As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking (NNW) as a promising solution. Among various NNW approaches, weight-based methods are favored for their simplicity and practicality; however, they remain generally vulnerable to forging and overwriting attacks. To address those challenges, we propose *NeuralMark*, a robust method built around a *hashed watermark filter*. Specifically, we utilize a hash function to generate an irreversible binary watermark from a secret key, which is then used as a filter to select the model parameters for embedding. This design cleverly intertwines the embedding parameters with the hashed watermark, providing a robust defense against both forging and overwriting attacks. Average pooling is also incorporated to resist fine-tuning and pruning attacks. Furthermore, it can be seamlessly integrated into various neural network architectures, ensuring broad applicability. We theoretically analyze its security boundary and highlight the necessity of using a hashed watermark as a filtering mechanism. Empirically, we demonstrate its effectiveness and robustness across 13 distinct Convolutional and Transformer architectures, covering five image classification tasks and one text generation task.

Recently, zero-shot object customization generation methods have rapidly developed and shown tremendous potential for applications. For instance, in the e-commerce domain, consumers can observe the visual effect of furniture placed within their personal living spaces or clothes worn on their own bodies. Many existing approaches perform object customization generation based on diffusion models and extracted reference object features. However, the generated object significantly diverges from the original reference object in details such as patterns and curves. Particularly for asymmetrical reference objects, the absence of comprehensive multi-viewpoint information prevents the generation of object poses that harmonize with the background scene. To address these shortcomings, we have constructed a novel dataset comprising multi-angle images of furniture and indoor scenes. Based on diffusion models, we introduce HomeDiffusion, which can leverage multi-viewpoint images of the same reference object to accurately generate visually harmonious object poses within specified areas of the background scene. During the diffusion process, we further extract high-fidelity details of the reference object and perform cross-attention with the noise latents in the latent space, thereby ensuring the preservation of details in the customized object generation. Extensive qualitative and quantitative experiments demonstrate that our method achieves superior performance over other existing zero-shot as well as few-shot object customization approaches.

Understanding the conformational landscape of proteins is essential for elucidating protein function and facilitating drug design. However, existing protein conformation benchmarks fail to capture the full energy landscape, limiting their ability to evaluate the diversity and physical plausibility of AI-generated structures. We introduce ProteinConformers, a large-scale benchmark dataset comprising over 381,000 physically realistic conformations for 87 CASP targets. These were derived from more than 40,000 structural decoys via extensive all-atom molecular dynamics simulations totaling over 6 million CPU hours. Using this dataset, we propose novel metrics to evaluate conformational diversity and plausibility, and systematically benchmark six protein conformation generative models. Our results highlight that leveraging large-scale protein sequence data can enhance a model’s ability to explore conformational space, potentially reducing reliance on MD-derived data. Additionally, we find that PDB and MD datasets influence model performance differently, current models perform well on inter-atomic distance prediction but struggle with inter-residue orientation generation. Overall, our dataset, evaluation metrics, and benchmarking results provide the first comprehensive foundation for assessing generative models in protein conformational modeling. Dataset and instructions are available at https://huggingface.co/ datasets/Jim990908/ProteinConformers/tree/main. Codes are stored at https://github.com/auroua/ProteinConformers. An interactive website locates at https://zhanggroup.org/ProteinConformers.

Bursting oscillations and bifurcation mechanisms in piecewise circuit systems have long been a research focus in the fields of dynamics and control. While most previous studies have focused on systems with a fixed discontinuous boundary, this paper examines systems with a variable discontinuous boundary. We develop a mathematical model based on Chua’s circuit and present numerical simulations of bursting oscillations under varying parameters. The impact of the translation of the discontinuous boundary (TDB) on the system’s topological structure and non-smooth bifurcations is analyzed. By combining the two-parameter bifurcation set of equilibrium points with the superposition diagram of the transformed phase diagram (TPD), we reveal mechanisms behind different bursting modes induced by the TDB. A Multisim-based simulation circuit is designed to validate the research results. It is found that the topology of the equilibrium branches of each subsystem remains the same during the TDB, but the number of smooth bifurcations changes due to the switching between subsystems. The TDB also alters the characteristics of the boundary equilibrium point, leading to the catastrophic disappearance or emergence of non-smooth limit cycles, which consequently changes the number of spiking oscillations. Moreover, the interaction of the slow passage effect (SPE) and the TDB causes the trajectory to remain in a delayed segment, affecting the number of spiking oscillations per period. Additionally, the TDB may lead to the disappearance of bursting oscillations, then the system exhibits a behavior similar to that of simple harmonic motion. Our study expands the scope of research on piecewise-smooth circuit systems.

Efficient and accurate detection of surface defects on trains is crucial for ensuring train safety. However, the insufficient defect samples and their diverse patterns make defect detection in complex environments highly challenging. This paper proposes a novel train surface defect detection model (ViLG) via visual-language knowledge guidance. By leveraging broad semantic knowledge of CLIP, the model compensates for the insufficient defect semantics in tiny datasets and enhances the ability to recognize unseen defects. First, we propose Visual Feature Guidance with CLIP, which enriches and enhances the global representation capabilities of backbone while preserving its self-learning ability for visual representations. This improves semantic understanding of complex scenarios and diverse defects. Second, we propose Defect Query Selector, which selects defect queries based on the semantic relevance between texts and global feature embeddings. This increases attention to potential defects and reduces missed detections. Finally, we propose Semantic Consistency Loss, which semantically aligns defect queries with defect prompts. With additional cross-modal supervision signals, it refines the semantics of defects. For real-world scenarios with normal reference images, we propose ViLG+, which effectively filters false positives using feature similarity. It further verifies that the global embeddings effectively represent the overall structure of visual scenes as well as subtle local features. Compared with other advanced methods on two train surface defect datasets and two public defect datasets, ViLG shows higher precision, recall, and average precision on unseen defects with relatively faster speed, with average improvements of 23.58, 3.23, and 6.05, and has a more balanced false positive rate and false negative rate.

Industrial micro aerial vehicles (MAVs) with robotic manipulators have numerous applications in search and rescue tasks that reduce risks to human beings. However, such tasks distinctly require MAVs to have the capability of real-time autonomous navigation only with onboard sensors, especially in GPS-denied applications. This article introduces a new approach to onboard vision-based autonomous state estimation and mapping for MAVs' navigation in unknown environments. The algorithms run on board and do not need an external positioning system to assist autonomous navigation. The state estimator is developed to provide MAV's current pose on the basis of the extended Kalman filter by using image patch features. Inverse depth convergence monitoring and local bundle adjustment are utilized to improve the accuracy. The mapping algorithm for navigation is developed according to a real-time stereo matching method for three-dimensional perception. Finally, we have performed several experiments to demonstrate the effectiveness of the proposed approach.

Ubiquitous and Wearable Computing both have the goal of pushing the computer into the background, supporting all kinds of human activities. Application areas include areas such as everyday environments (e.g. clothing, home, office), promoting new forms of creative learning via physical/virtual objects, and new tools for interactive design. In this paper, we thrust ubiquitous computing into the extremely hostile environment of the sparring ring of a martial art competition. Our system uses piezoelectric force sensors that transmit signals wirelessly to enable the detection of when a significant impact has been delivered to a competitor's body. The objective is to support the judges in scoring the sparring matches accurately, while preserving the goal of merging and blending into the background of the activity. The system therefore must take into account of the rules of the game, be responsive in real-time asynchronously, and often cope with untrained operators of the system. We present a pilot study of the finished prototype and detail our experience.