Instruction tuning adapts large language models (LLMs) to downstream tasks by training them to follow naturallanguage instructions. However, current biomedical instructiontuning pipelines rely largely on fixed instruction templates or randomly sampled instruction template pools, lacking contextaware or structured mechanisms for selecting instructions during fine-tuning. These limitations reduce semantic alignment between inputs and instructions and overlook task-specific differences in instruction sensitivity, which affect model performance in clinical NLP. We introduce CAIT (Context-Adaptive Instruction Tuning), a configurable framework that systematically explores instruction selection through three complementary mechanisms: (1) contextadaptive matching using keyword-driven clinical context detection, (2) deterministic round-robin cycling to ensure balanced template exposure, and (3) controlled random sampling to preserve exploration. Evaluation on three representative clinical NLP tasks, Medical Question Answering, Clinical Diagnosis, and Clinical Reasoning, demonstrates significant task-dependent performance variation. Round-robin selection improves diagnostic accuracy by 6.7% over random sampling (0.64 vs. 0.60), while context-adaptive selection increases clinical-reasoning conclusion accuracy by 5.7% (0.37 vs. 0.35). Medical QA exhibits relative insensitivity to selection strategy, indicating that optimal instruction selection is task-specific rather than universal. Future studies should explore semantically grounded approaches, such as embedding-based similarity or contextual bandit formulations for enhanced adaptive instruction selection.

Named entity recognition (NER) is a key task in natural language processing, but existing methods often fail to effectively handle nested structures due to fuzzy entity boundaries and structural ambiguity. To address this challenge, we propose a novel nested NER method based on an IoU-aware denoising diffusion model, which formulates the nested NER task as a generative denoising process that progressively recovers gold entity spans from noisy span proposals. We generate noisy samples during training by gradually adding Gaussian noise to the ground-truth entity boundaries. We then train a denoiser incorporating a top-k selective attention mechanism to refine entity span proposals iteratively. To strengthen the alignment between boundary localization and entity classification, we introduce an IoU-aware loss function that optimizes the overlap between predicted and ground-truth spans. This design more accurately guides boundary regression and effectively reduces misalignment caused by conventional regression losses. Our model leverages sentence features and timesteps as conditional inputs to capture contextual information throughout the denoising process. During inference, the model generates final entity predictions by starting from random noise spans and iteratively refining them through a multi-step reverse diffusion process. We conduct extensive experiments on four nested NER datasets, ACE2004, ACE2005, GENIA, and KBP2017, as well as two flat NER datasets, CoNLL2003 and OntoNotes. Experimental results show that the proposed method consistently outperforms existing advanced models across all benchmarks, demonstrating its effectiveness.

To address the challenge of detecting small targets caused by the small size and high quantity of targets in current unmanned aerial vehicle (UAV) aerial images, we propose a novel multi-scale self-attention graph neural network model based on YOLOv8. This model can learn the weak semantic information generated between small objects, guiding the network to estimate reliable details of small objects and capture relationships between them, thereby achieving accurate detection and classification of small objects through enhancing similar features. Additionally, we introduce an improved objective box loss function to tackle the issue of high-density object detection. We evaluate our proposed model on the widely-used open-source dataset Visdrone2019 and DOTAv2. Experimental results demonstrate that our model outperforms the existing baseline YOLOv8, achieving a significant improvement of 7.40% in terms of mAP50. Ablation experiments further validate the effectiveness of our designed modules and loss function. Furthermore, our approach can efficiently detect small objects in complex road traffic environments, contributing to the advancement of smart city development.

BACKGROUND: Recently, the process of evolution information and the deep learning network has promoted the improvement of protein contact prediction methods. Nevertheless, still remain some bottleneck: (1) One of the bottlenecks is the prediction of orphans and other fewer evolution information proteins. (2) The other bottleneck is the method of predicting single-sequence-based proteins mainly focuses on selecting protein sequence features and tuning the neural network architecture, However, while the deeper neural networks improve prediction accuracy, there is still the problem of increasing the computational burden. Compared with other neural networks in the field of protein prediction, the graph neural network has the following advantages: due to the advantage of revealing the topology structure via graph neural network and being able to take advantage of the hierarchical structure and local connectivity of graph neural networks has certain advantages in capturing the features of different levels of abstraction in protein molecules. When using protein sequence and structure information for joint training, the dependencies between the two kinds of information can be better captured. And it can process protein molecular structures of different lengths and shapes, while traditional neural networks need to convert proteins into fixed-size vectors or matrices for processing. RESULTS: Here, we propose a single-sequence-based protein contact map predictor PCP-GC-LM, with dual-level graph neural networks and convolution networks. Our method performs better with other single-sequence-based predictors in different independent tests. In addition, to verify the validity of our method against complex protein structures, we will also compare it with other methods in two homodimers protein test sets (DeepHomo test dataset and CASP-CAPRI target dataset). Furthermore, we also perform ablation experiments to demonstrate the necessity of a dual graph network. In all, our framework presents new modules to accurately predict inter-chain contact maps in protein and it's also useful to analyze interactions in other types of protein complexes.

BACKGROUND: Cryo-electron microscopy (Cryo-EM) plays an increasingly important role in the determination of the three-dimensional (3D) structure of macromolecules. In order to achieve 3D reconstruction results close to atomic resolution, 2D single-particle image classification is not only conducive to single-particle selection, but also a key step that affects 3D reconstruction. The main task is to cluster and align 2D single-grain images into non-heterogeneous groups to obtain sharper single-grain images by averaging calculations. The main difficulties are that the cryo-EM single-particle image has a low signal-to-noise ratio (SNR), cannot manually label the data, and the projection direction is random and the distribution is unknown. Therefore, in the low SNR scenario, how to obtain the characteristic information of the effective particles, improve the clustering accuracy, and thus improve the reconstruction accuracy, is a key problem in the 2D image analysis of single particles of cryo-EM. RESULTS: Aiming at the above problems, we propose a learnable deep clustering method and a fast alignment weighted averaging method based on frequency domain space to effectively improve the class averaging results and improve the reconstruction accuracy. In particular, it is very prominent in the feature extraction and dimensionality reduction module. Compared with the classification method based on Bayesian and great likelihood, a large amount of single particle data is required to estimate the relative angle orientation of macromolecular single particles in the 3D structure, and we propose that the clustering method shows good results. CONCLUSIONS: SimcryoCluster can use the contrastive learning method to perform well in the unlabeled high-noise cryo-EM single particle image classification task, making it an important tool for cryo-EM protein structure determination.

In recent years, crowds en sing has become a hot topic in contemporary research. However, the traditional crowd-sensing model has some issues, such as low-quality data uploaded by users, privacy and security issues, and a lack of incentive for user participation. To address these challenges, we propose a crowdsensing framework that combines blockchain and federated learning to build a decentralized security framework. Our framework enables each participant to upload model gradient data to the crowdsensing platform for aggregation while ensuring user privacy and security. And we proposed a model aggregation method based on reputation value. In addition, we also designed a reverse auction algorithm based on historical reputation to filter the set of candidates who want to participate in the task, to obtain a higher quality set of participants. Security analysis and experimental results show that this model guarantees data quality and data privacy, and enhances user participation motivation.

Blood pressure prediction is a crucial tool in preventing cardiovascular-related diseases. Therefore, improving the accuracy of blood pressure prediction plays a critical role in disease prevention. Previous models for blood pressure prediction have faced challenges related to inadequate feature extraction and insignificant effective information mining. To address these issues, this paper proposes an improved Unet-based continuous blood pressure prediction method that effectively processes the spatial information of multi-scale feature maps and establishes long-term dependencies between multi-scale channels. The proposed model achieves high accuracy meeting the requirements of the AAMI standard and the BHS A Grade. Moreover, the mean absolute errors of systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 3.41 mmHg and 2.58 mmHg, respectively, with standard deviations (STD) of 6.25 mmHg and 5.08 mmHg.

BACKGROUND: Quality assessment of protein tertiary structure prediction models, in which structures of the best quality are selected from decoys, is a major challenge in protein structure prediction, and is crucial to determine a model's utility and potential applications. Estimating the quality of a single model predicts the model's quality based on the single model itself. In general, the Pearson correlation value of the quality assessment method increases in tandem with an increase in the quality of the model pool. However, there is no consensus regarding the best method to select a few good models from the poor quality model pool. RESULTS: We introduce a novel single-model quality assessment method for poor quality models that uses simple linear combinations of six features. We perform weighted search and linear regression on a large dataset of models from the 12th Critical Assessment of Protein Structure Prediction (CASP12) and benchmark the results on CASP13 models. We demonstrate that our method achieves outstanding performance on poor quality models. CONCLUSIONS: According to results of poor protein structure assessment based on six features, contact prediction and relying on fewer prediction features can improve selection accuracy.

As digital sports video becomes increasingly pervasive, semantic video summary becomes one of the important components for the next generation of multimedia applications. Ontology is a feasible way to mine the semantic information from the video stream. However, current ontology‐based methods did not concentrate on the effectiveness and soundness of semantic reasoning. Here, the authors propose a content‐directed ontology reasoning approach to produce meaningful sports video summarisation. The proposed ontology can facilitate the metadata acquisition of video and the improvement of query performance. It also provides a flexible way to query the sports video database, which cannot be achieved by simple keyword search. For annotating, describing and managing the sports video content, we propose a sports video descriptive language (SVDL) based on the proposed ontology. Moreover, the semantically meaningful sports video abstraction is produced by reasoning engine which is based on the extension of the Tableau algorithm. Meanwhile, the soundness and completeness of the reasoning algorithm can be solidly proved. Subjective assessment experimental results reveal the reliability and efficiency of the propose scheme.