Joint Energy-based Model (JEM) [12] is a recently proposed hybrid model that retains strong discriminative power of modern CNN classifiers, while generating samples rivaling the quality of GAN-based approaches. In this paper, we propose a variety of new training procedures and architecture features to improve JEM’s accuracy, training stability, and speed altogether. 1) We propose a proximal SGLD to generate samples in the proximity of samples from previous step, which improves the stability. 2) We further treat the approximate maximum likelihood learning of EBM as a multi-step differential game, and extend the YOPO framework [47] to cut out redundant calculations during backpropagation, which accelerates the training substantially. 3) Rather than initializing SGLD chain from random noise, we introduce a new informative initialization that samples from a distribution estimated from training data. 4) This informative initialization allows us to enable batch normalization in JEM, which further releases the power of modern CNN architectures for hybrid modeling. ¹

Small object detection in UAV imagery remains challenging due to complex aerial perspectives and the presence of dense, small targets with blurred boundaries. To address these challenges, we propose ACD-DETR, an adaptive end-to-end Transformer detector tailored for UAV-based small object detection. The framework introduces three core modules: the Multi-Scale Edge-Enhanced Feature Fusion Module (MSEFM) to preserve fine-grained details; the Omni-Grained Boundary Calibrator (OG-BC) for boundary-aware semantic fusion; and the Dynamic Position Bias Attention-based Intra-scale Feature Interaction (DPB-AIFI) to enhance spatial reasoning. Furthermore, we introduce ACD-DETR-SBA+, a fusion-enhanced variant that removes OG-BC and DPB-AIFI while deploying densely connected Semantic–Boundary Aggregation (SBA) modules to intensify boundary–semantic fusion. This design sacrifices computational efficiency in exchange for higher detection precision, making it suitable for resource-rich deployment scenarios. On the VisDrone2019 dataset, ACD-DETR achieves 50.9% mAP@0.5, outperforming the RT-DETR-R18 baseline by 3.6 percentage points, while reducing parameters by 18.5%. ACD-DETR-SBA+ further improves accuracy to 52.0% mAP@0.5, demonstrating the benefit of SBA-based fusion. Extensive experiments on the VisDrone2019 and DOTA datasets demonstrate that ACD-DETR achieves a state-of-the-art trade-off between accuracy and efficiency, while ACD-DETR-SBA+ achieves further performance improvements at higher computational cost. Ablation studies and visual analyses validate the effectiveness of the proposed modules and design strategies.

In this paper, the time series classification frontier method MiniRocket was used to classify earthquakes, blasts, and background noise. From supervised to unsupervised classification, a comprehensive analysis was carried out, and finally, the supervised method achieved excellent results. The relatively simple model, MiniRocket, is only a one-dimensional convolutional neural network structure which has achieved the best comprehensive results, and its computational efficiency is far stronger than other supervised classification methods. Through our experimental results, we found that the MiniRocket model could well-extract the decisive features of the seismic sensing signal. In order to try to eliminate the tedious work of making data labels, we proposed a novel lightweight collaborative learning for seismic sensing signals (LCL-SSS) based on the method of feature extraction in MiniRocket combined with unsupervised classification. The new method gives new vitality to the unsupervised classification method that could not be used originally and opens up a new path for the unsupervised classification of seismic sensing signals.

As the primary mRNA delivery vehicles, ionizable lipid nanoparticles (LNPs) exhibit excellent safety, high transfection efficiency, and strong immune response induction. However, the screening process for LNPs is time-consuming and costly. To expedite the identification of high-transfection-efficiency mRNA drug delivery systems, we propose an explainable LNPs transfection efficiency prediction model, called TransMA. TransMA employs a multi-modal molecular structure fusion architecture, wherein the fine-grained atomic spatial relationship extractor named molecule 3D Transformer captures three-dimensional spatial features of the molecule, and the coarse-grained atomic sequence extractor named molecule Mamba captures one-dimensional molecular features. We design the mol-attention mechanism block, enabling it to align coarse and fine-grained atomic features and captures relationships between atomic spatial and sequential structures. TransMA achieves state-of-the-art performance in predicting transfection efficiency using the scaffold and cliff data splitting methods on the current largest LNPs dataset, including Hela and RAW cell lines. Moreover, we find that TransMA captures the relationship between subtle structural changes and significant transfection efficiency variations, providing valuable insights for LNPs design. Additionally, TransMA's predictions on external transfection efficiency data maintain a consistent order with actual transfection efficiencies, demonstrating its robust generalization capability. The code, model and data are made publicly available at https://github.com/wklix/TransMA/tree/master. We hope that high-accuracy transfection prediction models in the future can aid in LNPs design and initial screening, thereby assisting in accelerating the mRNA design process.

The demand for object pose estimation is steadily increasing, and deep learning has propelled the advancement of this field. However, the majority of research endeavors face challenges in their applicability to industrial production. This is primarily due to the high cost of annotating 3D data, which places higher demands on the generalization capabilities of neural network models. Additionally, existing methods struggle to handle the abundance of textureless objects commonly found in industrial settings. Finally, there is a strong demand for real-time processing capabilities in industrial production processes. Therefore, in this study, we introduced a dual-channel Siamese framework to address these challenges in industrial applications. The architecture employs a Siamese structure for template matching, enabling it to learn the matching capability between the templates constructed from high-fidelity simulated data and real-world scenes. This capacity satisfies the requirements for generalization to unseen objects. Building upon this, we utilized two feature extraction channels to separately process RGB and depth information, addressing the limited feature issue associated with textureless objects. Through our experiments, we demonstrated that this architecture effectively estimates the three-dimensional pose of objects, achieving a 6.0% to 10.9% improvement compared to the state-of-the-art methods, while exhibiting robust generalization and real-time processing capabilities.