arXiv subjects

Yun Zhang

Publications and source records attributed to Yun Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Tidal disruption and evaporation of rubble-pile and monolithic bodies as a source of flaring activity in Sgr A^\star$

Sgr A*, the supermassive black hole at the center of the Milky Way, exhibits frequent short-duration flares with luminosity greater than 1e34 erg/s across multiple wavelengths. The origin of the flares is still unknown. We revisited the role of small planetary bodies, originally from the stellar disk, and their tidally disrupted fragments as a source of flaring activity in Sgr A*. We refined previous models by incorporating material strength constraints on the tidal disruption limit and by evaluating the evaporation dynamics of the resulting fragments. We analyzed the tidal fragmentation and gas-induced fragmentation of small planetary bodies with rubble-pile and monolithic structures. Using constraints from recent space missions (e.g., NASA OSIRIS-REx and JAXA Hayabusa2), we estimated the survivability of fragments under aerodynamic heating and computed their expected luminosity from ablation, modeled as fireball flares analogous to meteor events. We find that planetary fragments can approach as close as 8 gravitational radii, consistent with observed flare locations. The fireball model yields luminosities from 1e34 to 1e36 erg/s for fragments whose parent bodies are a few kilometers in size. The derived flare frequency vs. luminosity distribution follows a power law with index 1.83, in agreement with observed values (1.65 - 1.9), while the flare duration scales as L^(-1/3), consistent with observations. We consider the young stars around Sgr A* as the planetary reservoir. Given a small-body population analogous in mass to the primordial Kuiper belt and the common existence of close-in super-Earths and long-period Neptunes, we show that this planetary reservoir can supply the observed flares.

astro-ph.HE↗

arXiv2025

MDG: Masked Denoising Generation for Multi-Agent Behavior Modeling in Traffic Environments

Modeling realistic and interactive multi-agent behavior is critical to autonomous driving and traffic simulation. However, existing diffusion and autoregressive approaches are limited by iterative sampling, sequential decoding, or task-specific designs, which hinder efficiency and reuse. We propose Masked Denoising Generation (MDG), a unified generative framework that reformulates multi-agent behavior modeling as the reconstruction of independently noised spatiotemporal tensors. Instead of relying on diffusion time steps or discrete tokenization, MDG applies continuous, per-agent and per-timestep noise masks that enable localized denoising and controllable trajectory generation in a single or few forward passes. This mask-driven formulation generalizes across open-loop prediction, closed-loop simulation, motion planning, and conditional generation within one model. Trained on large-scale real-world driving datasets, MDG achieves competitive closed-loop performance on the Waymo Sim Agents and nuPlan Planning benchmarks, while providing efficient, consistent, and controllable open-loop multi-agent trajectory generation. These results position MDG as a simple yet versatile paradigm for multi-agent behavior modeling.

cs.RO↗

arXiv2025

Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering

Contrastive learning has emerged as a cornerstone of unsupervised representation learning across vision, language, and graph domains, with InfoNCE as its dominant objective. Despite its empirical success, the theoretical underpinnings of InfoNCE remain limited. In this work, we introduce an explicit feature space to model augmented views of samples and a transition probability matrix to capture data augmentation dynamics. We demonstrate that InfoNCE optimizes the probability of two views sharing the same source toward a constant target defined by this matrix, naturally inducing feature clustering in the representation space. Leveraging this insight, we propose Scaled Convergence InfoNCE (SC-InfoNCE), a novel loss function that introduces a tunable convergence target to flexibly control feature similarity alignment. By scaling the target matrix, SC-InfoNCE enables flexible control over feature similarity alignment, allowing the training objective to better match the statistical properties of downstream data. Experiments on benchmark datasets, including image, graph, and text tasks, show that SC-InfoNCE consistently achieves strong and reliable performance across diverse domains.

cs.LG↗

arXiv2025

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities. However, current VLA models often struggle with physically infeasible action outputs, complex model structures, or unnecessarily long reasoning. In this paper, we propose AutoVLA, a novel VLA model that unifies reasoning and action generation within a single autoregressive generation model for end-to-end autonomous driving. AutoVLA performs semantic reasoning and trajectory planning directly from raw visual inputs and language instructions. We tokenize continuous trajectories into discrete, feasible actions, enabling direct integration into the language model. For training, we employ supervised fine-tuning to equip the model with dual thinking modes: fast thinking (trajectory-only) and slow thinking (enhanced with chain-of-thought reasoning). To further enhance planning performance and efficiency, we introduce a reinforcement fine-tuning method based on Group Relative Policy Optimization (GRPO), reducing unnecessary reasoning in straightforward scenarios. Extensive experiments across real-world and simulated datasets and benchmarks, including nuPlan, nuScenes, Waymo, and CARLA, demonstrate the competitive performance of AutoVLA in both open-loop and closed-loop settings. Qualitative results showcase the adaptive reasoning and accurate planning capabilities of AutoVLA in diverse scenarios.

cs.CV↗

arXiv2025

MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection

Infrastructure-based perception plays a crucial role in intelligent transportation systems, offering global situational awareness and enabling cooperative autonomy. However, existing camera-based detection models often underperform in such scenarios due to challenges such as multi-view infrastructure setup, diverse camera configurations, degraded visual inputs, and various road layouts. We introduce MIC-BEV, a Transformer-based bird's-eye-view (BEV) perception framework for infrastructure-based multi-camera 3D object detection. MIC-BEV flexibly supports a variable number of cameras with heterogeneous intrinsic and extrinsic parameters and demonstrates strong robustness under sensor degradation. The proposed graph-enhanced fusion module in MIC-BEV integrates multi-view image features into the BEV space by exploiting geometric relationships between cameras and BEV cells alongside latent visual cues. To support training and evaluation, we introduce M2I, a synthetic dataset for infrastructure-based object detection, featuring diverse camera configurations, road layouts, and environmental conditions. Extensive experiments on both M2I and the real-world dataset RoScenes demonstrate that MIC-BEV achieves state-of-the-art performance in 3D object detection. It also remains robust under challenging conditions, including extreme weather and sensor degradation. These results highlight the potential of MIC-BEV for real-world deployment. The dataset and source code are available at: https://github.com/HandsomeYun/MIC-BEV.

cs.CV↗

arXiv2025

Robust LLM Training Infrastructure at ByteDance

The training scale of large language models (LLMs) has reached tens of thousands of GPUs and is still continuously expanding, enabling faster learning of larger models. Accompanying the expansion of the resource scale is the prevalence of failures (CUDA error, NaN values, job hang, etc.), which poses significant challenges to training stability. Any large-scale LLM training infrastructure should strive for minimal training interruption, efficient fault diagnosis, and effective failure tolerance to enable highly efficient continuous training. This paper presents ByteRobust, a large-scale GPU infrastructure management system tailored for robust and stable training of LLMs. It exploits the uniqueness of LLM training process and gives top priorities to detecting and recovering failures in a routine manner. Leveraging parallelisms and characteristics of LLM training, ByteRobust enables high-capacity fault tolerance, prompt fault demarcation, and localization with an effective data-driven approach, comprehensively ensuring continuous and efficient training of LLM tasks. ByteRobust is deployed on a production GPU platform and achieves 97% ETTR for a three-month training job on 9,600 GPUs.

cs.LG↗

arXiv2025

RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors

Online high-definition (HD) map construction is crucial for scaling autonomous driving systems. While Transformer-based methods have become prevalent in online HD map construction, most existing approaches overlook the inherent spatial dependencies and semantic relationships among map elements, which constrains their accuracy and generalization capabilities. To address this, we propose RelMap, an end-to-end framework that explicitly models both spatial relations and semantic priors to enhance online HD map construction. Specifically, we introduce a Class-aware Spatial Relation Prior, which explicitly encodes relative positional dependencies between map elements using a learnable class-aware relation encoder. Additionally, we design a Mixture-of-Experts-based Semantic Prior, which routes features to class-specific experts based on predicted class probabilities, refining instance feature decoding. RelMap is compatible with both single-frame and temporal perception backbones, achieving state-of-the-art performance on both the nuScenes and Argoverse 2 datasets.

cs.CV↗

arXiv2025

GEN: A Practical Alternative to Graph Transformers for Long-Range Graph Modeling

Message Passing Neural Networks (MPNNs) model local relations effectively but struggle to propagate information over long distances. Graph Transformers (GTs) mitigate this via global self-attention, yet their quadratic cost in the number of nodes limits scalability. We propose Graph Elimination Networks (GENs), an MPNN variant that approximates GT-like long-range modeling while maintaining high efficiency. GENs combine edge-wise and hop-wise self-attention in parallel; their multiplicative composition yields an attention kernel separable across edge and hop factors within a bounded K-hop receptive field. To enable hop-wise attention, we introduce the Graph Elimination Algorithm (GEA), which prevents double counting across hops, ensuring that each round injects the k-hop incremental contribution exactly once. Taking differences between successive rounds recovers the k-hop increment and yields disentangled multi-hop features as inputs for hop-wise attention. This preserves clearer structural distinctions across hop distances and enables more faithful modeling of pairwise dependencies between distant nodes within the K-hop neighborhood. On the Long-Range Graph Benchmark (LRGB), GENs outperform strong MPNN baselines by 7.7 and 6.0 percentage points (pp) on PascalVOC-SP and COCO-SP, and achieve performance on par with or better than state-of-the-art Graph Transformers. On OGBN-Products, GENs support full-batch training/inference, while sparse-attention baselines like Exphormer struggle with memory limits under comparable budgets, highlighting GENs as a practical alternative for large, sparse graphs.

cs.LG↗

arXiv2025

Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models

Machine vision systems (MVS) are intrinsically vulnerable to performance degradation under adverse visual conditions. To address this, we propose a machine-centric image quality assessment (MIQA) framework that quantifies the impact of image degradations on MVS performance. We establish an MIQA paradigm encompassing the end-to-end assessment workflow. To support this, we construct a machine-centric image quality database (MIQD-2.5M), comprising 2.5 million samples that capture distinctive degradation responses in both consistency and accuracy metrics, spanning 75 vision models, 250 degradation types, and three representative vision tasks. We further propose a region-aware MIQA (RA-MIQA) model to evaluate MVS visual quality through fine-grained spatial degradation analysis. Extensive experiments benchmark the proposed RA-MIQA against seven human visual system (HVS)-based IQA metrics and five retrained classical backbones. Results demonstrate RA-MIQA's superior performance in multiple dimensions, e.g., achieving SRCC gains of 13.56% on consistency and 13.37% on accuracy for image classification, while also revealing task-specific degradation sensitivities. Critically, HVS-based metrics prove inadequate for MVS quality prediction, while even specialized MIQA models struggle with background degradations, accuracy-oriented estimation, and subtle distortions. This study can advance MVS reliability and establish foundations for machine-centric image processing and optimization. The model and code are available at: https://github.com/XiaoqiWang/MIQA.

cs.CV↗

arXiv2025

Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment

Current Omnidirectional Image Quality Assessment (OIQA) methods struggle to evaluate locally non-uniform distortions due to inadequate modeling of spatial variations in quality and ineffective feature representation capturing both local details and global context. To address this, we propose a graph neural network-based OIQA framework that explicitly models structural relationships between viewports to enhance perception of spatial distortion non-uniformity. Our approach employs Fibonacci sphere sampling to generate viewports with well-structured topology, representing each as a graph node. Multi-stage feature extraction networks then derive high-dimensional node representation. To holistically capture spatial dependencies, we integrate a Graph Attention Network (GAT) modeling fine-grained local distortion variations among adjacent viewports, and a graph transformer capturing long-range quality interactions across distant regions. Extensive experiments on two large-scale OIQA databases with complex spatial distortions demonstrate that our method significantly outperforms existing approaches, confirming its effectiveness and strong generalization capability.

cs.CV↗

arXiv2025

Joint multi-dimensional dynamic attention and transformer for general image restoration

Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining efficiency. This paper introduces a novel image restoration architecture that combines multi-dimensional dynamic attention and self-attention within a U-Net framework. To leverage the global modeling capabilities of transformers and the local modeling capabilities of convolutions, we integrate sole CNNs in the encoder-decoder and sole transformers in the latent layer. Additionally, we design convolutional kernels with selected multi-dimensional dynamic attention to capture diverse degraded inputs efficiently. A transformer block with transposed self-attention further enhances global feature extraction while maintaining efficiency. Extensive experiments demonstrate that our method achieves a better balance between performance and computational complexity across five image restoration tasks: deraining, deblurring, denoising, dehazing, and enhancement, as well as superior performance for high-level vision tasks. The source code will be available at https://github.com/House-yuyu/MDDA-former.

cs.CV↗

arXiv2025

V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction

Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents' information across different spatial locations but ignores temporal cues and temporal tasks (e.g., temporal perception and prediction). In this paper, we focus on the spatio-temporal fusion in V2X scenarios and design one-step and multi-step communication strategies (when to transmit) as well as examine their integration with three fusion strategies - early, late, and intermediate (what to transmit), providing comprehensive benchmarks with 11 fusion models (how to fuse). Furthermore, we propose V2XPnP, a novel intermediate fusion framework within one-step communication for end-to-end perception and prediction. Our framework employs a unified Transformer-based architecture to effectively model complex spatio-temporal relationships across multiple agents, frames, and high-definition maps. Moreover, we introduce the V2XPnP Sequential Dataset that supports all V2X collaboration modes and addresses the limitations of existing real-world datasets, which are restricted to single-frame or single-mode cooperation. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods in both perception and prediction tasks.

cs.CV↗

arXiv2025

PC-SRIF: Preconditioned Cholesky-based Square Root Information Filter for Vision-aided Inertial Navigation

In this paper, we introduce a novel estimator for vision-aided inertial navigation systems (VINS), the Preconditioned Cholesky-based Square Root Information Filter (PC-SRIF). When solving linear systems, employing Cholesky decomposition offers superior efficiency but can compromise numerical stability. Due to this, existing VINS utilizing (Square Root) Information Filters often opt for QR decomposition on platforms where single precision is preferred, avoiding the numerical challenges associated with Cholesky decomposition. While these issues are often attributed to the ill-conditioned information matrix in VINS, our analysis reveals that this is not an inherent property of VINS but rather a consequence of specific parameterizations. We identify several factors that contribute to an ill-conditioned information matrix and propose a preconditioning technique to mitigate these conditioning issues. Building on this analysis, we present PC-SRIF, which exhibits remarkable stability in performing Cholesky decomposition in single precision when solving linear systems in VINS. Consequently, PC-SRIF achieves superior theoretical efficiency compared to alternative estimators. To validate the efficiency advantages and numerical stability of PC-SRIF based VINS, we have conducted well controlled experiments, which provide empirical evidence in support of our theoretical findings. Remarkably, in our VINS implementation, PC-SRIF's runtime is 41% faster than QR-based SRIF.

cs.RO↗

arXiv2025

PC-JND: Subjective Study and Dataset on Just Noticeable Difference for Point Clouds in 6DoF Virtual Reality

The Just Noticeable Difference (JND) accounts for the minimum distortion at which humans can perceive a difference between a pristine stimulus and its distorted version. The JND concept has been widely applied in visual signal processing tasks, including coding, transmission, rendering, and quality assessment, to optimize human-centric media experiences. A point cloud is a mainstream volumetric data representation consisting of both geometry information and attributes (e.g. color). Point clouds are used for advanced immersive 3D media such as Virtual Reality (VR). However, the JND characteristics of viewing point clouds in VR have not been explored before. In this paper, we study the point cloud-wise JND (PCJND) characteristics in a Six Degrees of Freedom (6DoF) VR environment using a head-mounted display. Our findings reveal that the texture PCJND of human eyes is smaller than the geometry PCJND for most point clouds. Furthermore, we identify a correlation between colorfulness and texture PCJND. However, there is no significant correlation between colorfulness and the geometry PCJND, nor between the number of points and neither the texture or geometry PCJND. To support future research in JND prediction and perception-driven signal processing, we introduce PC-JND, a novel point cloud-based JND dataset. This dataset will be made publicly available to facilitate advancements in perceptual optimization for immersive media.

cs.MM↗

arXiv2025

CDA-SimBoost: A Unified Framework Bridging Real Data and Simulation for Infrastructure-Based CDA Systems

Cooperative Driving Automation (CDA) has garnered increasing research attention, yet the role of intelligent infrastructure remains insufficiently explored. Existing solutions offer limited support for addressing long-tail challenges, real-synthetic data fusion, and heterogeneous sensor management. This paper introduces CDA-SimBoost, a unified framework that constructs infrastructure-centric simulation environments from real-world data. CDA-SimBoost consists of three main components: a Digital Twin Builder for generating high-fidelity simulator assets based on sensor and HD map data, OFDataPip for processing both online and offline data streams, and OpenCDA-InfraX, a high-fidelity platform for infrastructure-focused simulation. The system supports realistic scenario construction, rare event synthesis, and scalable evaluation for CDA research. With its modular architecture and standardized benchmarking capabilities, CDA-SimBoost bridges real-world dynamics and virtual environments, facilitating reproducible and extensible infrastructure-driven CDA studies. All resources are publicly available at https://github.com/zhz03/CDA-SimBoost

eess.SY↗

arXiv2025

A reconfigurable arbitrary retarder array as complex structured matter

Tuneable retarder arrays, such as spatially patterned liquid crystal devices, have given rise to impressive photonic functionality, fuelling diverse applications ranging from microscopy and holography to encryption and communications. Presently these solutions are limited by the controllable degrees of freedom of structured matter, hindering applications that demand photonic systems with high flexibility and reconfigurable topologies. Here we demonstrate a compound modulator that implements a synthetic tuneable arbitrary retarder array as virtual pixels derived by cascading low functionality tuneable devices, realising full dynamic control of its arbitrary elliptical axis geometry, retardance value, and induced phase. Our approach offers unprecedented functionality that is user-defined and possesses high flexibility, allowing our modulator to act as a new beam generator, analyser, and corrector, opening an exciting path to tuneable topologies of light and matter.

physics.optics↗

arXiv2025

Deep Learning based Joint Geometry and Attribute Up-sampling for Large-Scale Colored Point Clouds

Colored point cloud, which includes geometry and attribute components, is a mainstream representation enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep learning-based Joint Geometry and Attribute Up-sampling (JGAU) method that learns to model both geometry and attribute patterns while leveraging spatial attribute correlations. First, we establish and release a large-scale dataset for colored point cloud up-sampling called SYSU-PCUD, containing 121 large-scale colored point clouds with diverse geometry and attribute complexities across six categories and four sampling rates. Second, to improve the quality of up-sampled point clouds, we propose a deep learning-based JGAU framework that jointly up-samples geometry and attributes. It consists of a geometry up-sampling network and an attribute up-sampling network, where the latter leverages the up-sampled auxiliary geometry to model neighborhood correlations of the attributes. Third, we propose two coarse attribute up-sampling methods, Geometric Distance Weighted Attribute Interpolation (GDWAI) and Deep Learning-based Attribute Interpolation (DLAI), to generate coarse up-sampled attributes for each point. Then, an attribute enhancement module is introduced to refine these up-sampled attributes and produce high-quality point clouds by further exploiting intrinsic attribute and geometry patterns. Extensive experiments show that the Peak Signal-to-Noise Ratio (PSNR) achieved by the proposed JGAU method is 33.90 decibels, 32.10 decibels, 31.10 decibels, and 30.39 decibels for up-sampling rates of 4 times, 8 times, 12 times, and 16 times, respectively. Compared to state-of-the-art methods, JGAU achieves average PSNR gains of 2.32 decibels, 2.47 decibels, 2.28 decibels, and 2.11 decibels at these four up-sampling rates, demonstrating significant improvement.

cs.CV↗

arXiv2025

Online high-precision prediction method for injection molding product weight by integrating time series/non-time series mixed features and feature attention mechanism

To address the challenges of untimely detection and online monitoring lag in injection molding quality anomalies, this study proposes a mixed feature attention-artificial neural network (MFA-ANN) model for high-precision online prediction of product weight. By integrating mechanism-based with data-driven analysis, the proposed architecture decouples time series data (e.g., melt flow dynamics, thermal profiles) from non-time series data (e.g., mold features, pressure settings), enabling hierarchical feature extraction. A self-attention mechanism is strategically embedded during cross-domain feature fusion to dynamically calibrate inter-modality feature weights, thereby emphasizing critical determinants of weight variability. The results demonstrate that the MFA-ANN model achieves a RMSE of 0.0281 with 0.5 g weight fluctuation tolerance, outperforming conventional benchmarks: a 25.1% accuracy improvement over non-time series ANN models, 23.0% over LSTM networks, 25.7% over SVR, and 15.6% over RF models, respectively. Ablation studies quantitatively validate the synergistic enhancement derived from the integration of mixed feature modeling (contributing 22.4%) and the attention mechanism (contributing 11.2%), significantly enhancing the model's adaptability to varying working conditions and its resistance to noise. Moreover, critical sensitivity analyses further reveal that data resolution significantly impacts prediction reliability, low-fidelity sensor inputs degrade performance by 23.8% RMSE compared to high-precision measurements. Overall, this study provides an efficient and reliable solution for the intelligent quality control of injection molding processes.

cs.LG↗