arXiv subjects

Tao Tang

Publications and source records attributed to Tao Tang.

At least 37 records · Page 2Linked to original sources

arXiv2026

FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks

Graph Transformers (GTs) are increasingly applied to social network analysis, yet their deployment is often constrained by fairness concerns. This issue is particularly critical in incomplete social networks, where sensitive attributes are frequently missing due to privacy and ethical restrictions. Existing solutions commonly generate these incomplete attributes, which may introduce additional biases and further compromise user privacy. To address this challenge, FairGE (Fair Graph Encoding) is introduced as a fairness-aware framework for GTs in incomplete social networks. Instead of generating sensitive attributes, FairGE encodes fairness directly through spectral graph theory. By leveraging the principal eigenvector to represent structural information and padding incomplete sensitive attributes with zeros to maintain independence, FairGE ensures fairness without data reconstruction. Theoretical analysis demonstrates that the method suppresses the influence of non-principal spectral components, thereby enhancing fairness. Extensive experiments on seven real-world social network datasets confirm that FairGE achieves at least a 16% improvement in both statistical parity and equality of opportunity compared with state-of-the-art baselines. The source code is shown in https://github.com/LuoRenqiang/FairGE.

cs.SI↗

arXiv2026

Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation

The clinical utility of deep learning models for medical image segmentation is severely constrained by their inability to generalize to unseen domains. This failure is often rooted in the models learning spurious correlations between anatomical content and domain-specific imaging styles. To overcome this fundamental challenge, we introduce Causal-SAM-LLM, a novel framework that elevates Large Language Models (LLMs) to the role of causal reasoners. Our framework, built upon a frozen Segment Anything Model (SAM) encoder, incorporates two synergistic innovations. First, Linguistic Adversarial Disentanglement (LAD) employs a Vision-Language Model to generate rich, textual descriptions of confounding image styles. By training the segmentation model's features to be contrastively dissimilar to these style descriptions, it learns a representation robustly purged of non-causal information. Second, Test-Time Causal Intervention (TCI) provides an interactive mechanism where an LLM interprets a clinician's natural language command to modulate the segmentation decoder's features in real-time, enabling targeted error correction. We conduct an extensive empirical evaluation on a composite benchmark from four public datasets (BTCV, CHAOS, AMOS, BraTS), assessing generalization under cross-scanner, cross-modality, and cross-anatomy settings. Causal-SAM-LLM establishes a new state of the art in out-of-distribution (OOD) robustness, improving the average Dice score by up to 6.2 points and reducing the Hausdorff Distance by 15.8 mm over the strongest baseline, all while using less than 9% of the full model's trainable parameters. Our work charts a new course for building robust, efficient, and interactively controllable medical AI systems.

cs.CV↗

arXiv2025

Overcoming Spectral Bias via Cross-Attention

Spectral bias implies an imbalance in training dynamics, whereby high-frequency components may converge substantially more slowly than low-frequency ones. To alleviate this issue, we propose a cross-attention-based architecture that adaptively reweights a scaled multiscale random Fourier feature bank with learnable scaling factors. The learnable scaling adjusts the amplitudes of the multiscale random Fourier features, while the cross-attention residual structure provides an input-dependent mechanism to emphasize the most informative scales. As a result, the proposed design accelerates high-frequency convergence relative to comparable baselines built on the same multiscale bank. Moreover, the attention module supports incremental spectral enrichment: dominant Fourier modes extracted from intermediate approximations via discrete Fourier analysis can be appended to the feature bank and used in subsequent training, without modifying the backbone architecture. We further extend this framework to PDE learning by introducing a linear combination of two sub-networks: one specialized in capturing high-frequency components of the PDE solution and the other in capturing low-frequency components, with a learnable (or optimally chosen) mixing factor to balance the two contributions and improve training efficiency in oscillatory regimes. Numerical experiments on high-frequency and discontinuous regression problems, image reconstruction tasks, as well as representative PDE examples, demonstrate the effectiveness and robustness of the proposed method.

math.NA↗

arXiv2025

OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving

Autonomous driving has seen remarkable advancements, largely driven by extensive real-world data collection. However, acquiring diverse and corner-case data remains costly and inefficient. Generative models have emerged as a promising solution by synthesizing realistic sensor data. However, existing approaches primarily focus on single-modality generation, leading to inefficiencies and misalignment in multimodal sensor data. To address these challenges, we propose OminiGen, which generates aligned multimodal sensor data in a unified framework. Our approach leverages a shared Bird\u2019s Eye View (BEV) space to unify multimodal features and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data. UAE achieves multimodal sensor decoding through volume rendering, enabling accurate and flexible reconstruction. Furthermore, we incorporate a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation. Our comprehensive experiments demonstrate that OminiGen achieves desired performances in unified multimodal sensor data generation with multimodal consistency and flexible sensor adjustments.

cs.CV↗

arXiv2025

CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving

End-to-end planning methods are the de facto standard of the current autonomous driving system, while the robustness of the data-driven approaches suffers due to the notorious long-tail problem (i.e., rare but safety-critical failure cases). In this work, we explore whether recent diffusion-based video generation methods (a.k.a. world models), paired with structured 3D layouts, can enable a fully automated pipeline to self-correct such failure cases. We first introduce an agent to simulate the role of product manager, dubbed PM-Agent, which formulates data requirements to collect data similar to the failure cases. Then, we use a generative model that can simulate both data collection and annotation. However, existing generative models struggle to generate high-fidelity data conditioned on 3D layouts. To address this, we propose DriveSora, which can generate spatiotemporally consistent videos aligned with the 3D annotations requested by PM-Agent. We integrate these components into our self-correcting agentic system, CorrectAD. Importantly, our pipeline is an end-to-end model-agnostic and can be applied to improve any end-to-end planner. Evaluated on both nuScenes and a more challenging in-house dataset across multiple end-to-end planners, CorrectAD corrects 62.5% and 49.8% of failure cases, reducing collision rates by 39% and 27%, respectively.

cs.CV↗

arXiv2025

LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priors

Recent GS-based rendering has made significant progress for LiDAR, surpassing Neural Radiance Fields (NeRF) in both quality and speed. However, these methods exhibit artifacts in extrapolated novel view synthesis due to the incomplete reconstruction from single traversal scans. To address this limitation, we present LiDAR-GS++, a LiDAR Gaussian Splatting reconstruction method enhanced by diffusion priors for real-time and high-fidelity re-simulation on public urban roads. Specifically, we introduce a controllable LiDAR generation model conditioned on coarsely extrapolated rendering to produce extra geometry-consistent scans and employ an effective distillation mechanism for expansive reconstruction. By extending reconstruction to under-fitted regions, our approach ensures global geometric consistency for extrapolative novel views while preserving detailed scene surfaces captured by sensors. Experiments on multiple public datasets demonstrate that LiDAR-GS++ achieves state-of-the-art performance for both interpolated and extrapolated viewpoints, surpassing existing GS and NeRF-based methods.

cs.CV↗

arXiv2025

Selection of Supervised Learning-based Sparse Matrix Reordering Algorithms

Sparse matrix ordering is a vital optimization technique often employed for solving large-scale sparse matrices. Its goal is to minimize the matrix bandwidth by reorganizing its rows and columns, thus enhancing efficiency. Conventional methods for algorithm selection usually depend on brute-force search or empirical knowledge, lacking the ability to adjust to diverse sparse matrix structures.As a result, we have introduced a supervised learning-based model for choosing sparse matrix reordering algorithms. This model grasps the correlation between matrix characteristics and commonly utilized reordering algorithms, facilitating the automated and intelligent selection of the suitable sparse matrix reordering algorithm. Experiments conducted on the Florida sparse matrix dataset reveal that our model can accurately predict the optimal reordering algorithm for various matrices, leading to a 55.37% reduction in solution time compared to solely using the AMD reordering algorithm, with an average speedup ratio of 1.45.

cs.DC↗

arXiv2025

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Real-world clinical decision-making requires integrating heterogeneous data, including medical text, 2D images, 3D volumes, and videos, while existing AI systems fail to unify all these signals, limiting their utility. In this paper, we introduce Hulu-Med, a transparent, generalist medical Vision-Language Model (VLM) designed to unify language-only, 2D/3D vision-language, and video understanding within a single architecture. Hulu-Med is trained on a curated corpus of 16.7 million samples, comprising exclusively public or synthetic data, spanning 12 major anatomical systems and 14 medical imaging modalities. Hulu-Med employs a medical-aware token-reduction strategy that prunes redundant visual tokens, achieving up to a 55% reduction for 3D and video inputs, improving cross-modal efficiency, and enabling training at 7B-32B parameter scales in approximately 4,000-40,000 GPU hours. Across 30 public in-domain and out-of-domain medical benchmarks-covering text reasoning, visual question answering, report generation, multilingual dialogue, video understanding, and rare disease diagnosis-Hulu-Med surpasses existing open-source models on 27 of 30 benchmarks and outperforms proprietary systems such as GPT-4o on 16 benchmarks. Despite being a VLM, Hulu-Med outperforms GPT-4o and matches GPT-o1 on the text-only HealthBench. For the first time in the community, we provide a fully transparent, reproducible and cost-effective pipeline for holistic medical vision-language understanding by releasing our end-to-end data curation, training procedures, and model parameters. Code and models are available at https://github.com/ZJUI-AI4H/Hulu-Med.

cs.CV↗

arXiv2025

H3DE-Net: Efficient and Accurate 3D Landmark Detection in Medical Imaging

3D landmark detection is a critical task in medical image analysis, and accurately detecting anatomical landmarks is essential for subsequent medical imaging tasks. However, mainstream deep learning methods in this field struggle to simultaneously capture fine-grained local features and model global spatial relationships, while maintaining a balance between accuracy and computational efficiency. Local feature extraction requires capturing fine-grained anatomical details, while global modeling requires understanding the spatial relationships within complex anatomical structures. The high-dimensional nature of 3D volume further exacerbates these challenges, as landmarks are sparsely distributed, leading to significant computational costs. Therefore, achieving efficient and precise 3D landmark detection remains a pressing challenge in medical image analysis. In this work, We propose a \textbf{H}ybrid \textbf{3}D \textbf{DE}tection \textbf{Net}(H3DE-Net), a novel framework that combines CNNs for local feature extraction with a lightweight attention mechanism designed to efficiently capture global dependencies in 3D volumetric data. This mechanism employs a hierarchical routing strategy to reduce computational cost while maintaining global context modeling. To our knowledge, H3DE-Net is the first 3D landmark detection model that integrates such a lightweight attention mechanism with CNNs. Additionally, integrating multi-scale feature fusion further enhances detection accuracy and robustness. Experimental results on a public CT dataset demonstrate that H3DE-Net achieves state-of-the-art(SOTA) performance, significantly improving accuracy and robustness, particularly in scenarios with missing landmarks or complex anatomical variations. We aready open-source our project, including code, data and model weights.

cs.CV↗

arXiv2025

A linear unconditionally structure-preserving L1 scheme for the time-fractional Allen-Cahn equation

As a variational phase-field model, the time-fractional Allen-Cahn (TFAC) equation enjoys the maximum bound principle (MBP) and a variational energy dissipation law. In this work, we develop and analyze linear, structure-preserving time-stepping schemes for TFAC, including first-order and $\min\{1+α, 2-α\}$-order L1 discretizations, together with fast implementations based on the sum-of-exponentials (SOE) technique. A central feature of the proposed linear schemes is their unconditional preservation of both the discrete MBP and the variational energy dissipation law on general temporal meshes, including graded meshes commonly used for these problems. Leveraging the MBP of the numerical solutions, we establish sharp error estimates by employing the time-fractional Gronwall inequality. Finally, numerical experiments validate the theoretical results and demonstrate the effectiveness of the proposed schemes with an adaptive time-stepping strategy.

math.NA↗

arXiv2025

LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting

We present LiDAR-GS, a Gaussian Splatting (GS) method for real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes. Recent GS methods proposed for cameras have achieved significant advancements in real-time rendering beyond Neural Radiance Fields (NeRF). However, applying GS representation to LiDAR, an active 3D sensor type, poses several challenges that must be addressed to preserve high accuracy and unique characteristics. Specifically, LiDAR-GS designs a differentiable laser beam splatting, using range-view representation for precise surface splatting by projecting lasers onto micro cross-sections, effectively eliminating artifacts associated with local affine approximations. Furthermore, LiDAR-GS leverages Neural Gaussian Representation, which further integrate view-dependent clues, to represent key LiDAR properties that are influenced by the incident direction and external factors. Combining these practices with some essential adaptations, e.g., dynamic instances decomposition, LiDAR-GS succeeds in simultaneously re-simulating depth, intensity, and ray-drop channels, achieving state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets when compared with the methods using explicit mesh or implicit NeRF. Our source code is publicly available at https://www.github.com/cqf7419/LiDAR-GS.

cs.CV↗

arXiv2025

Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods, Datasets, and Future Directions

Traffic accident prediction and detection are critical for enhancing road safety, and vision-based traffic accident anticipation (Vision-TAA) has emerged as a promising approach in the era of deep learning. This paper reviews 147 recent studies, focusing on the application of supervised, unsupervised, and hybrid deep learning models for accident prediction, alongside the use of real-world and synthetic datasets. Current methodologies are categorized into four key approaches: image and video feature-based prediction, spatio-temporal feature-based prediction, scene understanding, and multi modal data fusion. While these methods demonstrate significant potential, challenges such as data scarcity, limited generalization to complex scenarios, and real-time performance constraints remain prevalent. This review highlights opportunities for future research, including the integration of multi modal data fusion, self-supervised learning, and Transformer-based architectures to enhance prediction accuracy and scalability. By synthesizing existing advancements and identifying critical gaps, this paper provides a foundational reference for developing robust and adaptive Vision-TAA systems, contributing to road safety and traffic management.

cs.CV↗

arXiv2025

RAPNet: A Receptive-Field Adaptive Convolutional Neural Network for Pansharpening

Pansharpening refers to the process of integrating a high resolution panchromatic (PAN) image with a lower resolution multispectral (MS) image to generate a fused product, which is pivotal in remote sensing. Despite the effectiveness of CNNs in addressing this challenge, they are inherently constrained by the uniform application of convolutional kernels across all spatial positions, overlooking local content variations. To overcome this issue, we introduce RAPNet, a new architecture that leverages content-adaptive convolution. At its core, RAPNet employs the Receptive-field Adaptive Pansharpening Convolution (RAPConv), designed to produce spatially adaptive kernels responsive to local feature context, thereby enhancing the precision of spatial detail extraction. Additionally, the network integrates the Pansharpening Dynamic Feature Fusion (PAN-DFF) module, which incorporates an attention mechanism to achieve an optimal balance between spatial detail enhancement and spectral fidelity. Comprehensive evaluations on publicly available datasets confirm that RAPNet delivers superior performance compared to existing approaches, as demonstrated by both quantitative metrics and qualitative assessments. Ablation analyses further substantiate the effectiveness of the proposed adaptive components.

cs.CV↗

arXiv2025

Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning

This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training, which limits their practicality and scalability. To overcome these challenges, we propose a new setting to train a unified cross-domain model through a single process, eliminating the need for domain-specific components and multi-stage training. We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain model. While PiC generalizes across multiple pose-based tasks and datasets, it encounters difficulties with modality diversity, prompting strategy, and contextual dependency handling. We thus propose Human-in-Context (HiC), an extension of PiC that broadens generalization across modalities, tasks, and datasets. HiC combines pose and mesh representations within a unified framework, expands task coverage, and incorporates larger-scale datasets. Additionally, HiC introduces a max-min similarity prompt sampling strategy to enhance generalization across diverse domains and a network architecture with dual-branch context injection for improved handling of contextual dependencies. Extensive experimental results show that HiC performs better than PiC in terms of generalization, data scale, and performance across a wide range of domains. These results demonstrate the potential of HiC for building a unified cross-domain 3D human motion model with improved flexibility and scalability. The source codes and models are available at https://github.com/BradleyWang0416/Human-in-Context.

cs.CV↗

arXiv2025

MIND: A Noise-Adaptive Denoising Framework for Medical Images Integrating Multi-Scale Transformer

The core role of medical images in disease diagnosis makes their quality directly affect the accuracy of clinical judgment. However, due to factors such as low-dose scanning, equipment limitations and imaging artifacts, medical images are often accompanied by non-uniform noise interference, which seriously affects structure recognition and lesion detection. This paper proposes a medical image adaptive denoising model (MI-ND) that integrates multi-scale convolutional and Transformer architecture, introduces a noise level estimator (NLE) and a noise adaptive attention module (NAAB), and realizes channel-spatial attention regulation and cross-modal feature fusion driven by noise perception. Systematic testing is carried out on multimodal public datasets. Experiments show that this method significantly outperforms the comparative methods in image quality indicators such as PSNR, SSIM, and LPIPS, and improves the F1 score and ROC-AUC in downstream diagnostic tasks, showing strong prac-tical value and promotional potential. The model has outstanding benefits in structural recovery, diagnostic sensitivity, and cross-modal robustness, and provides an effective solution for medical image enhancement and AI-assisted diagnosis and treatment.

eess.IV↗

arXiv2025

Unconditional energy dissipation of Strang splitting for the matrix-valued Allen-Cahn equation

The energy dissipation property of the Strang splitting method was first demonstrated for the matrix-valued Allen-Cahn (MAC) equation under restrictive time-step constraints [J. Comput. Phys. 454, 110985, 2022]. In this work, we eliminate this limitation through a refined stability analysis framework, rigorously proving that the Strang splitting method preserves the energy dissipation law unconditionally for arbitrary time steps. The refined proof hinges on a precise estimation of the double-well potential term in the modified energy functional. Leveraging this unconditional energy dissipation property, we rigorously establish that the Strang splitting method achieves global-in-time $H^1$-stability, preserves determinant boundedness, and maintains second-order temporal convergence for the matrix-valued Allen-Cahn equation. To validate these theoretical findings, we conduct numerical experiments confirming the method's energy stability and determinant bound preservation for the MAC equation.

math.NA↗

arXiv2025

Efficient Bayesian Inference for Discretely Observed Continuous Time Markov Chains

Inference for continuous-time Markov chains (CTMCs) becomes challenging when the process is only observed at discrete time points. The exact likelihood is intractable, and existing methods often struggle even in medium-dimensional state-spaces. We propose a scalable Bayesian framework for CTMC inference based on a pseudo-likelihood that bypasses the need for the full intractable likelihood. Our approach jointly estimates the probability transition matrix and a biorthogonal spectral decomposition of the generator, enabling an efficient Gibbs sampling procedure that obeys embeddability. Existing methods typically integrate out the unobserved transitions, which becomes computationally burdensome as the number of data or dimensions increase. The computational cost of our method is near-invariant in the number of data and scales well to medium-high dimensions. We justify our pseudo-likelihood approach by establishing theoretical guarantees, including a Bernstein-von Mises theorem for the probability transition matrix and posterior consistency for the spectral parameters of the generator. Through simulation and applications, we showcase the flexibility and robustness of our approach, offering a tractable and scalable approach to Bayesian inference for CTMCs.

stat.ME↗

arXiv2025

Structured First-Layer Initialization Pre-Training Techniques to Accelerate Training Process Based on $\varepsilon$-Rank

Training deep neural networks for scientific computing remains computationally expensive due to the slow formation of diverse feature representations in early training stages. Recent studies identify a staircase phenomenon in training dynamics, where loss decreases are closely correlated with increases in $\varepsilon$-rank, reflecting the effective number of linearly independent neuron functions. Motivated by this observation, this work proposes a structured first-layer initialization (SFLI) pre-training method to enhance the diversity of neural features at initialization by constructing $\varepsilon$-linearly independent neurons in the input layer. We present systematic initialization schemes compatible with various activation functions and integrate the strategy into multiple neural architectures, including modified multi-layer perceptrons and physics-informed residual adaptive networks. Extensive numerical experiments on function approximation and PDE benchmarks, demonstrate that SFLI significantly improves the initial $\varepsilon$-rank, accelerates convergence, mitigates spectral bias, and enhances prediction accuracy. With the help of SILP, we only need to add one line of code to conventional existing algorithms.

math.NA↗