Point-based geometric representations such as point clouds and Gaussian Splatting are fundamental for 3D understanding. However, the inherent irregularity and high-dimensional nature of point structures present significant challenges for direct 3D learning approaches, which often struggle with scalability and achieve suboptimal performance due to sparse data distributions. In contrast, 2D learning paradigms benefit from well-established architectures with superior optimization stability and efficiency. To bridge this gap, we propose Maniflat3D, a unified framework that systematically transforms volumetric point-based geometries into structured 2D representations through a two-stage process: a multilayer Ball-Pivoting reconstruction with adaptive density control, followed by Scalable Locally Injective Mapping (SLIM) to produce distortion-minimized, bijective UV parameterizations. Our approach explicitly encodes both geometric and attribute information into the flattened domain, enabling conventional 2D neural networks to effectively learn from complex 3D structures such as Gaussian Splatting. Experiments on the ShapeSplat dataset demonstrate that Maniflat3D achieves comparable performance while reducing parameter count by 90% compared to native 3D baselines, and simultaneously attains 21× compression ratio through neural encoding. These results establish a new paradigm for efficient geometric understanding, demonstrating successful transfer of planar learning advantages to challenging 3D manifold problems through dimensional reduction.

Semantic communication (SC) emerges as a breakthrough paradigm for efficient data transmission in next-generation communication networks. However, SC is still in the infant stage with quite a few limitations, such as insufficient semantic representation capacity, high communication latency, and the susceptibility to channel noise. In this paper, we proposeLiFiSC, a cross-modal fusion based generative semantic communication framework with strong semantic compression capacity and high-fidelity semantic restoration. We then extend it toLiFiSCvv, specifically designed to achieve 3D volumetric video transmission and reconstruction with photorealistic visual quality and pixel-level visual consistency, providing end-to-end live watching experience with acceptable latency. We innovatively incorporate unified vision-language encoding into semantic communication, achieving superior semantic understanding and compression.LiFiSCvvcomprises three key components: (1) Information redundancy reduction through lightweight video analysis and structure-from-motion techniques, decreasing reconstruction cost; (2) Cross-modal fusion learning driven codec mechanisms that enable efficient semantic representation and robust transmission against channel impairments; and (3) Feed-forward vision transformer for rapid volumetric video reconstruction and rendering. Comprehensive evaluation results demonstrate thatLiFiSCvvachieves a live high-fidelity and visually consistent video watching experience, with only seconds of end-to-end latency and around 42× semantic compression, significantly outperforming SOTA methods in general image and volumetric video transmission. The project page is available here: https://inml-tygong.github.io/LiFiSCvv/.

While frequent lawsuits against businesses for claiming excessive damages have negative impacts on the economy, lawsuits may be strategically employed to improve law enforcement and social governance. Chinese consumer citizen suits are an example of such, although their patterns and impacts remain a mystery. This work constructs a comprehensive knowledge graph (KG) from judicial decisions and employs transformer-based heterogeneous graph neural networks (HGNNs) to analyze the behavioral patterns of plaintiffs. By leveraging deep contextual features from the KG, this study uncovers hidden social relationships among plaintiffs, revealing organized litigation behaviors facilitated by shared legal resources, such as lawyers, law offices, and common defendants. To the best of our knowledge, this is the first empirical study to uncover and validate hidden social connections among consumer-plaintiffs in China using a KG and a transformer-based HGNN framework. The findings reveal significant community structures, indicating that plaintiffs may frequently act in organized groups in lawsuit activities. This study advances methodological approaches by integrating HGNNs for link prediction and modularity-based community detection, offering actionable insights into the dynamics of grassroots litigation. By introducing a novel analytical framework and dataset, this work deepens the understanding of consumer lawsuits, underscores the influence of social networks on litigation behavior, and lays a foundation for future research in legal analytics and social network analysis (SNA) within the legal domain.

Large Language Models (LLMs) exhibit remarkable language understanding and problem-solving capabilities but are heavily reliant on vast amounts of high-quality data, which raises significant privacy concerns. Federated Learning (FL) presents a decentralized training paradigm that minimizes raw data sharing but is still vulnerable to privacy attacks that exploit shared model updates. Federated LLMs, especially dialogue models, are particularly prone to query-based attacks, which can lead to the unintentional disclosure of memorized private information. This study performs extensive experiments across multiple model sizes and federated architectures to assess the extent of query-based privacy leakage and evaluate existing protection mechanisms. To enable standardized and reproducible privacy assessments, we propose a multi-stage privacy leakage detection method, integrating structured privacy attribute extraction, controlled injection, realistic prompting, and quantitative evaluation under both generalized and personalized privacy scenarios. Additionally, we introduce FedShieldLLM, a lightweight, adaptable client-side anonymization framework that performs personalized data de-identification prior to federated training, effectively mitigating privacy risks while preserving task utility. Our contributions include: (1) a systematic analysis of query-based privacy leakage in federated LLMs; (2) the design of a reproducible, architecture-agnostic multi-stage detection method; and (3) the development of FedShieldLLM for secure and flexible client participation in privacy-sensitive federated learning.

Federated learning (FL) stands out as a promising solution to address the ever-increasing data scarcity problem of large language model (LLM) training through collecting data from distributed sources. The unique challenges however exist in three aspects, the extreme large communication overhead due to frequent model aggregation, the suboptimal performance due to data heterogeneity, and privacy leakage risk due to model parameter exchange. To address these issues, we propose Federated Knowledge Learning (FKL), a novel token-level knowledge sharing framework tailored for LLM to achieve effective task relevant knowledge aggregation. FKL offers the following advantages: (1) Adaptive Flexibility: Clients and servers can employ models customized for their specific tasks while ensuring seamless collaboration. Each node within the system functions independently and can be flexibly adapted as needed. (2) Communication Efficiency: Instead of huge model or parameter exchange, the unique knowledge sharing mechanism of FKL can significantly reduce the communication overhead while delivering superior performance. (3) Privacy Safeguards: The distributed token-level knowledge-sharing mechanism ensures privacy by deidentifying sensitive information and mitigating potential leakage risks. Experiments on LLMs (125M-7B parameters) validate FKL's versatility, achieving 50% higher accuracy on GLUE benchmarks and a notable 0.7x improvement in privacy task response quality compared to existing FL-based LLM approaches.

While 3D Gaussian Splatting (3DGS) has revolutionized static scene representation, the extension to dynamic scene, i.e., 3DGS video (GSV), faces challenges related to reconstruction quality, rendering speed, and storage requirements. The substantial data volume of current GSV poses significant hurdles for streaming applications, particularly in the realm of AR, VR and MR. To tackle these challenges, we introduce 4DGStream, a novel framework that integrates an efficient GSV compression method, Light4D, and a bitrate adaptation streaming strategy, QoSmooth, to ensure smooth playback while maintaining high visual quality. Light4D employs a binarizationassisted spatiotemporal deformation network to model the deformation of Gaussian primitive attributes over time, while a spatiotemporal-aware masking module prunes trivial Gaussians, further enhancing long-term reconstruction quality. To reduce storage, Light4D uses a binary hash grid to model the entropy of attributes for arithmetic coding, with its binary nature allowing efficient entropy modeling via a Bernoulli distribution. These components enable Light4D to improve the FPS/Storage metric by up to 12.4× over SpacetimeGS and 26.4× over 4DGS on the Neu3D dataset, with performance gains exceeding 3× orders of magnitude compared to other NeRF-based state-of-the-art (SOTA) methods. Here, FPS/Storage reflects the balance between rendering speed and data storage. Despite significant model size reductions, Light4D maintains or surpasses the reconstruction quality of 4DGS. Furthermore, QoSmooth provides effective rate control to enhance playback smoothness, reducing bitrate level switches by 61.6% and increasing time-average utility by 26.2%. All these improvements make 4DGStream highly suited for GSV streaming, improving QoE by 36.7% compared to SOTA methods.

This paper proposes an advanced composite predictive framework leveraging motion pattern decoupling, designed to enhance the prediction accuracy and computational efficiency of three-dimensional relative distance in autonomous underwater docking operations for Unmanned Underwater Vehicles (UUVs). Initially, the framework employs a velocity discontinuity detection algorithm to partition the original three-dimensional trajectory data into kinematic-consistent subtrajectories characterized by uniform motion patterns. Subsequently, integrating Dynamic Time Warping (DTW) with the elbow method, the K-means algorithm is refined to facilitate trajectory pattern clustering and establish distinct pattern category labels. For each motion pattern identified, a customized Gated Recurrent Unit (GRU) predictive model is meticulously trained. During the online prediction phase, real-time kinematic states are extracted through a sliding window mechanism, and the K-Nearest Neighbors (KNN) classifier is adeptly utilized to select the most suitable GRU model for dynamic forecasting. Empirical analyses, grounded in 200 sets of authentic underwater docking experiment data, reveal that this framework markedly surpasses standalone LSTM and GRU models, as well as acoustic-optic sensors, in predictive precision. Furthermore, the single-step prediction latency consistently remains under 17 milliseconds, thus fulfilling the real-time requisites of high-dynamic conditions. This research furnishes theoretical and technical underpinnings for precise UUV docking in intricate underwater milieus.

3D Gaussian Splatting (3DGS) has emerged as a groundbreaking 3D scene representation technique, offering unprecedented visual quality and rendering efficiency. However, the substantial data volume of 3DGS scenes poses significant challenges for streaming applications. Existing research on 3DGS has primarily focused on compression and rendering efficiency, neglecting the specific requirements of streaming transmission. Moreover, the Spherical Harmonics color representation in 3DGS complicates viewport-based transmission partitioning. Achieving hierarchical Gaussian streaming without noticeable quality degradation also remains a significant challenge.To address these challenges, we propose SRBF-Gaussian, a new paradigm that revolutionizes the traditional 3DGS format. Our approach introduces viewport-dependent color encoding based on Spherical Radial Basis Functions (SRBFs) and HSL color space, enabling selective transmission of viewport-relevant color data. This reduces data transmission while maintaining visual quality. We implement adaptive Gaussian pruning and transmission, optimized for current viewports and network conditions. Additionally, we develop coherent multi-level Gaussian representations for smooth transitions between quality levels. Our system incorporates user-behavior-aware streaming strategies to anticipate and pre-fetch relevant data. In cloud VR scenarios, our approach demonstrates substantial improvements, achieving a 5.63% - 14.17% increase in PSNR, a 7.61% - 59.16% reduction in latency, and a 10.45% - 30.12% improvement in overall Quality of Experience (QoE).

3-D Gaussian splatting (3DGS) has emerged as a promising technique for high-quality 3-D scene representation. However, streaming 3DGS scenes poses significant challenges due to large data volumes and complex spatial structures, resulting in nonsmooth scene loading, inferior visual quality, and ineffective streaming adaptation, ultimately impacting user experience adversely. To tackle these challenges and enhance user Quality of Experience (QoE), this article introduces a novel adaptive streaming framework called 3DGStreaming. Our framework comprises three key components: 1) smart Spatial Partitioning for efficient scene division, enabling selective streaming and seamless scene merging; 2) two-step Progressive Scene Generation, involving content-aware downsampling and attribute compression to create multibitrate 3DGS scenes; and 3) Field of View (FoV)-based Bitrate Adaptation using a decision transformer for viewport-based bitrate selection. Extensive experiments demonstrate the superiority of 3DGStreaming over existing state-of-the-art solutions. 3DGStreaming achieves a greater rendering quality with a 5.7%–25.5% increase in PSNR, a 27.8%–69.2% reduction in latency, a 54.7% reduction in training time, and a 17.2%–68.3% improvement in overall QoE.

Recent years have witnessed a growing trend toward employing deep reinforcement learning (Deep-RL) to derive heuristics for combinatorial optimization (CO) problems on graphs. Maximum Coverage Problem (MCP) and its probabilistic variant on social networks, Influence Maximization (IM), have been particularly prominent in this line of research. In this paper, we present a comprehensive benchmark study that thoroughly investigates the effectiveness and efficiency of five recent Deep-RL methods for MCP and IM. These methods were published in top data science venues, namely S2V-DQN, Geometric-QN, GCOMB, RL4IM, and LeNSE. Our findings reveal that, across various scenarios, the Lazy Greedy algorithmconsistently outperforms allDeep-RL methods for MCP. In the case of IM, theoretically sound algorithms like IMM and OPIM demonstrate superior performance compared to Deep-RL methods in most scenarios. Notably, we observe anabnormal phenomenonin IM problem where Deep-RL methods slightly outperform IMM and OPIM when the influence spread nearly does not increase as the budget increases. Furthermore, our experimental results highlight common issues when applying Deep-RL methods to MCP and IM in practical settings. Finally, we discuss potential avenues for improving Deep-RL methods. Our benchmark study sheds light on potential challenges in current deep reinforcement learning research for solving combinatorial optimization problems.

Point cloud video (PCV) offers watching experiences in photorealistic 3D scenes with six-degree-of-freedom (6-DoF), enabling a variety of VR and AR applications. The user's Field of View (FoV) is more fickle with 6-DoF movement than 3-DoF movement in 360-degree video. PCV streaming is extremely bandwidth-intensive. However, current streaming systems require hundreds of Mbps bandwidth, exceeding the bandwidth capabilities of commodity devices. To save bandwidth, FoV-adaptive streaming predicts a user's FoV and only downloads point cloud data falling in the predicted FoV. But it is difficult to accurately predict the user's FoV even 2-3 seconds before playback due to 6-DoF. Misprediction of FoV or network bandwidth dips results in frequent stalls. To avoid rebuffering, existing systems would cause incomplete FoV and degraded experience, deteriorating the user's quality of experience (QoE). In this paper, we describe Fumos, a novel system that preserves interactive experience by avoiding playback stalls while maintaining high perceptual quality and high compression rate. We find a research gap in inter-frame redundant utilization and progressive mechaism. Fumos has three crucial designs, including (1) Neural compression framework with inter-frame coding, namely N-PCC, which achieves both bandwidth efficiency and high fidelity. (2) Progressive refinement streaming framework that enables continuous playback by incrementally upgrading a fetched portion to a higher quality (3) System-level adaptation that employs Lyapunov optimization to jointly optimize the long-term user QoE. Experimental results demonstrate that Fumos significantly outperforms Draco, achieving an average decoding rate acceleration of over 260×. Moreover, the proposed compression framework N-PCC attains remarkable BD-Rate gains, averaging 91.7% and 51.7% against the state-of-the-art point cloud compression methods G-PCC and V-PCC, respectively.

Sara Rosenthal, Ken Barker, Zhicheng Liang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.