Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic-level insights. However, the referential aspect -- linking molecular concepts to specific structural components -- remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model's referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular understanding within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, comprising 117k QA pairs, and developed a multi-agent grounding prototype as proof of concept. This system outperforms existing models, including GPT-4o, and its grounding outputs have been integrated to enhance traditional tasks such as molecular captioning and ATC (Anatomical, Therapeutic, Chemical) classification.

Large language models (LLMs) exhibit probabilistic output characteristics, yet conventional evaluation frameworks rely on deterministic scalar metrics. This study introduces a Bayesian approach for LLM capability assessment that integrates prior knowledge through probabilistic inference, addressing limitations under limited-sample regimes. By treating model capabilities as latent variables and leveraging a curated query set to induce discriminative responses, we formalize model ranking as a Bayesian hypothesis testing problem over mutually exclusive capability intervals. Experimental evaluations with GPT-series models demonstrate that the proposed method achieves superior discrimination compared to conventional evaluation methods. Results indicate that even with reduced sample sizes, the approach maintains statistical robustness while providing actionable insights, such as probabilistic statements about a model's likelihood of surpassing specific baselines. This work advances LLM evaluation methodologies by bridging Bayesian inference with practical constraints in real-world deployment scenarios.

We present a machine-learning guided approach to predict saturation magnetization (MS) and coercivity (HC) in Fe-rich soft magnetic alloys, particularly Fe-Si-B systems. ML models trained on experimental data reveals that increasing Si and B content reduces MS from 1.81T (DFT~2.04 T) to ~1.54 T (DFT~1.56T) in Fe-Si-B, which is attributed to decreased magnetic density and structural modifications. Experimental validation of ML predicted magnetic saturation on Fe-1Si-1B (2.09T), Fe-5Si-5B (2.01T) and Fe-10Si-10B (1.54T) alloy compositions further support our findings. These trends are consistent with density functional theory (DFT) predictions, which link increased electronic disorder and band broadening to lower MS values. Experimental validation on selected alloys confirms the predictive accuracy of the ML model, with good agreement across compositions. Beyond predictive accuracy, detailed uncertainty quantification and model interpretability including through feature importance and partial dependence analysis reveals that MS is governed by a nonlinear interplay between Fe content, early transition metal ratios, and annealing temperature, while HC is more sensitive to processing conditions such as ribbon thickness and thermal treatment windows. The ML framework was further applied to Fe-Si-B/Cr/Cu/Zr/Nb alloys in a pseudo-quaternary compositional space, which shows comparable magnetic properties to NANOMET (Fe84.8Si0.5B9.4Cu0.8 P3.5C1), FINEMET (Fe73.5Si13.5B9 Cu1Nb3), NANOPERM (Fe88Zr7B4Cu1), and HITPERM (Fe44Co44Zr7B4Cu1. Our fundings demonstrate the potential of ML framework for accelerated search of high-performance, Co- and Ni-free, soft magnetic materials.

Animals can finely modulate their leg stiffness to interact with complex terrains and absorb sudden shocks. In feats like leaping and sprinting, animals demonstrate a sophisticated interplay of opposing muscle pairs that actively modulate joint stiffness, while tendons and ligaments act as biological springs storing and releasing energy. Although legged robots have achieved notable progress in robust locomotion, they still lack the refined adaptability inherent in animal motor control. Integrating mechanisms that allow active control of leg stiffness presents a pathway towards more resilient robotic systems. This paper proposes a novel mechanical design to integrate compliancy into robot legs based on tensegrity - a structural principle that combines flexible cables and rigid elements to balance tension and compression. Tensegrity structures naturally allow for passive compliance, making them well-suited for absorbing impacts and adapting to diverse terrains. Our design features a robot leg with tensegrity joints and a mechanism to control the joint's rotational stiffness by modulating the tension of the cable actuation system. We demonstrate that the robot leg can reduce the impact forces of sudden shocks by at least 34.7 % and achieve a similar leg flexion under a load difference of 10.26 N by adjusting its stiffness configuration. The results indicate that tensegrity-based leg designs harbors potential towards more resilient and adaptable legged robots.

In industrial settings, surface defects on steel can significantly compromise its service life and elevate potential safety risks. Traditional defect detection methods predominantly rely on manual inspection, which suffers from low efficiency and high costs. Although automated defect detection approaches based on Convolutional Neural Networks(e.g., Mask R-CNN) have advanced rapidly, their reliability remains challenged due to data annotation uncertainties during deep model training and overfitting issues. These limitations may lead to detection deviations when processing the given new test samples, rendering automated detection processes unreliable. To address this challenge, we first evaluate the detection model's practical performance through calibration data that satisfies the independent and identically distributed (i.i.d) condition with test data. Specifically, we define a loss function for each calibration sample to quantify detection error rates, such as the complement of recall rate and false discovery rate. Subsequently, we derive a statistically rigorous threshold based on a user-defined risk level to identify high-probability defective pixels in test images, thereby constructing prediction sets (e.g., defect regions). This methodology ensures that the expected error rate (mean error rate) on the test set remains strictly bounced by the predefined risk level. Additionally, we observe a negative correlation between the average prediction set size and the risk level on the test set, establishing a statistically rigorous metric for assessing detection model uncertainty. Furthermore, our study demonstrates robust and efficient control over the expected test set error rate across varying calibration-to-test partitioning ratios, validating the method's adaptability and operational effectiveness.

Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressing societal challenges such as extreme natural hazard events. As generalized models, LLMs often struggle to provide context-specific information, particularly in areas requiring specialized knowledge. In this work we propose a retrieval-augmented generation (RAG)-based multi-agent LLM system to support analysis and decision-making in the context of natural hazards and extreme weather events. As a proof of concept, we present WildfireGPT, a specialized system focused on wildfire hazards. The architecture employs a user-centered, multi-agent design to deliver tailored risk insights across diverse stakeholder groups. By integrating natural hazard and extreme weather projection data, observational datasets, and scientific literature through an RAG framework, the system ensures both the accuracy and contextual relevance of the information it provides. Evaluation across ten expert-led case studies demonstrates that WildfireGPT significantly outperforms existing LLM-based solutions for decision support.

We present a design called Proof of Gradient Optimization (PoGO) for blockchain consensus, where miners produce veri fiable evidence of training large-scale machine-learning models. Bu ilding on previous work [1,2,3], we incorporate quantized gradients (4-bit precision [7] [8][9]) to reduce storage and computation requirements, wh ile still preserving the ability of verifiers to check that real progress h as been made on lowering the model's loss. Additionally, we employ Merkl e proofs over the full 32-bit model to handle large parameter sets and to enable random leaf checks with minimal on-chain data. We illustrate these ideas using GPT-3 (175B parameters) [5] as a reference example and also r efer to smaller but high-performance models (e.g., Gemma 3 with 27B parameters). We provide an empirical cost analysis showing that ve rification is significantly cheaper than training, thanks in part to quant ization and sampling. We also discuss the necessity of longer block time s (potentially hours) when incorporating meaningful training steps, the t rade-offs when using specialized GPU hardware, and how binary diffs may incr ementally optimize updates. Finally, we note that fine-tuning can be ha ndled in a similar manner, merely changing the dataset and the manner o f sampling but preserving the overall verification flow. Our protocol al lows verifiers to issue either positive or negative attestations; these are aggregated at finalization to either confirm the update or slash the miner.

Accurately predicting chemical reactions is essential for driving innovation in synthetic chemistry, with broad applications in medicine, manufacturing, and agriculture. At the same time, reaction prediction is a complex problem which can be both time-consuming and resource-intensive for chemists to solve. Deep learning methods offer an appealing solution by enabling high-throughput reaction prediction. However, many existing models are trained on the US Patent Office dataset and treat reactions as overall transformations: mapping reactants directly to products with limited interpretability or mechanistic insight. To address this, we introduce PMechRP (Polar Mechanistic Reaction Predictor), a system that trains machine learning models on the PMechDB dataset, which represents reactions as polar elementary steps that capture electron flow and mechanistic detail. To further expand model coverage and improve generalization, we augment PMechDB with a diverse set of combinatorially generated reactions. We train and compare a range of machine learning models, including transformer-based, graph-based, and two-step siamese architectures. Our best-performing approach was a hybrid model, which combines a 5-ensemble of Chemformer models with a two-step Siamese framework to leverage the accuracy of transformer architectures, while filtering away "alchemical" products using the two-step network predictions. For evaluation, we use a test split of the PMechDB dataset and additionally curate a human benchmark dataset consisting of complete mechanistic pathways extracted from an organic chemistry textbook. Our hybrid model achieves a top-10 accuracy of 94.9% on the PMechDB test set and a target recovery rate of 84.9% on the pathway dataset.

The acoustic response of an object can reveal a lot about its global state, for example its material properties or the extrinsic contacts it is making with the world. In this work, we build an active acoustic sensing gripper equipped with two piezoelectric fingers: one for generating signals, the other for receiving them. By sending an acoustic vibration from one finger to the other through an object, we gain insight into an object's acoustic properties and contact state. We use this system to classify objects, estimate grasping position, estimate poses of internal structures, and classify the types of extrinsic contacts an object is making with the environment. Using our contact type classification model, we tackle a standard long-horizon manipulation problem: peg insertion. We use a simple simulated transition model based on the performance of our sensor to train an imitation learning policy that is robust to imperfect predictions from the classifier. We finally demonstrate the policy on a UR5 robot with active acoustic sensing as the only feedback.

Atom probe tomography (APT) is a burgeoning characterization technique that provides compositional mapping of materials in three-dimensions at near-atomic scale. Since its significant expansion in the past 30 years, we estimate that one million APT datasets have been collected, each containing millions to billions of individual ions. Their analysis and the extraction of microstructural information has largely relied upon individual users whose varied level of expertise causes clear and documented bias. Current practices hinder efficient data processing, and make challenging standardization and the deployment of data analysis workflows that would be compliant with FAIR data principles. Over the past decade, building upon the long-standing expertise of the APT community in the development of advanced data processing or data mining techniques, there has been a surge of novel machine learning (ML) approaches aiming for user-independence, and that are efficient, reproducible, and robust from a statistics perspective. Here, we provide a snapshot review of this rapidly evolving field. We begin with a brief introduction to APT and the nature of the APT data. This is followed by an overview of relevant ML algorithms and a comprehensive review of their applications to APT. We also discuss how ML can enable discoveries beyond human capability, offering new insights into the mechanisms within materials. Finally, we provide guidance for future directions in this domain.