Personalized image generation is crucial for improving the user experience, as it renders reference images into preferred ones according to user visual preferences. Although effective, existing methods face two main issues. First, existing methods treat all items in the user's historical sequence equally when extracting user preferences, overlooking the varying semantic similarities between historical items and the reference item. Disproportionately high weights for low-similarity items distort user visual preferences for the reference item. Second, existing methods heavily rely on consistency between generated and reference images to optimize generation, which leads to underfitting user preferences and hinders personalization. To address these issues, we propose Retrieval Augmented Personalized Image GenerAtion guided by Recommendation (RAGAR). Our approach uses a retrieval mechanism to assign different weights to historical items according to their similarities to the reference item, thereby extracting more refined users' visual preferences for the reference item. Then we introduce a novel rank task based on the multi-modal ranking model to optimize the personalization of the generated images instead of forcing depend on consistency. Extensive experiments and human evaluations on three real-world datasets demonstrate that RAGAR achieves significant improvements in both personalization and semantic metrics compared to five baselines.

Low Earth Orbit (LEO) satellite constellations offer great promise for distributed sensing and intelligence in future networks. However, their potential is hindered by communication inefficiencies and heterogeneous data distributions, which lead to excessive transmission costs, slow convergence, and degraded model performance. Existing federated learning (FL) methods alleviate data privacy and communication load, but typically rely on centralized coordination and lack robustness to Non-IID data, especially in dynamic satellite environments. To address these limitations, we propose the GOOD (Gossip Learning with OOD Enhancement) framework, a fully decentralized, gossip-based FL system enhanced with adaptive out-of-distribution (OOD) detection. GOOD enables satellites to evaluate the distributional compatibility of incoming model updates using lightweight OOD scores, thereby reducing negative transfer and eliminating ineffective transmissions. Additionally, it introduces an adaptive grouping mechanism that dynamically clusters satellites based on distributional similarity, optimizing inter-satellite communication. Extensive experiments demonstrate that GOOD consistently outperforms prior decentralized FL approaches in terms of convergence accuracy and communication efficiency under both statistical and semantic Non-IID conditions, making it a compelling solution for autonomous on-orbit learning.

Real-time communication (RTC) systems, such as video conferencing and cloud gaming, depend on effective congestion control (CC) algorithms to manage diverse network conditions and access technologies like Wi-Fi, LTE/5G, and satellite networks. While tools like AlphaRTC and Pandia have significantly advanced CC algorithm development for WebRTC, there is an absence of a unified framework for systematic benchmarking and cross-platform evaluation.

Artistic style transfer aims to repaint the content image with the learned artistic style. Existing artistic style transfer methods can be divided into two categories: small model-based approaches and pre-trained large-scale model-based approaches. Small model-based approaches can preserve the content strucuture, but fail to produce highly realistic stylized images and introduce artifacts and disharmonious patterns; Pre-trained large-scale model-based approaches can generate highly realistic stylized images but struggle with preserving the content structure. To address the above issues, we propose ArtBank, a novel artistic style transfer framework, to generate highly realistic stylized images while preserving the content structure of the content images. Specifically, to sufficiently dig out the knowledge embedded in pre-trained large-scale models, an Implicit Style Prompt Bank (ISPB), a set of trainable parameter matrices, is designed to learn and store knowledge from the collection of artworks and behave as a visual prompt to guide pre-trained large-scale models to generate highly realistic stylized images while preserving content structure. Besides, to accelerate training the above ISPB, we propose a novel Spatial-Statistical-based self-Attention Module (SSAM). The qualitative and quantitative experiments demonstrate the superiority of our proposed method over state-of-the-art artistic style transfer methods. Code is available at https://github.com/Jamie-Cheung/ArtBank.

Bayesian Optimization is a powerful technique employed to address black-box optimization problems, finding applications in various domains. Meta-Bayesian Optimization (Meta-BO) is a specific approach designed to improve data efficiency by leveraging information from related tasks. In recent years, there has been notable progress in the field of Meta-BO, particularly in surrogate models and acquisition functions that utilize data from related tasks. However, these advancements have predominantly focused on singular aspects of Bayesian optimization, leaving untapped potential in the integration of these two aspects.We propose a novel approach that enables the surrogate model to effectively integrate the acquisition function for Bayesian optimization tasks. This makes the surrogate model to transcend mere function approximation, effectively addressing the aforementioned problem. Taking inspiration from large language models that receive feedback in actual human dialogue tasks, our approach involves pre-training a neural process surrogate model and subsequently leveraging feedback obtained from real Bayesian optimization scenarios to enhance its Bayesian optimization capability. To achieve this, we have extended the Proximal Policy Optimization to utilize feedback derived from Bayesian optimization, incentivizing the pre-trained surrogate model. Our approach has undergone thorough evaluation across diverse models and various benchmark functions. Remarkably, even with minimal incentives, the models exhibit significant advancements in Bayesian optimization, highlighting the effectiveness and robust generalization ability of our proposed method.

Currently, reference-based super-resolution (RefSR) techniques leverage high-resolution (HR) reference images to provide useful content and texture information for low-resolution (LR) images during the super-resolution (SR) process. Nevertheless, it is time-consuming, laborious, and even impossible in some cases to find high-quality reference images. To tackle this problem, we propose a brand-new self-reference image super-resolution approach using a pre-trained diffusion large model and a window adjustable transformer, termed DWTrans. Our proposed method does not require explicitly inputting manually acquired reference images during training and inference. Specifically, we feed the degraded LR images into a pre-trained stable diffusion large model to automatically generate corresponding high-quality self-reference (SRef) images that provide valuable high-frequency details for the LR images in the process of SR. To extract valuable high-frequency information in SRef images, we design a window adjustable transformer with both non-adjustable window layer (NWL) and adjustable window layer (AWL). The NWL learns local features from LR images using a dense window, while the AWL acquires global features from the SRef images using a random sparse window. Furthermore, to fully utilize the high-frequency features in the SRef image, we introduce the adaptive deformable fusion module to adaptively fuse the features of the LR and SRef images. Experimental results validate that our proposed DWTrans outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually.

Estimating similarity between streaming sets is a fundamental problem with many Internet applications, such as evaluating user similarity in social networks and analyzing similarity of IP hosts' behaviors in communication networks. For a “streaming” data set, its elements arrive in a streaming fashion, and we have only limited memory to process its element stream. To meet the size constraint of high-speed memory, this data set must be stored as a summary called `sketch'. Then, in the distributed scenario, the sketches of all data sets can be efficiently transferred to a central server to calculate the Jaccard similarity between each pair of sets. To balance between memory cost and similarity evaluation accuracy, many sketching methods have been proposed, such as MinHash, virtual odd sketch (VOS) and MaxLogHash. However, both MinHash and MaxLogHash fail to deal with fully dynamic streaming sets that allow the deletion of elements. Although VOS partially solves the deletion problem by adopting the odd sketch structure and enhance it with a physical-virtual structure, its similarity evaluation accuracy will degrade when handling small streaming sets. In this paper, we propose a multi-resolution odd sketch (MROS), which allows more accurate similarity estimation with less memory consumption. Its design is to encode a streaming set into multiple layers of odd sketches with exponentially reducing sampling probabilities. We conduct both experiments and analysis to evaluate our method. Results show that the estimation accuracy of our MROS outperforms existing works, e.g., MinHash and VOS.

Summary: Although the genome-wide association study (GWAS) is a powerful method to identify disease-associated variants, it does not directly address the biological mechanisms underlying such genetic association signals. Here, we present PGA, a Perl- and Java-based program for post-GWAS analysis that predicts likely disease genes given a list of GWAS-reported variants. Designed with a command line interface, PGA incorporates genomic and eQTL data in identifying disease gene candidates and uses gene network and ontology data to score them based upon the strength of their relationship to the disease in question. Availability and implementation: http://zdzlab.einstein.yu.edu/1/pga.html. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

Bioinformatics (2013) 29(19), 2509–2511 doi:10.1093/bioinformatics/btt430 The authors would like to apologize for an error in the author byline. Christophe Lemetre is included as the first author in the author group and should read as above. And also, the first two authors should be regarded as joint First Authors.

SUMMARY: The extraction of targeted subnetworks is a powerful way to identify functional modules and pathways within complex networks. Here, we present SubNet, a Java-based stand-alone program for extracting subnetworks, given a basal network and a set of selected nodes. Designed with a graphical user-friendly interface, SubNet combines four different extraction methods, which offer the possibility to interrogate a biological network according to the question investigated. Of note, we developed a method based on the highly successful Google PageRank algorithm to extract the subnetwork using the node centrality metric, to which possible node weights of the selected genes can be incorporated. AVAILABILITY: http://www.zdzlab.org/1/subnet.html