Explore the vast range of titles available.

In the field of chemical synthesis planning, the accurate recommendation of reaction conditions is essential for achieving successful outcomes. This work introduces an innovative deep learning approach designed to address the complex task of predicting appropriate reagents, solvents, and reaction temperatures for chemical reactions. Our proposed methodology combines a multi-label classification model with a ranking model to offer tailored reaction condition recommendations based on relevance scores derived from anticipated product yields. To tackle the challenge of limited data for unfavorable reaction contexts, we employed the technique of hard negative sampling to generate reaction conditions that might be mistakenly classified as suitable, forcing the model to refine its decision boundaries, especially in challenging cases. Our developed model excels in proposing conditions where an exact match to the recorded solvents and reagents is found within the top-10 predictions 73% of the time. It also predicts temperatures within ± 20 ° C of the recorded temperature in 89% of test cases. Notably, the model demonstrates its capacity to recommend multiple viable reaction conditions, with accuracy varying based on the availability of condition records associated with each reaction. What sets this model apart is its ability to suggest alternative reaction conditions beyond the constraints of the dataset. This underscores its potential to inspire innovative approaches in chemical research, presenting a compelling opportunity for advancing chemical synthesis planning and elevating the field of reaction engineering. Scientific contribution The combination of multi-label classification and ranking models provides tailored recommendations for reaction conditions based on the reaction yields. A novel approach is presented to address the issue of data scarcity in negative reaction conditions through data augmentation. Graphical Abstract

Recently, imputation techniques have been adapted to predict activity values among sparse bioactivity matrices, showing improvements in predictive performance over traditional QSAR models. These models are able to use experimental activity values for auxiliary assays when predicting the activity of a test compound on a specific assay. In this study, we tested three different multi-task imputation techniques on three classification-based toxicity datasets: two of small scale (12 assays each) and one large scale with 417 assays. Moreover, we analyzed in detail the improvements shown by the imputation models. We found that test compounds that were dissimilar to training compounds, as well as test compounds with a large number of experimental values for other assays, showed the largest improvements. We also investigated the impact of sparsity on the improvements seen as well as the relatedness of the assays being considered. Our results show that even a small amount of additional information can provide imputation methods with a strong boost in predictive performance over traditional single task and multi-task predictive models.

In the short term, a fully autonomous level of machine intelligence cannot be achieved. Humans are still an important part of HCI systems, and intelligent systems should be able to “feel” and “predict” human intentions in order to achieve dynamic coordination between humans and machines. Intent recognition is very important to improve the accuracy and efficiency of the HCI system. However, it is far from enough to focus only on explicit intent. There is a lot of vague and hidden implicit intent in the process of human–computer interaction. Based on passive brain–computer interface (pBCI) technology, this paper proposes a method to integrate humans into HCI systems naturally, which is to establish an intent-based HCI model and automatically recognize the implicit intent according to human EEG signals. In view of the existing problems of few divisible patterns and low efficiency of implicit intent recognition, this paper finally proves that EEG can be used as the basis for judging human implicit intent through extracting multi-task intention, carrying out experiments, and constructing algorithmic models. The CSP + SVM algorithm model can effectively improve the EEG decoding performance of implicit intent in HCI, and the effectiveness of the CSP algorithm on intention feature extraction is further verified by combining 3D space visualization. The translation of implicit intent information is of significance for the study of intent-based HCI models, the development of HCI systems, and the improvement of human–machine collaboration efficiency.

Reactive oxygen species (ROS) occupy a mechanistically complex role in cancer, simultaneously sustaining oncogenic signaling and generating oxidative vulnerability. Existing antioxidant prediction approaches fail to account for this mechanistic stratification or the chemical diversity of redox‐active small molecules. Here, we curate human‐relevant ROS modulators from PubChem BioAssays and the antioxidant database (AODB) and segregate the compiled compounds into three coherent mechanistic regimes: signaling/metabolic modulators (HIF, NF‐κB), antioxidant‐defense activators (NRF2/KEAP1), and ROS source inhibitors (NOX/XDH). Building on this, we introduce a dual prediction framework, named mechanism‐informed hierarchical multitask learning (MI‐HMTL), comprising a multimodal chemistry‐driven classical model (BioChem‐AOS) and a mechanism‐aware hierarchical multitask deep learning system (MA‐AOS), both powered by unified chemical dice integrator (CDI) generalised embeddings. MA‐AOS achieves high predictive accuracy across six mechanistic targets and, similar to structure‐driven scoring, uniquely recapitulates metabolic redox behavior in human tumor metabolomics samples. These findings demonstrate that the mechanistic context governs antioxidant function, positioning this framework as a scalable platform for mechanism‐guided discovery of redox therapeutics. A mechanism‐aware deep learning framework links chemical structure to redox biology, enabling pathway‐specific prediction of antioxidant mechanisms across six core reactive oxygen species‐regulatory systems and outperforming structure‐only baseline by learning biologically grounded rather than purely chemical similarity rules.

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified framework. Typical methods heavily rely on region-of-interest (RoI) operations to extract local features and complex post-processing steps to produce final predictions. To address these limitations, we propose TextFormer, a query-based end-to-end text spotter with a transformer architecture. Specifically, using query embedding per text instance, TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multitask modeling. It allows for mutual training and optimization of classification, segmentation and recognition branches, resulting in deeper feature sharing without sacrificing flexibility or simplicity. Additionally, we design an adaptive global aggregation (AGG) module to transfer global features into sequential features for reading arbitrarily-shaped texts, which overcomes the suboptimization problem of RoI operations. Furthermore, potential corpus information is utilized from weak annotations to full labels through mixed supervision, further improving text detection and end-to-end text spotting results. Extensive experiments on various bilingual (i.e., English and Chinese) benchmarks demonstrate the superiority of our method. Especially on the TDA-ReCTS dataset, TextFormer surpasses the state-of-the-art method in terms of 1-NED by 13.2%.

Hydrological signatures (HS) have proven to be highly effective in calibrating physically‐based hydrological models, enhancing their process consistency. However, their integration into parameter optimization for deep learning (DL)‐based hydrological models has been limited. To address this gap, we propose a novel HS‐informed framework that dynamically integrates HS into DL parameterization through a multi‐task learning approach. This study evaluates the impact of HS integration on model performance using a large‐scale, global hydrological data set. The HS‐informed model achieved a significant performance improvement, with a median Nash‐Sutcliffe Efficiency (NSE) of 0.739, compared to 0.666 for the baseline model across the test set. Notably, the most pronounced improvements in NSE were observed in hydrologically complex basins, including baseflow‐dominated (+0.135), drought‐prone (+0.148), and flood‐prone basins (+0.159). Sensitivity analysis further revealed that the HS‐informed model could leverage extended historical input data (over 120 days) to sustain robust performance (median NSE of 0.715) over a 30‐day forecast period. Shapley Additive Explanations analysis highlighted two key mechanisms underlying these improvements: the enhanced recognition of long‐term hydrological patterns through improved memory and a better representation of catchment heterogeneity by emphasizing non‐climatic attributes. These findings demonstrate that integrating HS offers a superior approach to traditional point‐error‐based calibration in AI‐driven hydrological modeling.

Deep learning has shown great promise in hydrological modeling, especially when large sample data sets are used to capture generalizable patterns across basins. However, challenges remain in addressing data scarcity and ensuring model reliability, particularly when key hydrological observations are modeled as individual tasks. In this study, we shift from traditional single‐task learning (STL) to multi‐task learning (MTL) to leverage the interconnections among hydrological variables and potentially improve modeling outcomes in data‐limited settings. Using a Long Short‐Term Memory (LSTM) neural network with the Catchment Attributes and Meteorology for Large‐Sample Studies data set, we developed an MTL model to predict streamflow and evapotranspiration across 591 basins. The MTL model exhibited comparable predictions for streamflow and evapotranspiration to STL models, with similar spatiotemporal generalization across varying data sizes. MTL's strength appeared when using LSTM cell state probes to predict the non‐target variable, surface soil moisture (SSM), showing slightly higher correlation coefficients. This highlights MTL's ability to capture intrinsic hydrological rules, enhancing model reliability. Leveraging this ability, we further explored MTL's advantages under two data‐limited scenarios: one with less‐observed SSM data and another with no available streamflow data. In both cases, MTL, supported by another well‐observed variable, outperformed STL models by a notable difference. These findings highlight MTL's potential to address the challenges of hydrological modeling in data‐limited basins. As Earth observation data continues to grow, MTL could become a valuable approach for building more reliable and generalizable hydrological models.

We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known single-task 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across-tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select—not learn—a few common variables across the tasks.

The process of evapotranspiration transfers liquid water from vegetation and soil surfaces to the atmosphere, the so-called latent heat flux ( Q LE ), and modulates the Earth’s energy, water, and carbon cycle. Vegetation controls Q LE by regulating leaf stomata opening (surface resistance r s in the Big Leaf approach) and by altering surface roughness (aerodynamic resistance r a ). Estimating r s and r a across different vegetation types is a key challenge in predicting Q LE . We propose a hybrid approach that combines mechanistic modeling and machine learning for modeling Q LE . The hybrid model combines a feed-forward neural network which estimates the resistances from observations as intermediate variables and a mechanistic model in an end-to-end setting. In the hybrid modeling setup, we make use of the Penman–Monteith equation in conjunction with multi-year flux measurements across different forest and grassland sites from the FLUXNET database. This hybrid model setup is successful in predicting Q LE , however, this approach leads to equifinal solutions in terms of estimated physical parameters. We follow two different strategies to constrain the hybrid model and therefore control for the equifinality that arises when the two resistances are estimated simultaneously. One strategy is to impose an a priori constraint on r a based on mechanistic assumptions (theory-driven strategy), while the other strategy makes use of more observational data and adds a constraint in predicting r a through multi-task learning of both latent and sensible heat flux ( Q H ; data-driven strategy) together. Our results show that all hybrid models predict the target variables with a high degree of success, with R 2 = 0.82–0.89 for grasslands and R 2 = 0.70–0.80 for forest sites at the mean diurnal scale. The predicted r s and r a show strong physical consistency across the two regularized hybrid models, but are physically implausible in the under-constrained hybrid model. The hybrid models are robust in reproducing consistent results for energy fluxes and resistances across different scales (diurnal, seasonal, and interannual), reflecting their ability to learn the physical dependence of the target variables on the meteorological inputs. As a next step, we propose to test these heavily observation-informed parameterizations derived through hybrid modeling as a substitute for ad hoc formulations in Earth system models.

Considering the data collection and labeling cost in real-world applications, training a model with limited examples is an essential problem in machine learning, visual recognition, etc. Directly training a model on such few-shot learning (FSL) tasks falls into the over-fitting dilemma, which would turn to an effective task-level inductive bias as a key supervision. By treating the few-shot task as an entirety, extracting task-level pattern, and learning a task-agnostic model initialization, the model-agnostic meta-learning (MAML) framework enables the applications of various models on the FSL tasks. Given a training set with a few examples, MAML optimizes a model via fixed gradient descent steps from an initial point chosen beforehand. Although this general framework possesses empirically satisfactory results, its initialization neglects the task-specific characteristics and aggravates the computational burden as well. In this manuscript, we propose our AdaptiVely InitiAlized Task OptimizeR (Aviator) approach for few-shot learning, which incorporates task context into the determination of the model initialization. This task-specific initialization facilitates the model optimization process so that it obtains high-quality model solutions efficiently. To this end, we decouple the model and apply a set transformation over the training set to determine the initial top-layer classifier. Re-parameterization of the first-order gradient descent approximation promotes the gradient back-propagation. Experiments on synthetic and benchmark data sets validate that our Aviator approach achieves the state-of-the-art performance, and visualization results demonstrate the task-adaptive features of our proposed Aviator method.