To reduce the experimental validation workload for chemical researchers and accelerate the design and optimization of high-energy-density lithium metal batteries, we aim to leverage models to automatically predict Coulombic Efficiency (CE) based on the composition of liquid electrolytes. There are mainly two representative paradigms in existing methods: machine learning and deep learning. However, the former requires intelligent input feature selection and reliable computational methods, leading to error propagation from feature estimation to model prediction, while the latter (e.g. MultiModal-MoLFormer) faces challenges of poor predictive performance and overfitting due to limited diversity in augmented data. To tackle these issues, we propose a novel method COEFF (COlumbic EFficiency prediction via Fine-tuned models), which consists of two stages: pre-training a chemical general model and fine-tuning on downstream domain data. Firstly, we adopt the publicly available MoLFormer model to obtain feature vectors for each solvent and salt in the electrolyte. Then, we perform a weighted average of embeddings for each token across all molecules, with weights determined by the respective electrolyte component ratios. Finally, we input the obtained electrolyte features into a Multi-layer Perceptron or Kolmogorov-Arnold Network to predict CE. Experimental results on a real-world dataset demonstrate that our method achieves SOTA for predicting CE compared to all baselines. Data and code used in this work will be made publicly available after the paper is published.

A robot dog equipped with a flamethrower could be used to stop weeds growing on farms, potentially offering a replacement for harmful herbicides. Even highly targeted herbicides can cause environmental problems, affecting local wildlife, and "superweeds" are quickly evolving resistance to the most common weed-killers like glyphosate. In search of an alternative solution, Dezhen Song at Texas A&M University and his colleagues have developed a weed control system that uses a brief burst of heat from a propane-powered flamethrower controlled by a robotic arm, attached to a Spot robot manufactured by Boston Dynamics. Rather than incinerate the weeds, the robot is designed to identify and heat up the centre of the plant, which can stop it growing for several weeks, says Song. "The weeds don't die – you just suppress their growth so it gives your crop a chance to fight the weed." Song and his team first tested the flame nozzle to make sure they could accurately target the weeds' centre.

A robot dog equipped with a blowtorch could be used to stop weeds growing on farms, potentially offering a replacement for harmful herbicides. Even highly targeted herbicides can cause environmental problems, affecting local wildlife, and "superweeds" are quickly evolving resistance to the most common weed-killers like glyphosate. In search of an alternative solution, Dezhen Song at Texas A&M University and his colleagues have developed a weed control system that uses a brief burst of heat from a propane-powered torch controlled by a robotic arm, attached to a Spot robot manufactured by Boston Dynamics. Rather than incinerate the weeds, the robot is designed to identify and heat up the centre of the plant, which can stop it growing for several weeks, says Song. "The weeds don't die – you just suppress their growth so it gives your crop a chance to fight the weed." The latest science news delivered to your inbox, every day.

Fish locomotion is enabled by fin rays-actively deformable boney rods, which manipulate the fin to facilitate complex interaction with surrounding water and enable propulsion. Replicating the performance and kinematics of the biological fin ray from an engineering perspective is a challenging task and has not been realised thus far. This work introduces a prototype of a fin ray-inspired origami electromagnetic tendon-driven (FOLD) actuator, designed to emulate the functional dynamics of fish fin rays. Constructed in minutes using origami/kirigami and paper joinery techniques from flat laser-cut polypropylene film, this actuator is low-cost at {\pounds}0.80 (\$1), simple to assemble, and durable for over one million cycles. We leverage its small size to embed eight into two fin membranes of a 135 mm long cuttlefish robot capable of four degrees of freedom swimming. We present an extensive kinematic and swimming parametric study with 1015 data points from 7.6 hours of video, which has been used to determine optimal kinematic parameters and validate theoretical constants observed in aquatic animals. Notably, the study explores the nuanced interplay between undulation patterns, power distribution, and locomotion efficiency, underscoring the potential of the actuator as a model system for the investigation of energy-efficient propulsion and control of bioinspired systems. The versatility of the actuator is further demonstrated by its integration into a fish and a jellyfish.

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform well leading to degraded results. Previous approaches to this problem have largely focused on broadening the training observation distribution, employing techniques like data augmentation and domain randomization. However, given the sequential nature of the RL decision-making problem, it is often the case that residual errors are propagated by the learned policy model and accumulate throughout the trajectory, resulting in highly degraded performance. In this paper, we leverage the observation that predicted rewards under domain shift, even though imperfect, can still be a useful signal to guide fine-tuning. We exploit this property to fine-tune a policy using reward prediction in the target domain. We have found that, even under significant domain shift, the predicted reward can still provide meaningful signal and fine-tuning substantially improves the original policy. Our approach, termed Predicted Reward Fine-tuning (PRFT), improves performance across diverse tasks in both simulated benchmarks and real-world experiments. More information is available at project web page: https://sites.google.com/view/prft.

Machine learning plays an increasingly important role in computational chemistry and materials science, complementing computationally intensive ab initio and first-principles methods. Despite their utility, machine-learning models often lack generalization capability and robustness during atomistic simulations, yielding unphysical energy and force predictions that hinder their real-world applications. We address this challenge by introducing a physics-informed, weakly supervised approach for training machine-learned interatomic potentials (MLIPs). We introduce two novel loss functions, extrapolating the potential energy via a Taylor expansion and using the concept of conservative forces. Our approach improves the accuracy of MLIPs applied to training tasks with sparse training data sets and reduces the need for pre-training computationally demanding models with large data sets. Particularly, we perform extensive experiments demonstrating reduced energy and force errors -- often lower by a factor of two -- for various baseline models and benchmark data sets. Finally, we show that our approach facilitates MLIPs' training in a setting where the computation of forces is infeasible at the reference level, such as those employing complete-basis-set extrapolation.

The vast majority of materials science knowledge exists in unstructured natural language, yet structured data is crucial for innovative and systematic materials design. Traditionally, the field has relied on manual curation and partial automation for data extraction for specific use cases. The advent of large language models (LLMs) represents a significant shift, potentially enabling efficient extraction of structured, actionable data from unstructured text by non-experts. While applying LLMs to materials science data extraction presents unique challenges, domain knowledge offers opportunities to guide and validate LLM outputs. This review provides a comprehensive overview of LLM-based structured data extraction in materials science, synthesizing current knowledge and outlining future directions. We address the lack of standardized guidelines and present frameworks for leveraging the synergy between LLMs and materials science expertise. This work serves as a foundational resource for researchers aiming to harness LLMs for data-driven materials research. The insights presented here could significantly enhance how researchers across disciplines access and utilize scientific information, potentially accelerating the development of novel materials for critical societal needs.

Continuous transportation of material in the mining industry is achieved by the dispatch of autonomous haul-trucks with discrete haulage capacities. Recently, Monte Carlo Tree Search (MCTS) was successfully deployed in tackling challenges of long-run optimality, scalability and adaptability in haul-truck dispatch. Typically, operational constraints imposed on the mine site are satisfied by heuristic controllers or human operators independent of the dispatch planning. This article incorporates operational constraint satisfaction into the dispatch planning by utilising the MCTS based dispatch planner Flow-Achieving Scheduling Tree (FAST). Operational constraint violation and satisfaction are modelled as opportunity costs in the combinatorial optimisation problem of dispatch. Explicit cost formulations are avoided by utilising MCTS generator models to derive opportunity costs. Experimental studies with four types of operational constraints demonstrate the success of utilising opportunity costs for constraint satisfaction, and the effectiveness of integrating constraints into dispatch planning.

While the search for new solvents in the chemical industry is of uttermost importance with respect to environmental considerations, this domain remains strongly tied to highly manual and visual inspection tasks by human experts. As the manipulated chemicals may imply a critical danger (CMR substances), mechanical protection barrier are used (fume hoods, gloveboxes). This, in turn, can induce postural discomfort in the long term. Carrying out this task using a remotely controlled robot to reproduce the desired vial motions would alleviate these postural constraints. Nevertheless, the adoption of such a system will depend on its ability to transcribe the users' expertise. Particular attention must be paid to the intuitiveness of the system : transparency of the actions performed, relevance of the perceptual feedback, etc. and, in particular, the fidelity of the movements performed in relation to the user's commands. However, the extent of the rotational movements to be generated and the task interactivity complicates the problem both from the point of view of the motor capacities of industrial robots and for the transparency/responsiveness of the control.To tackle the problen of guaranteeing a secure and reactive expression of the manual characteristics of this task, we propose to separate the control of movement into two parts: control of the path (set of spatial poses) and of the trajectories associated with this path (speed, direction of travel along the path). The user can then partially control the robot's movements, by choosing the type of generic, secure path and modulating the trajectory performed on this path in real time. Although this drastically limits the possibilities for interaction, we assume that this teleoperated system can enable this type of observation task to be carried out as effectively as for direct manipulation. This hypothesis was tested through an experiment in which a reading task, less dangerous but with similar characteristics to the application task, had to be performed using different variants of trajectory modulation. This experiment consisted in reading words printed on four white capsules (dimensions 6 x 12 mm) placed into cylindrical vials ( dimensions 16 mm x 70 mm). Four randomly selected vials were tested by each variant. Firstly, users had to perform the task via direct handling, then under conditions secured by a protection barrier. Users were then invited to perform the task using different trajectory modulation variants (modulation and passive viewing of a pre-recorded video, modulation of the trajectory of a Franka-Emika Panda robot performing the task in real time in front of a monocular Logitech Brio 4K camera). After each trial of a variant, users evaluate different aspects of this variant (manual and visual performance, ease of use, acceptability of the interface) through a questionnaire. During the trials, various objective criteria are also measured (number and nature of interaction with the interface, time and degree of success in the task). This experiment was carried out with 37 subjects (age : 27$\pm$5, 20 females). The data recorded showed that the proportion of successes, as well as the subjects' perceptions of visual performance, comfort of use and acceptability of the interface, were similar and high for all the variants. This suggests that this task is indeed achievable via the proposed interface. However, data also showed that average task completion times when using the trajectory modulation variants were significantly higher than handling by hand variants, which implies that the proposed remote semi-automatic control procedure fails to achieve satisfactory performance regarding execution time. An interface allowing more reactive manipulation of the vial's movements seems necessary, and will be tested in a future experiment.

The task of searching through patent documents is crucial for chemical patent recommendation and retrieval. This can be enhanced by creating a patent knowledge base (ChemPatKB) to aid in prior art searches and to provide a platform for domain experts to explore new innovations in chemical compound synthesis and use-cases. An essential foundational component of this KB is the extraction of important reaction snippets from long patents documents which facilitates multiple downstream tasks such as reaction co-reference resolution and chemical entity role identification. In this work, we explore the problem of extracting reactions spans from chemical patents in order to create a reactions resource database. We formulate this task as a paragraph-level sequence tagging problem, where the system is required to return a sequence of paragraphs that contain a description of a reaction. We propose several approaches and modifications of the baseline models and study how different methods generalize across different domains of chemical patents.