failure events. We evaluate two architectures: an XGBoost regressor achieving a median absolute error (MedAE) of 14.3 per cent and a Long Short-Term Memory network with a MedAE of 15.1 per cent. Shapley Additive exPlanations (SHAP) value analyses identify cumulative rainfall, historical payload trends, and simulated breakdown frequencies as dominant predictors. Integration of simulated breakdown data and shift-planning features notably reduces prediction volatility. Future work will further integrate maintenance-scheduling indicators (Mean Time Between Failures, Mean Time to Repair), detailed human resource data (operator absenteeism, crew efficiency metrics), blast event scheduling, and other operational constraints to enhance forecast robustness and adaptability. This hybrid modelling approach offers a comprehensive decision-support tool for proactive, data-driven fleet management under dynamically uncertain conditions.

Autonomous manipulation of powders remains a significant challenge for robotic automation in scientific laboratories. The inherent variability and complex physical interactions of powders in flow, coupled with variability in laboratory conditions necessitates adaptive automation. This work introduces FLIP, a flowability-informed powder weighing framework designed to enhance robotic policy learning for granular material handling. Our key contribution lies in using material flowability, quantified by the angle of repose, to optimise physics-based simulations through Bayesian inference. This yields material-specific simulation environments capable of generating accurate training data, which reflects diverse powder behaviours, for training "robot chemists". Building on this, FLIP integrates quantified flowability into a curriculum learning strategy, fostering efficient acquisition of robust robotic policies by gradually introducing more challenging, less flowable powders. We validate the efficacy of our method on a robotic powder weighing task under real-world laboratory conditions. Experimental results show that FLIP with a curriculum strategy achieves a low dispensing error of 2.12 +/- 1.53 mg, outperforming methods that do not leverage flowability data, such as domain randomisation (6.11 +/- 3.92 mg). These results demonstrate FLIP's improved ability to generalise to previously unseen, more cohesive powders and to new target masses.

In the context of self-driving laboratories (SDLs), ensuring automated and error-free capping is crucial, as it is a ubiquitous step in sample preparation. Automated capping in SDLs can occur in both large and small workspaces (e.g., inside a fume hood). However, most commercial capping machines are designed primarily for large spaces and are often too bulky for confined environments. Moreover, many commercial products are closed-source, which can make their integration into fully autonomous workflows difficult. This paper introduces an open-source capping machine suitable for compact spaces, which also integrates a vision system that recognises capping failure. The capping and uncapping processes are repeated 100 times each to validate the machine's design and performance. As a result, the capping machine reached a 100 % success rate for capping and uncapping. Furthermore, the machine sealing capacities are evaluated by capping 12 vials filled with solvents of different vapour pressures: water, ethanol and acetone. The vials are then weighed every 3 hours for three days. The machine's performance is benchmarked against an industrial capping machine (a Chemspeed station) and manual capping. The vials capped with the prototype lost 0.54 % of their content weight on average per day, while the ones capped with the Chemspeed and manually lost 0.0078 % and 0.013 %, respectively. The results show that the capping machine is a reasonable alternative to industrial and manual capping, especially when space and budget are limitations in SDLs.

As soft robot design matures, researchers have converged to sophisticated design paradigms to enable the development of more suitable platforms. Two such paradigms are soft-rigid hybrid robots, which utilize rigid structural materials in some aspect of the robot's design, and architectured materials, which deform based on geometric parameters as opposed to purely material ones. In this work, we combine the two design approaches, utilizing trimmed helicoid structures in series with rigid linkages. Additionally, we extend the literature on wave spring-inspired soft structures by deriving a mechanical model of the stiffness for arbitrary geometries. We present a novel manufacturing method for such structures utilizing an injection molding approach and we make available the design tool to generate 3D printed molds for arbitrary designs of this class. Finally, we produce a robot using the above methods and operate it in closed-loop demonstrations.

Structural Health Monitoring (SHM) is vital for maintaining the safety and longevity of civil infrastructure, yet current solutions remain constrained by cost, power consumption, scalability, and the complexity of data processing. Here, we present a diffractive vibration monitoring system, integrating a jointly optimized diffractive layer with a shallow neural network - base d backend to remotely extract 3D structural vibration spectra, offering a low - power, cost - effective and scalable solution. T his architecture eliminates the need for dense sensor arrays or extensive data acquisition; instead, it us es a spatially - optimized passive diffractive layer that encodes 3D structural displacements into modulated light, captured by a minimal number of detectors and decoded in real - time by shallow and low - power neural networ k s to reconstruct the 3D displacement spectra of structure s . The diffractive system ' s efficacy was demonstrated both numerically and experimentally using millimeter - wave illumination on a laboratory - scale building model with a 2 programmable shake table . O ur system achieves more than an order - of - magnitude improvement in accuracy over conventional optics or separately trained modules, establishing a foundation for high - throughput 3D monitoring of structures . Beyond SHM, the 3D vibration monitoring capabilities of this cost - effective and data - efficient framework establish a new computational sensing modality with potential applications in disaster resilience, aerospace diagnostics, and autonomous navigation -- where energy efficiency, low latency, and high - throughput are critical .

Methods for automatic chemical retrosynthesis have found recent success through the application of models traditionally built for natural language processing, primarily through transformer neural networks. These models have demonstrated significant ability to translate between the SMILES encodings of chemical products and reactants, but are constrained as a result of their autoregressive nature. We propose DiffER, an alternative template-free method for retrosynthesis prediction in the form of categorical diffusion, which allows the entire output SMILES sequence to be predicted in unison. We construct an ensemble of diffusion models which achieves state-of-the-art performance for top-1 accuracy and competitive performance for top-3, top-5, and top-10 accuracy among template-free methods. We prove that DiffER is a strong baseline for a new class of template-free model, capable of learning a variety of synthetic techniques used in laboratory settings and outperforming a variety of other template-free methods on top-k accuracy metrics. By constructing an ensemble of categorical diffusion models with a novel length prediction component with variance, our method is able to approximately sample from the posterior distribution of reactants, producing results with strong metrics of confidence and likelihood. Furthermore, our analyses demonstrate that accurate prediction of the SMILES sequence length is key to further boosting the performance of categorical diffusion models.

The field of health informatics has been profoundly influenced by the development of random forest models, which have led to significant advances in the interpretability of feature interactions. These models are characterized by their robustness to overfitting and parallelization, making them particularly useful in this domain. However, the increasing number of features and estimators in random forests can prevent domain experts from accurately interpreting global feature interactions, thereby compromising trust and regulatory compliance. A method called the surrogate interpretability graph has been developed to address this issue. It uses graphs and mixed-integer linear programming to analyze and visualize feature interactions. This improves their interpretability by visualizing the feature usage per decision-feature-interaction table and the most dominant hierarchical decision feature interactions for predictions. The implementation of a surrogate interpretable graph enhances global interpretability, which is critical for such a high-stakes domain.