Personalized recommender systems are critical for enhancing user engagement across a range of digital platforms. However, conventional approaches rely heavily on centralized data collection, raising significant privacy concerns. Federated recommender systems (PFRS) address these concerns by decentralizing model training, ensuring user data privacy. Despite the progress, existing methods still struggle with capturing the multi-faceted nature of user and transferring global knowledge effectively. In this work, we propose FedMUR, a novel federated recommendation framework that models user representation as a Gaussian mixture distribution, capturing users' multi-faceted characteristics. Each Gaussian component corresponds to a distinct interest facet, with adaptive mixture weights representing the user's preference intensity toward each facet. To facilitate knowledge transfer, FedMUR constructs global consistent prototypes that encode shared behavioral trends across users via popularity-weighted optimal transport. These prototypes enhance local models by injecting global shared patterns into personalized representation learning. Extensive experiments across several real-world datasets demonstrate that FedMUR significantly outperforms existing state-of-the-art federated recommendation systems.

Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the desired modifications in a single step, which often struggles with ambiguous user intent, complex transformations, or the need for progressive refinements. As a result, these methods frequently produce inconsistent outcomes or fail to meet user expectations. To address these challenges, we propose a multi-turn image editing framework that enables users to iteratively refine their edits, progressively achieving more satisfactory results. Our approach leverages flow matching for accurate image inversion and a dual-objective Linear Quadratic Regulators (LQR) for stable sampling, effectively mitigating error accumulation. Additionally, by analyzing the layer-wise roles of transformers, we introduce a adaptive attention highlighting method that enhances editability while preserving multi-turn coherence. Extensive experiments demonstrate that our framework significantly improves edit success rates and visual fidelity compared to existing methods.

Virtual human avatars are essential for applications such as gaming, augmented reality, and virtual production. However, existing methods struggle to achieve high fidelity reconstruction from monocular input while keeping hardware costs low. Many approaches rely on the SMPL body prior and apply vertex offsets to represent clothed avatars. Unfortunately, excessive offsets often cause misalignment and blurred contours, particularly around clothing wrinkles, silhouette boundaries, and facial regions. To address these limitations, we propose a dual branch framework for human avatar reconstruction from monocular video. A lightweight Vertex Align Net (VAN) predicts per-vertex normal direction offsets on the SMPL mesh to achieve coarse geometric alignment and guide Gaussian-based human avatar modeling. In parallel, we construct a high resolution facial Gaussian branch based on FLAME estimated parameters, with facial regions localized via pretrained detectors. The facial and body renderings are fused using a semantic mask to enhance facial clarity and ensure globally consistent avatar appearance. Experiments demonstrate that our method surpasses state of the art approaches in modeling animatable human avatars with fine grained fidelity.

Remote sensing (RS) image segmentation faces persistent challenges due to limited labeled data and the presence of long-tailed distribution. While semi-supervised learning (SSL) can leverage unlabeled data, it often struggles to address the severe class imbalance that manifests as a long-tailed distribution. To tackle this, we propose the Dynamic Category Preference-Aware Semantic Segmentation Framework (CPSeg). Unlike existing methods that estimate model’s category preference on pseudo-labels or rely on prior information, CPSeg introduces a simple yet effective approach to directly model this preference. By feeding a Pattern-Free Image (PFI) into the model, we capture its current tendencies toward certain categories without any prior knowledge. This dynamically learned category preference drives two key components of CPSeg. First, it enables adaptive weight allocation, which adjusts the training focus by assigning higher weights to low-frequency categories, promoting balanced learning across all categories. Second, CPSeg introduces a Category-wise Pairwise Memory Bank (CPMB) and integrates category preference information to perform dynamic preference-aware data augmentation, making the augmentation process more suitable for addressing the long-tailed distribution problem. When compared with other advanced approaches, CPSeg exhibits superior performance, achieving mean intersection over union (mIoU) scores of 74.50% on the GID-15 and 59.26% on the MSl dataset, respectively, under a challenging 1/8 labeled data setting, highlighting its strong potential for addressing long-tailed distribution and class imbalance in RS segmentation.

Despite the remarkable process in the field of arbitrary image style transfer (AST), inconsistent evaluation continues to plague style transfer research. Existing methods often suffer from limited objective evaluation and inconsistent subjective feedback, hindering reliable comparisons among AST variants. In this study, we propose a multi-granularity assessment system that combines standardized objective and subjective evaluations. We collect a fine-grained dataset considering a range of image contexts such as different scenes, object complexities, and rich parsing information from multiple sources. Objective and subjective studies are conducted using the collected dataset. Specifically, we innovate on traditional subjective studies by developing an online evaluation system utilizing a combination of point-wise, pair-wise, and group-wise questionnaires. Finally, we bridge the gap between objective and subjective evaluations by examining the consistency between the results from the two studies. We experimentally evaluate CNN-based, flow-based, transformer-based, and diffusion-based AST methods by the proposed multi-granularity assessment system, which lays the foundation for a reliable and robust evaluation. Providing standardized measures, objective data, and detailed subjective feedback empowers researchers to make informed comparisons and drive innovation in this rapidly evolving field.