The scarcity data of medical field brings the collaborative training in medical vision-language pre-training (VLP) cross different clients. Therefore, the collaborative training in medical VLP faces two challenges: First, the medical data requires privacy, thus can not directly shared across different clients. Second, medical data distribution across institutes is typically heterogeneous, hindering local model alignment and representation capabilities. To simultaneously overcome these two challenges, we propose the framework called personalized model selector with fused multimodal information (PMS-FM). The contribution of PMS-FM is two-fold: 1) PMS-FM uses embeddings to represent information in different formats, allowing for the fusion of multimodal data. 2) PMS-FM adapts to personalized data distributions by training multiple models. A model selector then identifies and selects the best-performing model for each individual client. Extensive experiments with multiple real-world medical datasets demonstrate the superb performance of PMS-FM over existing federated learning methods on different zero-shot classification tasks.

Distributed Quantum Computing (DQC) provides a scalable architecture by interconnecting multiple quantum processor units (QPUs).Among various DQC implementations, quantum data centers (QDCs) -where QPUs in different racks are connected through reconfigurable optical switch networks -are becoming feasible in the near term.However, the latency of cross-rack communications and dynamic switch reconfigurations poses unique challenges to communications in QDCs, significantly increasing the overall latency, thereby also reducing the overall fidelity.In this paper, we address these challenges by introducing a novel compiler that optimizes scheduling of communications across the program and network layers.Our evaluation shows that it reduces the overall latency by 8.02× over prior approaches with a small overhead and can be integrated with quantum error correction (QEC) to facilitate fault-tolerant quantum computing (FTQC).We have open-sourced our codes at https://zenodo.org/records/15377656.

Abstract In exploring the intersection of scholarly research with technological advancement and societal impact, our analysis delves into nearly 40 million research papers spanning from 1950 to 2020 across all fields of study in science. Our scrutiny reveals an intriguing phenomenon: papers characterized by a higher CD index, often considered transformative, paradoxically exhibit a diminished propensity to influence technological and societal domains. This observation suggests a latent bias against the CD index, prompting a deeper inquiry into its implications. To unravel this trend, we introduce the concept of “disruptive citation,” a nuanced metric gauging the absolute disruptive impact of papers. Notably, papers drawing higher disruptive citations exhibit a significantly higher probability to influence both technological and societal spheres. Upon examining the heterogeneity across years and fields, we identify a bias against the CD index predominantly in the last two decades and within STEM fields. However, the positive effects of disruptive impact remain consistent across all years and fields. Our findings remain robust even when employing alternative measures of disruptive impact and controlling for total citations. By shedding light on these dynamics, our study seeks to enrich discussions regarding the recognition and role of disruptive scientific endeavors in shaping our world.

Free-form scribbles are a convenient way for users to describe their intentions for image editing. However, prevalent issues arise in existing methods. First, the rich color of scribbles may contain information that deviates significantly from the original image distribution, causing common blending methods to yield unrealistic results due to inadequate interaction between the scribble and the image. Secondly, inputting extensive scribble areas may obscure crucial image components, resulting in identity loss post-editing. To address these issues, we propose a two-stage scribble editing method that achieves photo-realistic and identity-preserving editing. Our proposed method employs a two-channel multimodal interaction module, facilitating deep interaction between scribbles and images in channel and position domains, achieving semantic alignment and enhancement. In the second stage, we interact the editing offset with scribble area image content via the texture supplement module to achieve texture detail supplementation. Our method adeptly handles complex scribbles, even across extensive areas, demonstrating superior photo-realism and identity preservation in experimental results.

3D object detection is one of the most important tasks in autonomous driving and robotics. Our research focuses on tackling low efficiency issue of point-based methods, and we propose a novel Instance-Centroid Faster Point Sampling (IC-FPS) framework. We design a Neighboring Feature Diffusion Module (NFDM) to extract local features for the purpose of efficiently distinguishing the foreground from the background. Considering Farthest Point Sampling (FPS) strategy for downsampling is computationally intensive, we propose the Centroid-Instance Sampling Strategy (CISS). CISS samples center point in large-scale point cloud by rapidly sampling the centroid and instance points of the foreground block. The proposed IC-FPS framework can be inserted into every point-based model and effectively replace the first Set Abstraction (SA) layer. Extensive experiments on several public benchmarks demonstrate the superior performance of our proposed IC-FPS. On the Waymo dataset, IC-FPS significantly improves performance of the benchmark model and increases inference speed by 3.8 times. And real-time detection of point-based methods is realized for the first time, which is meaningful for industrial applications.

In the point cloud analysis task, the existing local feature aggregation descriptors (LFAD) do not fully utilize the neighborhood information of center points. Previous methods only use the distance information to constrain the local aggregation process, which is easy to be affected by abnormal points and cannot adequately fit the original geometry of the point cloud. This paper argues that fine-grained geometric information (FGGI) plays an important role in the aggregation of local features. Based on this, we propose a gradient-based local attention module to address the above problem, which is called Gradient Attention Module (GAM). GAM simplifies the process of extracting the gradient information in the neighborhood to explicit representation using the Zenith Angle matrix and Azimuth Angle matrix, which makes the module 35X faster. The comprehensive experiments on the ScanObjectNN dataset, ShapeNet dataset, S3DIS dataset, Modelnet40 dataset, and KITTI dataset demonstrate the effectiveness, efficientness, and generalization of our newly proposed GAM for 3D point cloud analysis. Especially in S3DIS, GAM achieves the highest index in the current point-based model with mIoU/OA/mAcc of 74.4%/90.6%/83.2%.

Inspired by CLIP’s excellent image/text representation capability and StyleGAN’s disentangled latent space, text-guide image editing techniques make significant progress. However, as CLIP cannot perform local fine-grained image/text alignment, existing methods suffer from entanglement problems. Moreover, there lacks a deep interaction between textual tokens and visual features, which may lead to unfaithful editing results. In this paper, we propose DF-CLIP for Disentangled and Fine-grained text-guide image editing. Specifically, we design a novel dual-branch LatentMask module to generate more accurate editing directions in StyleGAN’s latent space, which can avoid changes in text-unrelated areas. Furthermore, we present a Multi-modal Interaction module to associate the text embedding with the image embedding and perform a deep interaction between them, which greatly enhance the guidance of text in image editing process and accelerate the training convergence. Extensive experiments show that our models perform more disentangled and natural editing results with a shorter training time.

In recent years, cooperative jamming (CJ) is introduced as a promising method to improve the security performance in the presence of eavesdroppers. By masking the confidential signal with the help of the cooperative jammer, the signal-to-noise ratio of the eavesdropper can be selectively reduced without prior information, whereas the authorized receiver is unaffected since the CJ can be suppressed by some means. Unfortunately, with the impacts of the clock jitter caused by non-ideal crystals, the received CJ may suffer sampling clock offset, carrier frequency offset and phase noise, which deteriorates the performance of the CJ cancellation at the authorized receiver. In this paper, the impacts of clock jitter on CJ cancellation are investigated. First, the deterioration of CJ caused by sampling clock offset is modeled as inter-symbol interference (ISI) in the time domain. Then, the impacts of the sampling clock offset, carrier frequency offset and phase noise on the spectral purity of CJ are modeled as inter-frequency interference (IFI). Furthermore, the expression of the power of residual CJ (PRCJ) is derived to analyze the impacts of clock jitter on CJ cancellation. Finally, numerical results prove the theoretical analysis, indicating that the PRCJ increases as the carrier frequency offset and the 3 dB coherence bandwidth of phase noise increases, and is more sensitive to phase noise.

Although the use of pay-per-click mechanisms stimulates the prosperity of the mobile advertisement network, fraudulent ad clicks result in huge financial losses for advertisers. Extensive studies identify click fraud according to click/traffic patterns based on dynamic analysis. However, in this study, we identify a novel click fraud, named humanoid attack, which can circumvent existing detection schemes by generating fraudulent clicks with similar patterns to normal clicks. We implement the first tool ClickScanner to detect humanoid attacks on Android apps based on static analysis and variational AutoEncoders (VAEs) with limited knowledge of fraudulent examples. We define novel features to characterize the patterns of humanoid attacks in the apps' bytecode level. ClickScanner builds a data dependency graph (DDG) based on static analysis to extract these key features and form a feature vector. We then propose a classification model only trained on benign datasets to overcome the limited knowledge of humanoid attacks.