arXiv subjects

Rui Tang

Publications and source records attributed to Rui Tang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Towards Physically Executable 3D Gaussian for Embodied Navigation

3D Gaussian Splatting (3DGS), a 3D representation method with photorealistic real-time rendering capabilities, is regarded as an effective tool for narrowing the sim-to-real gap. However, it lacks fine-grained semantics and physical executability for Visual-Language Navigation (VLN). To address this, we propose SAGE-3D (Semantically and Physically Aligned Gaussian Environments for 3D Navigation), a new paradigm that upgrades 3DGS into an executable, semantically and physically aligned environment. It comprises two components: (1) Object-Centric Semantic Grounding, which adds object-level fine-grained annotations to 3DGS; and (2) Physics-Aware Execution Jointing, which embeds collision objects into 3DGS and constructs rich physical interfaces. We release InteriorGS, containing 1K object-annotated 3DGS indoor scene data, and introduce SAGE-Bench, the first 3DGS-based VLN benchmark with 2M VLN data. Experiments show that 3DGS scene data is more difficult to converge, while exhibiting strong generalizability, improving baseline performance by 31% on the VLN-CE Unseen task. Our data and code are available at: https://sage-3d.github.io.

cs.CV↗

arXiv2025

Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning

We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, learning, or deployment) rarely sustain improvement or generalize beyond narrow settings. We introduce Arcadia, a closed-loop framework that operationalizes embodied lifelong learning by tightly coupling four stages: (1) Self-evolving exploration and grounding for autonomous data acquisition in physical environments, (2) Generative scene reconstruction and augmentation for realistic and extensible scene creation, (3) a Shared embodied representation architecture that unifies navigation and manipulation within a single multimodal backbone, and (4) Sim-from-real evaluation and evolution that closes the feedback loop through simulation-based adaptation. This coupling is non-decomposable: removing any stage breaks the improvement loop and reverts to one-shot training. Arcadia delivers consistent gains on navigation and manipulation benchmarks and transfers robustly to physical robots, indicating that a tightly coupled lifecycle: continuous real-world data acquisition, generative simulation update, and shared-representation learning, supports lifelong improvement and end-to-end generalization. We release standardized interfaces enabling reproducible evaluation and cross-model comparison in reusable environments, positioning Arcadia as a scalable foundation for general-purpose embodied agents.

cs.RO↗

arXiv2025

Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning

RL (reinforcement learning) methods (e.g., GRPO) for MLLM (Multimodal LLM) perception ability has attracted wide research interest owing to its remarkable generalization ability. Nevertheless, existing reinforcement learning methods still face the problem of low data quality, where data samples cannot elicit diverse responses from MLLMs, thus restricting the exploration scope for MLLM reinforcement learning. Some methods attempt to mitigate this problem by imposing constraints on entropy, but none address it at its root. Therefore, to tackle this problem, this work proposes Syn-GRPO (Synthesis-GRPO), which employs an online data generator to synthesize high-quality training data with diverse responses in GRPO training. Specifically, Syn-GRPO consists of two components: (1) data server; (2) GRPO workflow. The data server synthesizes new samples from existing ones using an image generation model, featuring a decoupled and asynchronous scheme to achieve high generation efficiency. The GRPO workflow provides the data server with the new image descriptions, and it leverages a diversity reward to supervise the MLLM to predict image descriptions for synthesizing samples with diverse responses. Experiment results across three visual perception tasks demonstrate that Syn-GRPO improves the data quality by a large margin, achieving significant superior performance to existing MLLM perception methods, and Syn-GRPO presents promising potential for scaling long-term self-evolving RL. Our code is available at https://github.com/hqhQAQ/Syn-GRPO.

cs.CV↗

arXiv2025

Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning

Value decomposition is a central approach in multi-agent reinforcement learning (MARL), enabling centralized training with decentralized execution by factorizing the global value function into local values. To ensure individual-global-max (IGM) consistency, existing methods either enforce monotonicity constraints, which limit expressive power, or adopt softer surrogates at the cost of algorithmic complexity. In this work, we present a dynamical systems analysis of non-monotonic value decomposition, modeling learning dynamics as continuous-time gradient flow. We prove that, under approximately greedy exploration, all zero-loss equilibria violating IGM consistency are unstable saddle points, while only IGM-consistent solutions are stable attractors of the learning dynamics. Extensive experiments on both synthetic matrix games and challenging MARL benchmarks demonstrate that unconstrained, non-monotonic factorization reliably recovers IGM-optimal solutions and consistently outperforms monotonic baselines. Additionally, we investigate the influence of temporal-difference targets and exploration strategies, providing actionable insights for the design of future value-based MARL algorithms.

cs.LG↗

arXiv2025

SpatialLM: Training Large Language Models for Structured Indoor Modeling

SpatialLM is a large language model designed to process 3D point cloud data and generate structured 3D scene understanding outputs. These outputs include architectural elements like walls, doors, windows, and oriented object boxes with their semantic categories. Unlike previous methods which exploit task-specific network designs, our model adheres to the standard multimodal LLM architecture and is fine-tuned directly from open-source LLMs. To train SpatialLM, we collect a large-scale, high-quality synthetic dataset consisting of the point clouds of 12,328 indoor scenes (54,778 rooms) with ground-truth 3D annotations, and conduct a careful study on various modeling and training decisions. On public benchmarks, our model gives state-of-the-art performance in layout estimation and competitive results in 3D object detection. With that, we show a feasible path for enhancing the spatial understanding capabilities of modern LLMs for applications in augmented reality, embodied robotics, and more.

cs.CV↗

arXiv2025

X2Video: Adapting Diffusion Models for Multimodal Controllable Neural Video Rendering

We present X2Video, the first diffusion model for rendering photorealistic videos guided by intrinsic channels including albedo, normal, roughness, metallicity, and irradiance, while supporting intuitive multi-modal controls with reference images and text prompts for both global and local regions. The intrinsic guidance allows accurate manipulation of color, material, geometry, and lighting, while reference images and text prompts provide intuitive adjustments in the absence of intrinsic information. To enable these functionalities, we extend the intrinsic-guided image generation model XRGB to video generation by employing a novel and efficient Hybrid Self-Attention, which ensures temporal consistency across video frames and also enhances fidelity to reference images. We further develop a Masked Cross-Attention to disentangle global and local text prompts, applying them effectively onto respective local and global regions. For generating long videos, our novel Recursive Sampling method incorporates progressive frame sampling, combining keyframe prediction and frame interpolation to maintain long-range temporal consistency while preventing error accumulation. To support the training of X2Video, we assembled a video dataset named InteriorVideo, featuring 1,154 rooms from 295 interior scenes, complete with reliable ground-truth intrinsic channel sequences and smooth camera trajectories. Both qualitative and quantitative evaluations demonstrate that X2Video can produce long, temporally consistent, and photorealistic videos guided by intrinsic conditions. Additionally, X2Video effectively accommodates multi-modal controls with reference images, global and local text prompts, and simultaneously supports editing on color, material, geometry, and lighting through parametric tuning. Project page: https://luckyhzt.github.io/x2video

cs.GR↗

arXiv2025

Noise Reduction Method for Radio Astronomy Single Station Observation Based on Wavelet Transform and Mathematical Morphology

The 21 cm radiation of neutral hydrogen provides crucial information for studying the early universe and its evolution. To advance this research, countries have made significant investments in constructing large low-frequency radio telescope arrays, such as the Low Frequency Array (LOFAR) and the Square Kilometre Array Phase 1 Low Frequency (SKA1-low). These instruments are pivotal for radio astronomy research. However, challenges such as ionospheric plasma interference, ambient radio noise, and instrument-related effects have become increasingly prominent, posing major obstacles in cosmology research. To address these issues, this paper proposes an efficient signal processing method that combines wavelet transform and mathematical morphology. The method involves the following steps: Background Subtraction: Background interference in radio observation signals is eliminated. Wavelet Transform: The signal, after removing background noise, undergoes a two-dimensional discrete wavelet transform. Threshold processing is then applied to the wavelet coefficients to effectively remove interference components. Wavelet Inversion: The processed signal is reconstructed using wavelet inversion. Mathematical Morphology: The reconstructed signal is further optimized using mathematical morphology to refine the results. Experimental verification was conducted using solar observation data from the Xinjiang Observatory and the Yunnan Observatory. The results demonstrate that this method successfully removes interference signals while preserving useful signals, thus improving the accuracy of radio astronomy observations and reducing the impact of radio frequency interference (RFI).

astro-ph.IM↗

arXiv2025

Knowledge-aware Diffusion-Enhanced Multimedia Recommendation

Multimedia recommendations aim to use rich multimedia content to enhance historical user-item interaction information, which can not only indicate the content relatedness among items but also reveal finer-grained preferences of users. In this paper, we propose a Knowledge-aware Diffusion-Enhanced architecture using contrastive learning paradigms (KDiffE) for multimedia recommendations. Specifically, we first utilize original user-item graphs to build an attention-aware matrix into graph neural networks, which can learn the importance between users and items for main view construction. The attention-aware matrix is constructed by adopting a random walk with a restart strategy, which can preserve the importance between users and items to generate aggregation of attention-aware node features. Then, we propose a guided diffusion model to generate strongly task-relevant knowledge graphs with less noise for constructing a knowledge-aware contrastive view, which utilizes user embeddings with an edge connected to an item to guide the generation of strongly task-relevant knowledge graphs for enhancing the item's semantic information. We perform comprehensive experiments on three multimedia datasets that reveal the effectiveness of our KDiffE and its components on various state-of-the-art methods. Our source codes are available https://github.com/1453216158/KDiffE.

cs.MM↗

arXiv2025

Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection

Surgical phase recognition plays a critical role in developing intelligent assistance systems for minimally invasive procedures such as Endoscopic Submucosal Dissection (ESD). However, the high visual similarity across different phases and the lack of structural cues in RGB images pose significant challenges. Depth information offers valuable geometric cues that can complement appearance features by providing insights into spatial relationships and anatomical structures. In this paper, we pioneer the use of depth information for surgical phase recognition and propose Geo-RepNet, a geometry-aware convolutional framework that integrates RGB image and depth information to enhance recognition performance in complex surgical scenes. Built upon a re-parameterizable RepVGG backbone, Geo-RepNet incorporates the Depth-Guided Geometric Prior Generation (DGPG) module that extracts geometry priors from raw depth maps, and the Geometry-Enhanced Multi-scale Attention (GEMA) to inject spatial guidance through geometry-aware cross-attention and efficient multi-scale aggregation. To evaluate the effectiveness of our approach, we construct a nine-phase ESD dataset with dense frame-level annotations from real-world ESD videos. Extensive experiments on the proposed dataset demonstrate that Geo-RepNet achieves state-of-the-art performance while maintaining robustness and high computational efficiency under complex and low-texture surgical environments.

cs.CV↗

arXiv2025

EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery

Endoscopic surgery is the gold standard for robotic-assisted minimally invasive surgery, offering significant advantages in early disease detection and precise interventions. However, the complexity of surgical scenes, characterized by high variability in different surgical activity scenarios and confused image features between targets and the background, presents challenges for surgical environment understanding. Traditional deep learning models often struggle with cross-activity interference, leading to suboptimal performance in each downstream task. To address this limitation, we explore multi-task learning, which utilizes the interrelated features between tasks to enhance overall task performance. In this paper, we propose EndoARSS, a novel multi-task learning framework specifically designed for endoscopy surgery activity recognition and semantic segmentation. Built upon the DINOv2 foundation model, our approach integrates Low-Rank Adaptation to facilitate efficient fine-tuning while incorporating Task Efficient Shared Low-Rank Adapters to mitigate gradient conflicts across diverse tasks. Additionally, we introduce the Spatially-Aware Multi-Scale Attention that enhances feature representation discrimination by enabling cross-spatial learning of global information. In order to evaluate the effectiveness of our framework, we present three novel datasets, MTLESD, MTLEndovis and MTLEndovis-Gen, tailored for endoscopic surgery scenarios with detailed annotations for both activity recognition and semantic segmentation tasks. Extensive experiments demonstrate that EndoARSS achieves remarkable performance across multiple benchmarks, significantly improving both accuracy and robustness in comparison to existing models. These results underscore the potential of EndoARSS to advance AI-driven endoscopic surgical systems, offering valuable insights for enhancing surgical safety and efficiency.

cs.CV↗

arXiv2025

Network Alignment

Complex networks are frequently employed to model physical or virtual complex systems. When certain entities exist across multiple systems simultaneously, unveiling their corresponding relationships across the networks becomes crucial. This problem, known as network alignment, holds significant importance. It enhances our understanding of complex system structures and behaviours, facilitates the validation and extension of theoretical physics research about studying complex systems, and fosters diverse practical applications across various fields. However, due to variations in the structure, characteristics, and properties of complex networks across different fields, the study of network alignment is often isolated within each domain, with even the terminologies and concepts lacking uniformity. This review comprehensively summarizes the latest advancements in network alignment research, focusing on analyzing network alignment characteristics and progress in various domains such as social network analysis, bioinformatics, computational linguistics and privacy protection. It provides a detailed analysis of various methods' implementation principles, processes, and performance differences, including structure consistency-based methods, network embedding-based methods, and graph neural network-based (GNN-based) methods. Additionally, the methods for network alignment under different conditions, such as in attributed networks, heterogeneous networks, directed networks, and dynamic networks, are presented. Furthermore, the challenges and the open issues for future studies are also discussed.

physics.soc-ph↗

arXiv2025

CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity of anomalies, existing methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner. Previous studies have shown that existing unsupervised VAD models are incapable of label-independent data offsets (e.g., scene changes) in real-world scenarios and may fail to respond to light anomalies due to the overgeneralization of deep neural networks. Inspired by causality learning, we argue that there exist causal factors that can adequately generalize the prototypical patterns of regular events and present significant deviations when anomalous instances occur. In this regard, we propose Causal Representation Consistency Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning. Specifically, building on the structural causal models, we propose scene-debiasing learning and causality-inspired normality learning to strip away entangled scene bias in deep representations and learn causal video normality, respectively. Extensive experiments on benchmarks validate the superiority of our method over conventional deep representation learning. Moreover, ablation studies and extension validation show that the CRCL can cope with label-independent biases in multi-scene settings and maintain stable performance with only limited training data available.

cs.CV↗

arXiv2025

Scalable intensity-based photonic matrix-vector multiplication processor using single-wavelength time-division-multiplexed signals

Photonic integrated circuits provide a compact platform for ultrafast and energy-efficient matrix-vector multiplications (MVMs) in the optical domain. Recently, schemes based on time-division multiplexing (TDM) have been proposed as scalable approaches for realizing large-scale photonic MVM processors. However, existing demonstrations rely on coherent detection or multiple wavelengths, both of which complicate their operations. In this work, we demonstrate a scalable TDM-based photonic MVM processor that uses only single-wavelength intensity-modulated optical signals, thereby avoiding coherent detection and enabling simplified operations. A 32-channel processor is fabricated on a Si-on-insulator (SOI) platform and used to experimentally perform convolution operations in a convolutional neural network (CNN) for handwritten digit recognition, achieving a classification accuracy of 93.47% for 1500 images.

physics.optics↗

arXiv2024

ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speech

The proliferation of hate speech (HS) on social media poses a serious threat to societal security. Automatic counter narrative (CN) generation, as an active strategy for HS intervention, has garnered increasing attention in recent years. Existing methods for automatically generating CNs mainly rely on re-training or fine-tuning pre-trained language models (PLMs) on human-curated CN corpora. Unfortunately, the annotation speed of CN corpora cannot keep up with the growth of HS targets, while generating specific and effective CNs for unseen targets remains a significant challenge for the model. To tackle this issue, we propose Retrieval-Augmented Zero-shot Generation (ReZG) to generate CNs with high-specificity for unseen targets. Specifically, we propose a multi-dimensional hierarchical retrieval method that integrates stance, semantics, and fitness, extending the retrieval metric from single dimension to multiple dimensions suitable for the knowledge that refutes HS. Then, we implement an energy-based constrained decoding mechanism that enables PLMs to use differentiable knowledge preservation, countering, and fluency constraint functions instead of in-target CNs as control signals for generation, thereby achieving zero-shot CN generation. With the above techniques, ReZG can integrate external knowledge flexibly and improve the specificity of CNs. Experimental results show that ReZG exhibits stronger generalization capabilities and outperforms strong baselines with significant improvements of 2.0%+ in the relevance and 4.5%+ in the countering success rate metrics.

cs.CL↗

arXiv2024

Waveguide-multiplexed photonic matrix-vector multiplication processor using multiport photodetectors

The slowing down of Moore's law has driven the development of application-specific processors for deep learning. Analog photonic processors offer a promising solution for accelerating matrix-vector multiplications (MVMs) in deep learning by leveraging parallel computations in the optical domain. Intensity-based photonic MVM processors, which do not utilize the phase information of light, are appealing due to their simplified operations. However, existing intensity-based schemes for such processors often employ wavelength multiplexing or mode multiplexing, both of which have limited scalability due to high insertion loss or wavelength crosstalk. In this work, we present a scalable intensity-based photonic MVM processor based on the concept of waveguide multiplexing. This scheme employs multiport photodetectors (PDs) to sum the intensities of multiple optical signals, eliminating the need for multiple wavelengths or modes. A 16-port Ge PD with a 3 dB bandwidth of 11.8 GHz at a bias voltage of -3 V is demonstrated, and it can be further scaled up to handle 250 ports while maintaining a 6.1 GHz operation bandwidth. A 4 $\times$ 4 circuit fabricated on a Si-on-insulator (SOI) platform is used to perform MVMs in a 3-layer neural network designed for classifying Iris flowers, achieving a classification accuracy of 93.3%. Furthermore, the performance of large-scale circuits in a convolutional neural network (CNN) for Fashion-MNIST is simulated, resulting in a classification accuracy of 90.53%. This work provides a simplified and scalable approach to photonic MVM, laying a foundation for large-scale and multi-dimensional photonic matrix-matrix multiplication in optical neural networks.

physics.optics↗

arXiv2024

Optimizing Drug Delivery in Smart Pharmacies: A Novel Framework of Multi-Stage Grasping Network Combined with Adaptive Robotics Mechanism

Robots-based smart pharmacies are essential for modern healthcare systems, enabling efficient drug delivery. However, a critical challenge exists in the robotic handling of drugs with varying shapes and overlapping positions, which previous studies have not adequately addressed. To enhance the robotic arm's ability to grasp chaotic, overlapping, and variously shaped drugs, this paper proposed a novel framework combining a multi-stage grasping network with an adaptive robotics mechanism. The framework first preprocessed images using an improved Super-Resolution Convolutional Neural Network (SRCNN) algorithm, and then employed the proposed YOLOv5+E-A-SPPFCSPC+BIFPNC (YOLO-EASB) instance segmentation algorithm for precise drug segmentation. The most suitable drugs for grasping can be determined by assessing the completeness of the segmentation masks. Then, these segmented drugs were processed by our improved Adaptive Feature Fusion and Grasp-Aware Network (IAFFGA-Net) with the optimized loss function, which ensures accurate picking actions even in complex environments. To control the robot grasping, a time-optimal robotic arm trajectory planning algorithm that combines an improved ant colony algorithm with 3-5-3 interpolation was developed, further improving efficiency while ensuring smooth trajectories. Finally, this system was implemented and validated within an adaptive collaborative robot setup, which dynamically adjusts to different production environments and task requirements. Experimental results demonstrate the superiority of our multi-stage grasping network in optimizing smart pharmacy operations, while also showcasing its remarkable adaptability and effectiveness in practical applications.

cs.RO↗

arXiv2024

Symmetric silicon microring resonator optical crossbar array for accelerated inference and training in deep learning

Photonic integrated circuits are emerging as a promising platform for accelerating matrix multiplications in deep learning, leveraging the inherent parallel nature of light. Although various schemes have been proposed and demonstrated to realize such photonic matrix accelerators, the in-situ training of artificial neural networks using photonic accelerators remains challenging due to the difficulty of direct on-chip backpropagation on a photonic chip. In this work, we propose a silicon microring resonator (MRR) optical crossbar array with a symmetric structure that allows for simple on-chip backpropagation, potentially enabling the acceleration of both the inference and training phases of deep learning. We demonstrate a $4 \times 4$ circuit on a Si-on-insulator (SOI) platform and use it to perform inference tasks of a simple neural network for classifying Iris flowers, achieving a classification accuracy of 93.3%. Subsequently, we train the neural network using simulated on-chip backpropagation and achieve an accuracy of 91.1% in the same inference task after training. Furthermore, we simulate a convolutional neural network (CNN) for handwritten digit recognition, using a $9 \times 9$ MRR crossbar array to perform the convolution operations. This work contributes to the realization of compact and energy-efficient photonic accelerators for deep learning.

cs.ET↗

arXiv2024

Lower-depth programmable linear optical processors

Programmable linear optical processors (LOPs) can have widespread applications in computing and information processing due to their capabilities to implement reconfigurable on-chip linear transformations. A conventional LOP that uses a mesh of Mach-Zehnder interferometers (MZIs) requires $2N+3$ stages of phase shifters for $N \times N$ matrices. However, it is beneficial to reduce the number of phase shifter stages to realize a more compact and lower-loss LOP, especially when long and lossy electro-optic phase shifters are used. In this work, we propose a novel structure for LOPs that can implement arbitrary matrices as long as they can be realized by previous MZI-based schemes. Through numerical analysis, we further show that the number of phase shifter stages in the proposed structure can be reduced to $N+2$ and $N+3$ for a large number of random dense matrices and sparse matrices, respectively. This work contributes to the realization of compact, low-loss, and energy-efficient programmable LOPs.

physics.optics↗