Generating high-quality human interactions holds significant value for applications like virtual reality and robotics. However, existing methods often fail to preserve unique individual characteristics or fully adhere to textual descriptions. To address these challenges, we introduce InterMoE, a novel framework built on a Dynamic Temporal-Selective Mixture of Experts. The core of InterMoE is a routing mechanism that synergistically uses both high-level text semantics and low-level motion context to dispatch temporal motion features to specialized experts. This allows experts to dynamically determine the selection capacity and focus on critical temporal features, thereby preserving specific individual characteristic identities while ensuring high semantic fidelity. Extensive experiments show that InterMoE achieves state-of-the-art performance in individual-specific high-fidelity 3D human interaction generation, reducing FID scores by 9% on the InterHuman dataset and 22% on InterX.

We introduce SegviGen , a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes an input 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the training data. This undoubtedly demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. Code and pretrained weights are publicly available at https://github.com/Nelipot-Lee/SegviGen.

Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive pipelines. We propose a Collaborative Multi-Agent Reasoning Framework based on upfront collaborative reasoning to overcome these issues. Our framework uses multiple agents to collaboratively analyze occlusion relationships and determine necessary boundary expansion, yielding a precise mask for inpainting. Concurrently, an agent generates fine-grained textual descriptions, enabling Fine-Grained Semantic Guidance. This ensures accurate object synthesis and prevents the regeneration of occluders or other unwanted elements, especially within large inpainting areas. Furthermore, our method directly produces layered RGBA outputs guided by visible masks and attention maps from a Diffusion Transformer, eliminating extra segmentation. Extensive evaluations demonstrate our framework achieves state-of-the-art visual quality.

Multi-part portrait customization aims to generate realistic human images by assembling specified body parts from multiple reference images, with significant applications in digital human creation. Existing customization methods typically follow two approaches: 1) test-time fine-tuning, which learn concepts effectively but is time-consuming and struggles with multi-part composition; 2) generalizable feed-forward methods, which offer efficiency but lack fine control over appearance specifics. To address these limitations, we present Parts2Whole, a diffusion-based generalizable portrait generator that harmoniously integrates multiple reference parts into high-fidelity human images by our proposed multi-reference mechanism. To adequately characterize each part, we propose a detail-aware appearance encoder, which is initialized and inherits powerful image priors from the pre-trained denoising U-Net, enabling the encoding of detailed information from reference images. The extracted features are incorporated into the denoising U-Net by a shared self-attention mechanism, enhanced by mask information for precise part selection. Additionally, we integrate pose map conditioning to control the target posture of generated portraits, facilitating more flexible customization. Extensive experiments demonstrate the superiority of our approach over existing methods and applicability to related tasks like pose transfer and pose-guided human image generation, showcasing its versatile conditioning. Our project is available at https://huanngzh.github.io/Parts2Whole/.

Multilabel pathological tissue segmentation is a vital task in computational pathology that aims to semantically segment different tissues within pathological images. Fully and weakly supervised models have demonstrated impressive performances in this regard. However, weakly supervised models still face challenges, such as the poor performance of nondominant samples and limited effectiveness of aggregation functions in conveying supervisory signals. To address these issues, we propose two key contributions: the introduction of a graph attention network(GAT) module to establish contextual relationships between pixels within patches and generate high-quality pseudo-labels, and the development of a novel global classified max pooling(GCMP) aggregation function that effectively transmits the supervision signal from weakly annotated labels and improves the model's classification accuracy. The experimental results show that our method improved the MIoU scores by 3.3 and 3 for the nondominant samples, necrosis(NEC) and lymphocytes(LYM), respectively, in the LUAD-HistoSeg test set. This led to an overall MIoU of 0.774, which is a 1.8 increase in the state-of-the-art(SOTA) performance. Similarly, our approach improved MIoU scores by 5.7 and 2 on the NEC and LYM samples, respectively, in the Breast Cancer Semantic Segmentation(BCSS) test set, resulting in an overall MIoU of 0.721. This represents a 1.6 increase in SOTA performance. In summary, our work addresses the issues of poor performance on nondominant samples and the suboptimal performance of aggregation functions. We propose a novel approach to achieve a significant performance improvement. This is extremely significant in reducing the workload of manual annotation and promoting the development of computational pathologies.

With the rapid development of distance education institution, there exist lots of educational data to be analyzed for improving online teaching. Decision tree is an effective analysis algorithm in data mining. In this paper, decision tree algorithm is used to analyze students' achievement data provided by the Open University of China. The experiment result shows that students have different achievement appearances between areas, and the classify rules which can improve on-line teaching are obtained.