Search arXiv⌕ Search

arXiv subjects

Da Zhang

Publications and source records attributed to Da Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Evaluation of Image Noise from Computed Tomography in an Organ-Specific Anthropomorphic Phantom

Computed tomography (CT) is used ubiquitously for diagnostic imaging, with novel iterative reconstructions such as hybrid iterative reconstruction with partial model-based component (ASiR-V) and deep learning image reconstruction (DLIR) increasingly utilized. In conjunction, CT vendors have developed a noise index (NI) to reduce radiation dose during protocol development. However, it is unclear how these reconstruction algorithms reduce noise as NI changes, particularly across multiple organs. The goal of this study was to utilize an anthropomorphic phantom to evaluate image noise against the prescribed NI across different organs, determine if DLIR reduces image noise compared to ASiR-V, and use this relationship to determine the maximum volume CT dose index (CTDIvol) reduction at equivalent noise levels. Repeat images were acquired on a GE HealthCare Revolution Apex CT scanner across NI values in an anthropomorphic adult-sized phantom from Kyoto Kagaku with ASiR-V and DLIR. Organs-of-interest were contoured using TotalSegmentator in 3D Slicer. The correlation between the CTDIvol and NI was determined. The standard deviation of the difference in the repeat images was used as a noise metric (NM), correlated with NI, used to determine the NI at equivalent NM between ASiR-V and DLIR, then applied to determine the dose reduction and difference in NM. The relationship between NI and the resulting CTDIvol was found to be proportional to a power law of exponent -2.23. The maximum potential absolute dose reduction from using DLIR was found in the liver at 1.3 mGy with an NI of 7.9. Across all organs, the relative dose reduction increased, the NM-to-NI ratio decreased, and the noise reduction increased across NI. The relationship between image noise and the prescribed NI differed between ASiR-V and DLIR and varied by organ, with model-based dose reductions of up to 1.3 mGy in the liver.

physics.med-ph↗
arXiv2026

Exploring the Underwater World Segmentation without Extra Training

Accurate segmentation of marine organisms is vital for biodiversity monitoring and ecological assessment, yet existing datasets and models remain largely limited to terrestrial scenes. To bridge this gap, we introduce \textbf{AquaOV255}, the first large-scale and fine-grained underwater segmentation dataset containing 255 categories and over 20K images, covering diverse categories for open-vocabulary (OV) evaluation. Furthermore, we establish the first underwater OV segmentation benchmark, \textbf{UOVSBench}, by integrating AquaOV255 with five additional underwater datasets to enable comprehensive evaluation. Alongside, we present \textbf{Earth2Ocean}, a training-free OV segmentation framework that transfers terrestrial vision--language models (VLMs) to underwater domains without any additional underwater training. Earth2Ocean consists of two core components: a Geometric-guided Visual Mask Generator (\textbf{GMG}) that refines visual features via self-similarity geometric priors for local structure perception, and a Category-visual Semantic Alignment (\textbf{CSA}) module that enhances text embeddings through multimodal large language model reasoning and scene-aware template construction. Extensive experiments on the UOVSBench benchmark demonstrate that Earth2Ocean achieves significant performance improvement on average while maintaining efficient inference.

cs.CV↗
arXiv2026

Perturbation-Regularized Open-Vocabulary Remote Sensing Segmentation with Unified Multi-Domain Evaluation

Open-vocabulary remote sensing image segmentation (OVRSIS) aims to segment text-specified categories beyond a fixed label space. Its key challenge is to maintain reliable pixel--text correspondence under substantial appearance variation in remote-sensing imagery. Existing methods often rely on specialized vision--language representations or complex adaptation mechanisms, yet still perform deterministic matching between fixed text prototypes and individual visual features. We instead formulate OVRSIS as a \emph{distributional pixel--text alignment} problem and propose \textbf{Pi-Seg}, a lightweight perturbation-based framework. Pi-Seg introduces learnable variations into textual prototypes and dense visual features before alignment. Segmentation supervision encourages perturbations that enlarge the target-to-distractor margin while suppressing harmful feature shifts. Pi-Seg consistently improves performance under the existing \textit{single-source} OVRSISBench protocols. To evaluate OVRSIS beyond source-specific training settings, we further introduce a unified \textit{multi-source} protocol and construct \textbf{GlobalRSOV95K}, containing approximately 95K densely annotated images and 35 semantic categories. Models are trained on this shared dataset and evaluated on an image-disjoint suite of 10 downstream datasets. The complete benchmark covers more than 170K images and 122 categories. Experiments under both single-source and multi-source protocols show that Pi-Seg improves cross-dataset transfer and generalizes effectively to practical geospatial segmentation tasks, while GlobalRSOV95K provides a common foundation for transferable OVRSIS research. \footnote{\url{https://github.com/LiBingyu01/Pi-Seg}}

cs.CV↗
arXiv2026

Dissipative phase transitions in quantum reservoir computing

Enhanced performance of quantum reservoir computing has been associated with dynamical phase transitions, but whether this connection extends to dissipative systems and which relaxation mechanisms underlie it remain insufficiently understood. We systematically compare driven-dissipative Kerr reservoirs across first-order and continuous dissipative phase transitions and find enhanced memory and nonlinear processing near both phase boundaries. Although the closure of the Liouvillian gap marks the transitions in the thermodynamic limit, computational performance does not generally follow gap suppression. An exact post-training Liouvillian-mode decomposition quantitatively attributes the trained memory to intrinsic relaxation channels. It shows that the gap mode contributes only weakly, while finite-rate modes and their cross-contributions dominate the enhanced capacity. These results go beyond phenomenological correlations by directly linking memory capacity to the intrinsic Liouvillian relaxation spectrum. Moreover, these findings provide a physical basis for designing dissipative quantum reservoirs and testing memory-enhancement mechanisms in experimentally accessible Kerr platforms.

quant-ph↗
arXiv2026

Coherent Floquet quantum reservoirs for molecular property prediction

Quantum reservoir computing (QRC) uses quantum dynamics to represent input histories for prediction through a trained classical readout. Discrete time crystals (DTCs) exhibit robust subharmonic responses under periodic driving, and previous work has used their dynamics to construct DTC-QRC. Here we construct a DTC-based reservoir architecture to predict molecular properties from structural and dynamical observations. Coherent Floquet evolution processes local molecular graph events and surface-hopping frames, while controlled reset regulates the contribution of earlier inputs. Measurements at the end of each input sequence yield a feature vector of fixed dimension. Trained classical decoders use this vector for inhibitor-activity and blood--brain-barrier permeability classification and electronic-gap forecasting, while the reservoir parameters remain fixed during training. With matched input lengths and output widths, DTC-QRC outperforms echo-state networks on long-prefix graph classification and the studied ethene gap forecasting tasks. Dephasing lowers performance in both applications, consistent with a role for coherent propagation. Experiments on the Quafu superconducting quantum cloud platform show that pair observables retain task information under device noise. The architecture provides a common framework for molecular screening and time-resolved property prediction using quantum reservoir computing.

quant-ph↗
arXiv2026

Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing

Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS), an emerging task that adapts Open-Vocabulary Segmentation (OVS) to the remote sensing (RS) domain, remains underexplored due to the absence of a unified evaluation benchmark and the domain gap between natural and RS images. To bridge these gaps, we first establish a standardized OVRSIS benchmark (\textbf{OVRSISBench}) based on widely-used RS segmentation datasets, enabling consistent evaluation across methods. Using this benchmark, we comprehensively evaluate several representative OVS/OVRSIS models and reveal their limitations when directly applied to remote sensing scenarios. Building on these insights, we propose \textbf{RSKT-Seg}, a novel open-vocabulary segmentation framework tailored for remote sensing. RSKT-Seg integrates three key components: (1) a Multi-Directional Cost Map Aggregation (RS-CMA) module that captures rotation-invariant visual cues by computing vision-language cosine similarities across multiple directions; (2) an Efficient Cost Map Fusion (RS-Fusion) transformer, which jointly models spatial and semantic dependencies with a lightweight dimensionality reduction strategy; and (3) a Remote Sensing Knowledge Transfer (RS-Transfer) module that injects pre-trained knowledge and facilitates domain adaptation via enhanced upsampling. Extensive experiments on the benchmark show that RSKT-Seg consistently outperforms strong OVS baselines by +3.8 mIoU and +5.9 mACC, while achieving 2x faster inference through efficient aggregation. Our code is \href{https://github.com/LiBingyu01/RSKT-Seg}{\textcolor{blue}{here}}.

cs.CV↗
arXiv2026

Semantic-Aware Temporal Adaptation for UAV Anti-UAV Tracking

UAV Anti-UAV tracking is an emerging low-altitude security task for localizing an adversarial UAV using the onboard camera of a moving observer UAV. It differs from conventional UAV tracking and ground-based Anti-UAV tracking because both the camera platform and the target move simultaneously. This dual-dynamic setting induces rapid viewpoint changes, motion blur, scale variation, and visually similar distractors, making reliable appearance matching difficult. Under such rapidly changing conditions, fixed visual representations are often insufficient because target appearance becomes unreliable and feature distributions may deviate from the training domain. The target language description remains stable across frames and can therefore serve as a semantic anchor for temporal state propagation, while online feature-distribution alignment can reduce video-specific test-time shifts. In this paper, we propose \emph{SATATrack}, a Semantic-Aware Temporal Adaptation framework for UAV Anti-UAV tracking. SATATrack introduces Semantic-Aware Context Propagation (SACP), which uses the target description to guide temporal context propagation across backbone stages and preserve target identity under rapid appearance changes. An auxiliary contrastive regularizer is used during training to discourage responses to semantically similar background regions. During inference, Temporal-Aware Distribution Alignment (TADA) aligns feature distributions online without updating model parameters, combining recent-frame estimates with training-time statistics for stability. SATATrack achieves state-of-the-art performance on the UAV-Anti-UAV benchmark while remaining competitive in Anti-UAV and UAV object tracking tasks. The code will be available at https://github.com/XiaozhenQiao/SATATrack.

cs.CV↗
arXiv2026

CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking

Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight. During sustained occlusion, a policy may lose the target state, execute actions toward an incorrect region, and amplify this error through subsequent observations until re-acquisition becomes impossible. To this end, we present CosFly-VLA, a spatially aware VLA model that jointly grounds the target, estimates its visibility, and generates continuous flight actions through a structured prediction interface. To train this policy, we use a large-scale recipe over diverse data sources. Spatially Grounded Continued Pretraining (CPT) on a 500k mixed pool injects UAV-view depth, distance, and 3-D spatial reasoning. A three-stage Curriculum-based Supervised Fine-Tuning (SFT) process then specializes the tracker through multi-head warm-up followed by two-stage curriculum learning over natural and hard / long-occlusion data. Chain-of-Thought (CoT) training subsequently teaches recovery-oriented reasoning traces before structured answers. Finally, a closed-loop Reinforcement Learning (RL) stage optimizes tracking behavior with a multi-component reward covering stand-off tracking, grounding quality, collision avoidance, and task success. Relative to OpenVLA, CosFly-VLA-0.8B reduces open-loop Average Displacement Error (ADE) by 34.1% on seen-test and 35.3% on unseen-test. Closed-loop optimization improves Success Rate (SR) by 29.8% and 2.5%, respectively. These results demonstrate progress from visible-frame imitation toward spatially grounded action-closed-loop control, evaluated under a shared oracle state history.

cs.RO↗
arXiv2026

Enhancing Quantum Machine Learning with Anyons

The power of quantum computing and quantum machine learning relies on harnessing uniquely quantum phenomena as computational resources. While superposition, coherence and entanglement have been central to this effort, the role of particle exchange statistics remains largely unexplored. Here, we introduce a quantum kernel framework that unifies bosonic, fermionic, and anyonic (fractional) exchange statistics within a single learning paradigm. We study this family of kernels from three perspectives. At the representation level, Haar-averaged effective-dimension analysis shows that fractional exchange phases access feature-space directions inaccessible to the purely symmetric or antisymmetric limits. At the level of kernel geometry, the corresponding Gram matrices show greater separation from the distinguishable-particle baseline and reduced label-dependent model complexity. Finally, on learning benchmarks, anyonic kernels consistently outperform their bosonic and fermionic counterparts, with stronger target alignment and more favorable class geometry. Together, these findings show that exchange statistics reshape the structure and geometry of quantum feature space, leading to enhanced learning performance. Our work identifies particle exchange statistics as an overlooked computational ingredient for quantum machine learning and provides the first systematic comparison of quantum learning models across exchange phases.

quant-ph↗
arXiv2026

An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation

Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored. To bridge this gap, we introduce \textbf{Multi-temporal Referring Segmentation (MTRS)}, a new task that aims to segment language-described temporal changes from multi-temporal images. MTRS extends conventional referring segmentation and change detection by jointly requiring temporal correspondence reasoning, language grounding, and pixel-level mask prediction. We propose \textbf{CRAFT-Agent}, an automated data construction pipeline with human auditing, and build \textbf{MTRefSeg-21K}, the first MTRS benchmark, containing 21K high-quality multi-temporal image-text-mask triplets across diverse scenes, viewpoints, and domains. Benchmarking a broad set of VLM- and LVLM-based models reveals that direct inference performs poorly, while task-specific fine-tuning remains limited. To address this, we propose \textbf{MTRefSeg-R1}, a change-aware LVLM framework trained with a two-stage strategy. It first learns general temporal-change perception from 20K vision-only bi-temporal samples, and is then fine-tuned on MTRefSeg-21K for fine-grained language-guided temporal localization. MTRefSeg-R1 explicitly models cross-temporal visual differences, aligns language instructions with temporal variations, and predicts referred change masks. Extensive experiments show that MTRefSeg-R1 achieves strong and often superior performance compared with existing LVLM baselines, demonstrating the challenge and potential of MTRS.

cs.CV↗
arXiv2026

MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification

Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointly model local-global dynamics and handle nonstationarities like baseline drift, while often failing to capture latent channel interactions. To address these challenges, we propose MedMamba, an end-to-end architecture that integrates state space models with domain-specific inductive biases. Specifically, MedMamba first employs multi-scale convolutional embeddings to capture discriminative local morphology. Second, to mitigate nonstationarity, we introduce a tri-branch differential state space encoder that processes raw, temporal-difference, and frequency-domain views, fusing them to emphasize informative patterns while suppressing drift. Furthermore, to uncover latent channel correlations, we design a spatial graph Mamba module that learns a directed dependency structure regularized toward sparsity and acyclicity, which obviates the need for predefined graphs. Extensive experiments on five real-world datasets demonstrate that MedMamba achieves state-of-the-art performance while maintaining linear computational complexity, and ablation studies validate each component's contribution.Code is available at https://github.com/zhangda1018/MedMamba.

cs.LG↗
arXiv2026

Simulation of complex DNA damage enhancement and biological effect validation for Proton-CAT

Proton therapy has been rapidly advancing due to its excellent conformal index, but its relatively low relative biological effect (RBE) has somewhat limited its therapeutic efficacy for certain tumors. To address this, we previously proposed a nitrogen-targeting Proton-Carbon-Alpha-Therapy (Proton-CAT) enhancement method. In this letter, we present combined multi-scale DNA damage simulations and in vitro cell experiments, further investigating the mechanism of the Proton-CAT. It has been show that $^{15}$N enrichment significantly enhances complex DNA damage induced by high linear energy transfer(LET) particles within tumor regions. Under 30\% $^{15}$N conditions, $α$ and $^{12}$C particle induced DSB++ increased by 175.19\% and 52.94\%, respectively. Furthermore, in vitro cell experiments using $^{15}$N-glutamine ($^{15}$N-Glu) as the $^{15}$N carrier indicated that high concentrations of $^{15}$N-Glu did not bring about significant cytotoxicity. Following 2 Gy irradiation, the cell viability in the 500 $μ$g/mL $^{15}$N-Glu treated group exhibited a net reduction of about 15.41\% compared to the control group.This indicates that the enhanced effect of Proton-CAT primarily stems from increased complex DNA damage. This work provides a theoretical basis and multi-scale research framework for the development of the Proton-CAT.

physics.med-ph↗
arXiv2026

Generation of energy-time entangled triphotons in a six-level cold atomic system

Multiphoton entangled states are pivotal resources for implementing optical quantum information protocols. Recently, energy-time-entangled triphotons have been observed in hot atomic ensembles. However, in these protocols, the complex fifth-order nonlinear susceptibility entailed by four- or five-level systems limits our understanding of triphoton generation. Here, to directly capture the generation mechanism of triphotons and their associated optical properties, we investigate the generation of energy-time-entangled triphotons in a six-level cold atomic ensemble. The fifth-order nonlinear susceptibility indicates the existence of two sets of spontaneous six-wave mixing in the system. Notably, triphoton generation in this system is subject to stringent timing constraints. Collectively, these characteristics give rise to threefold coincidence counts, which -- dominated by the fifth-order nonlinear susceptibility -- exhibit asymmetrically damped Rabi oscillations in the two-dimensional time domain. Furthermore, we analytically derive that the temporal correlation properties of conditional two-photon states are preserved -- a unique feature of $W$-class tripartite entanglement. These results not only lay the groundwork for the experimental preparation of triphotons using six-level systems but also provide key support for understanding the generation mechanism of triphotons involving more complex fifth-order nonlinear susceptibilities.

quant-ph↗
arXiv2026

Prototype-Based Low Altitude UAV Semantic Segmentation

Semantic segmentation of low-altitude UAV imagery presents unique challenges due to extreme scale variations, complex object boundaries, and limited computational resources on edge devices. Existing transformer-based segmentation methods achieve remarkable performance but incur high computational overhead, while lightweight approaches struggle to capture fine-grained details in high-resolution aerial scenes. To address these limitations, we propose PBSeg, an efficient prototype-based segmentation framework tailored for UAV applications. PBSeg introduces a novel prototype-based cross-attention (PBCA) that exploits feature redundancy to reduce computational complexity while maintaining segmentation quality. The framework incorporates an efficient multi-scale feature extraction module that combines deformable convolutions (DConv) with context-aware modulation (CAM) to capture both local details and global semantics. Experiments on two challenging UAV datasets demonstrate the effectiveness of the proposed approach. PBSeg achieves 71.86\% mIoU on UAVid and 80.92\% mIoU on UDD6, establishing competitive performance while maintaining computational efficiency. Code is available at https://github.com/zhangda1018/PBSeg.

cs.CV↗
arXiv2026

Nonclassicality of fully degenerate triple-photon states and its application in generating non-Gaussian entanglement

We theoretically demonstrate via numerical modeling that fully degenerate triple-photon states generated by three-mode spontaneous parametric down-conversion can be categorized into four distinct states: 0-phase, $π$/2-phase, $π$-phase, and 3$π$/2-phase squeezed states. Using quantum relative entropy and Wigner negativity as quantitative measures, we show that the nonGaussianity and nonclassicality of these squeezed states increase with the increase of interaction strength. Analogous to Gaussian scenarios, these squeezed states serve as basic building blocks for deterministic preparation of two-mode non-Gaussian states. We study the correlation properties of two-mode state generated by interfering 0-phase and $π$-phase squeezed states on a beam splitter, and reveal its entanglement at 3rd and 6th-order moments using the positive partial transposition criterion based on higher-order covariance matrices. In particular, by adjusting the intensities of the two input beams, the entanglement of the two output modes at the 3rd- and 6th-order moments can be dynamically modulated. Our results highlight the nonclassical nature of fully degenerate triple-photon states and establish a pathway for preparing non-Gaussian entanglement based on such states.

quant-ph↗
arXiv2026

MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment

Most existing underwater instance segmentation approaches are constrained by close-vocabulary prediction, limiting their ability to recognize novel marine categories. To support evaluation, we introduce \textbf{MARIS} (\underline{Mar}ine Open-Vocabulary \underline{I}nstance \underline{S}egmentation), the first large-scale fine-grained benchmark for underwater Open-Vocabulary (OV) segmentation, featuring a limited set of seen categories and diverse unseen categories. Although OV segmentation has shown promise on natural images, our analysis reveals that transfer to underwater scenes suffers from severe visual degradation (e.g., color attenuation) and semantic misalignment caused by lack underwater class definitions. To address these issues, we propose a unified framework with two complementary components. The Geometric Prior Enhancement Module (\textbf{GPEM}) leverages stable part-level and structural cues to maintain object consistency under degraded visual conditions. The Semantic Alignment Injection Mechanism (\textbf{SAIM}) enriches language embeddings with domain-specific priors, mitigating semantic ambiguity and improving recognition of unseen categories. Experiments show that our framework consistently outperforms existing OV baselines both In-Domain and Cross-Domain setting on MARIS, establishing a strong foundation for future underwater perception research.

cs.CV↗
arXiv2026

Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting

Zero-shot object counting (ZSOC) aims to enumerate objects of arbitrary categories specified by text descriptions without requiring visual exemplars. However, existing methods often treat counting as a coarse retrieval task, suffering from a lack of fine-grained quantity awareness. Furthermore, they frequently exhibit spatial insensitivity and degraded generalization due to feature space distortion during model adaptation.To address these challenges, we present \textbf{QICA}, a novel framework that synergizes \underline{q}uantity percept\underline{i}on with robust spatial \underline{c}ast \underline{a}ggregation. Specifically, we introduce a Synergistic Prompting Strategy (\textbf{SPS}) that adapts vision and language encoders through numerically conditioned prompts, bridging the gap between semantic recognition and quantitative reasoning. To mitigate feature distortion, we propose a Cost Aggregation Decoder (\textbf{CAD}) that operates directly on vision-text similarity maps. By refining these maps through spatial aggregation, CAD prevents overfitting while preserving zero-shot transferability. Additionally, a multi-level quantity alignment loss ($\mathcal{L}_{MQA}$) is employed to enforce numerical consistency across the entire pipeline. Extensive experiments on FSC-147 demonstrate competitive performance, while zero-shot evaluation on CARPK and ShanghaiTech-A validates superior generalization to unseen domains.

cs.CV↗
arXiv2026

IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework

Scalable Vector Graphics (SVG) are central to digital design due to their inherent scalability and editability. Despite significant advancements in content generation enabled by Visual Language Models (VLMs), existing text-to-SVG generation methods are limited by a core challenge: the autoregressive training process does not incorporate visual perception of the final rendered image, which fundamentally constrains generation quality. To address this limitation, we propose an Introspective SVG Generation Framework (IntroSVG). At its core, the framework instantiates a unified VLM that operates in a closed loop, assuming dual roles of both generator and critic. Specifically, through Supervised Fine-Tuning (SFT), the model learns to draft SVGs and to provide feedback on their rendered outputs; moreover, we systematically convert early-stage failures into high-quality error-correction training data, thereby enhancing model robustness. Subsequently, we leverage a high-capacity teacher VLM to construct a preference dataset and further align the generator's policy through Direct Preference Optimization (DPO). During inference, the optimized generator and critic operate collaboratively in an iterative "generate-review-refine" cycle, starting from imperfect intermediate drafts to autonomously improve output quality. Experimental results demonstrate that our method achieves state-of-the-art performance across several key evaluation metrics, generating SVGs with more complex structures, stronger semantic alignment, and greater editability. These results corroborate the effectiveness of incorporating explicit visual feedback into the generation loop.

cs.CV↗