Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes as undifferentiated wholes and fails to recognize complete object from partial observations. In this paper, we propose InstaScene, a new paradigm towards holistic 3D perception of complex scenes with a primary goal: decomposing arbitrary instances while ensuring complete reconstruction. To achieve precise decomposition, we develop a novel spatial contrastive learning by tracing rasterization of each instance across views, significantly enhancing semantic supervision in cluttered scenes. To overcome incompleteness from limited observations, we introduce in-situ generation that harnesses valuable observations and geometric cues, effectively guiding 3D generative models to reconstruct complete instances that seamlessly align with the real world. Experiments on scene decomposition and object completion across complex real-world and synthetic scenes demonstrate that our method achieves superior decomposition accuracy while producing geometrically faithful and visually intact objects.

Human video synthesis aims to create lifelike characters in various environments. While 2D diffusion-based methods have made significant progress, they struggle to generalize to complex 3D poses and varying scene backgrounds. To address these limitations, we introduce CFSynthesis, a novel framework for generating high-quality human videos with customizable attributes, including identity, motion, and scene configurations. Our method leverages a texture-SMPL-based representation to ensure consistent and stable character appearances across free viewpoints. Additionally, we introduce a novel foreground-background separation strategy that effectively decomposes the scene as foreground and background, enabling seamless integration of user-defined backgrounds. Experimental results on multiple datasets show that CFSynthesis not only achieves state-of-the-art performance in complex human animations but also adapts effectively to 3D motions in free-view and user-specified scenarios.

Scene-level 3D generation represents a critical frontier in multimedia and computer graphics. While existing approaches have achieved encouraging progress, they still face challenges such as constrained object diversity and limited support for interactive editing. In this paper, we present HiScene, a novel hierarchical framework that bridges the gap between 2D image generation and 3D object generation and delivers high-fidelity scenes with compositional identities and aesthetic scene content. Our key insight is treating scenes as hierarchical ''objects'' under isometric views, where a room functions as a complex object that can be further decomposed into manipulatable items. This hierarchical approach enables us to generate 3D content that aligns with 2D representations while maintaining compositional structure. To ensure completeness and spatial alignment of each decomposed instance, we develop a video-diffusion-based amodal completion technique that effectively handles occlusions and shadows between objects, and introduce shape prior injection to ensure spatial coherence within the scene. Experimental results demonstrate that our method produces more natural object arrangements and complete object instances suitable for interactive applications, while maintaining physical plausibility and alignment with user inputs.

Website fingerprinting (WF) attacks exploit distinctive traffic patterns to identify the specific web page a user visits over anonymized connections. While traditional WF attacks have achieved impressive results, they are typically evaluated in abundant labeled data settings and assume that website traffic features remain static. This assumption is often unrealistic in real-world scenarios. Recent methods either rely on deep learning, which still requires large amounts of labeled data, or employ self-supervised pre-training to ease this demand. However, they leave clustering information crucial for few-shot WF attacks underexplored, leaving ample room for performance gains. In this paper, we propose a novel self-supervised pre-training model for few-shot WF attacks, called Swapped Contrastive Clustering (SwCC). SwCC proposes a comprehensive and principled data augmentation scheme, combining Tor-tailored transformations with statistical procedures to foster robust and discriminative feature learning for WF attacks. SwCC further introduces an innovative dual-level contrastive learning framework that jointly leverages instance-level and prototype-based objectives, which can further perform latent-space clustering on extracted features in WF attacks. Our pre-trained model can be fine-tuned in few-shot learning scenarios and achieves state-of-the-art(SOTA) performance on few-shot WF attack tasks. Under a 5-shot learning setting in a closed-world scenario, our SwCC achieves up to 83.5% accuracy when the evaluation traces are collected from an environment unseen by the WF adversary, outperforming the SOTA methods.

Pre-trained Transformer models have demonstrated remarkable ability in learning generalizable feature representations for encrypted traffic analysis, driving the development of effective methods in this field. Their separate hidden and output layer architecture supports efficient multi-task joint classification. However, in real-world multi-task scenarios, these models face challenges due to high computational overhead and performance degradation on individual tasks during joint training. To address these, we introduce ET-FS (Encrypted Traffic Classification via Functional Specialization), a novel three-stage framework for efficient multi-task training in encrypted traffic classification. In the first stage, ET-FS constructs a multi-task joint model based on pre-trained encrypted traffic models and task groups, followed by joint fine-tuning using single-task labeled datasets. In the second stage, we propose an innovative method to assess the nature of tasks within the model and groups, allowing identification of optimal parameters. In the third stage, we leverage the functional specialization of multi-head attention in Transformer architectures, introducing a partially frozen multi-task fine-tuning strategy. Specifically, during the final phase of training, only a selected proportion of task-related attention heads are updated, while irrelevant heads are frozen, mitigating gradient interference between tasks. Experimental results show that the ET-FS Final Model, trained with the proposed framework, is applicable across diverse scenarios. With sufficient resources, it surpasses baselines on all tasks and metrics, achieving 93% accuracy for app classification, 98% for service classification, and over 99% for other tasks. Even with limited resources and imbalanced datasets, it maintains robust performance and good generalization, highlighting its practical potential for encrypted traffic classification.

Spatial transcriptomics enables the contextualization of gene expression with spatial organization, advancing our understanding of development, disease, and tissue architecture. However, existing analysis pipelines require multiple tools to explore spatial domains, and few methods can jointly analyse spatial data from annotation-free and annotation-guided perspectives with high interpretability. We therefore propose the Spatial Topic Model (SpaTM), a topic-modelling framework capable of annotation-guided and annotation-free analysis of spatial transcriptomes. SpaTM can learn gene programs that represent histology-based annotations while also inferring spatial domains with an annotation-free approach if manual annotations are limited or noisy. In benchmarking experiments, SpaTM achieves competitive performance at spatial label prediction and clustering when compared with existing state-of-the-art methods. We demonstrate SpaTM's interpretability by using topic mixtures to capture transcriptional programs in dorsolateral prefrontal cortex and ductal carcinoma samples and show how its intuitive framework facilitates the integration of spatial transcriptomics tasks. Finally, we showcase how SpaTM can extend the analysis of large-scale snRNA-seq atlases in human brains with Major Depressive Disorder. Overall, SpaTM provides a unified and interpretable analysis framework for spatial transcriptomics, enabling competitive performance in multiple tasks while inferring biologically informed gene programs.

In this paper, we present TexPro, a novel method for high-fidelity material generation for input 3D meshes given text prompts. Unlike existing text-conditioned texture generation methods that typically generate RGB textures with baked lighting, TexPro is able to produce diverse texture maps via procedural material modeling, which enables physically-based rendering, relighting, and additional benefits inherent to procedural materials. Specifically, we first generate multi-view reference images given the input textual prompt by employing the latest text-to-image model. We then derive texture maps through rendering-based optimization with recent differentiable procedural materials. To this end, we design several techniques to handle the misalignment between the generated multiview images and 3D meshes, and introduce a novel material agent that enhances material classification and matching by exploring both part-level understanding and object-aware material reasoning. Experiments demonstrate the superiority of the proposed method over existing SOTAs, and its capability of relighting.

Encrypted traffic classification is highly challenging in network security due to the need for extracting robust features from content-agnostic traffic data. Existing approaches face critical issues: (i) Distribution drift, caused by reliance on the closedworld assumption, limits adaptability to real-world, shifting patterns; (ii) Dependence on labeled data restricts applicability where such data is scarce or unavailable. Large language models (LLMs) have demonstrated remarkable potential in offering generalizable solutions across a wide range of tasks, achieving notable success in various specialized fields. However, their effectiveness in traffic analysis remains constrained by challenges in adapting to the unique requirements of the traffic domain. In this paper, we introduce a novel traffic representation model named Encrypted Traffic Out-of-Distribution Instruction Tuning with LLM (ETooL), which integrates LLMs with knowledge of traffic structures through a self-supervised instruction tuning paradigm. This framework establishes connections between textual information and traffic interactions. ETooL demonstrates more robust classification performance and superior generalization in both supervised and zero-shot traffic classification tasks. Notably, it achieves significant improvements in F1 scores: APP53 (I.I.D.) to 93.19%(6.62%↑) and 92.11%(4.19%↑), APP53 (O.O.D.) to 74.88%(18.17%↑) and 72.13%(15.15%↑), and ISCX-Botnet (O.O.D.) to 95.03%(9.16%↑) and 81.95%(12.08%↑). Additionally, we construct NETD, a traffic dataset designed to support dynamic distributional shifts, and use it to validate ETooL’s effectiveness under varying distributional conditions. Furthermore, we evaluate the efficiency gains achieved through ETooL’s instruction tuning approach.

Diffusion-based methods have achieved prominent success in generating 2D media. However, accomplishing similar proficiencies for scene-level mesh texturing in 3D spatial applications, e.g., XR/VR, remains constrained, primarily due to the intricate nature of 3D geometry and the necessity for immersive free-viewpoint rendering. In this paper, we propose a novel indoor scene texturing framework, which delivers text-driven texture generation with enchanting details and authentic spatial coherence. The key insight is to first imagine a stylized 360° panoramic texture from the central viewpoint of the scene, and then propagate it to the rest areas with inpainting and imitating techniques. To ensure meaningful and aligned textures to the scene, we develop a novel coarse-to-fine panoramic texture generation approach with dual texture alignment, which both considers the geometry and texture cues of the captured scenes. To survive cluttered geometries during texture propagation, we design a separated strategy, which conducts texture inpainting in visible regions and then learns an implicit imitating network to synthesize textures in occluded and tiny structural areas. Extensive experiments and the immersive VR application on real-world indoor scenes demonstrate the high quality of the generated textures and the engaging experience on VR headsets. Project webpage: https://ybbbbt.com/publication/dreamspace.

Static voltage stability of power grids will become more sensitive to the coordinated operation of renewable energy resources (RESs) and energy storage systems (ESSes) due to their different output characteristics. This paper presents a generalized approach for static voltage stability evaluation under coordinated operations of wind power, PV and energy storage stations. First, a combined model for coordinated operation of stations which describes the output characteristics of active and reactive power is established. Then, the integration point of stations is optimized by modal analysis such that the most sensitive bus in the system can be located. Afterwards, the static voltage stability margin can be evaluated for load buses via impedance modulus margin index (IMMI). Furthermore, impact of penetration rates and penetration rate ratio among wind power, PV and energy storage stations on static voltage stability margin is investigated. To validate the effectiveness of proposed method, a standard IEEE 14 bus test system is studied and numerical results are presented.

For satellite Internet the content was examined by location and time of day, as well as within the context of online social networks. The ground Information-Centric Networking (ICN) is a paradigm shift from host-to-host Internet Protocol (IP)-based communication to content-based communication. With the development and universal application of satellite technology, an important way to expand the function of satellites is setting up inter-satellite networks to make them work together. The Internet and the Global Positioning System are based on the dual structure network and the Uniform Content Label UCL national standard. Through the integration of these two inventions, the integration of time and space is realized, creating an endogenous security environment of both mathematics and physics that is self-consistent in cyberspace, is expected to bring a breakthrough in principle for cracking network security challenges.