arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2025

Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting

Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooking the fine-grained human-object interactions or action semantics that define complex anomalies in surveillance videos. We propose ASK-Hint, a structured prompting framework that leverages action-centric knowledge to elicit more accurate and interpretable reasoning from frozen VLMs. Our approach organizes prompts into semantically coherent groups (e.g. violence, property crimes, public safety) and formulates fine-grained guiding questions that align model predictions with discriminative visual cues. Extensive experiments on UCF-Crime and XD-Violence show that ASK-Hint consistently improves AUC over prior baselines, achieving state-of-the-art performance compared to both fine-tuned and training-free methods. Beyond accuracy, our framework provides interpretable reasoning traces towards anomaly and demonstrates strong generalization across datasets and VLM backbones. These results highlight the critical role of prompt granularity and establish ASK-Hint as a new training-free and generalizable solution for explainable video anomaly detection.

cs.CV↗

arXiv2025

PPD-CPP: Pointwise predictive density calibrated-power prior in dynamically borrowing historical information

Incorporating historical or real-world data into analyses of treatment effects for rare diseases has become increasingly popular. A major challenge, however, lies in determining the appropriate degree of congruence between historical and current data. In this study, we devote ourselves to the capacity of historical data in replicating the current data, and propose a new congruence measure/estimand $p_{CM}$. $p_{CM}$ quantifies the heterogeneity between two datasets following the idea of the marginal posterior predictive $p$-value, and its asymptotic properties were derived. Building upon $p_{CM}$, we develop the pointwise predictive density calibrated-power prior (PPD-CPP) to dynamically leverage historical information. PPD-CPP achieves the borrowing consistency and allows modeling the power parameter either as a fixed scalar or case-specific quantity informed by covariates. Simulation studies were conducted to demonstrate the performance of these methods and the methodology was illustrated using the Mother's Gift study and \textit{Ceriodaphnia dubia} toxicity test.

stat.ME↗

arXiv2025

Neural Operator Feedback for a First-Order PIDE with Spatially-Varying State Delay

A transport PDE with a spatial integral and recirculation with constant delay has been a benchmark for neural operator approximations of PDE backstepping controllers. Introducing a spatially-varying delay into the model gives rise to a gain operator defined through integral equations which the operator's input -- the varying delay function -- enters in previously unencountered manners, including in the limits of integration and as the inverse of the `delayED time' function. This, in turn, introduces novel mathematical challenges in estimating the operator's Lipschitz constant. The backstepping kernel function having two branches endows the feedback law with a two-branch structure, where only one of the two feedback branches depends on both of the kernel branches. For this rich feedback structure, we propose a neural operator approximation of such a two-branch feedback law and prove the approximator to be semiglobally practically stabilizing. With numerical results we illustrate the training of the neural operator and its stabilizing capability.

eess.SY↗

arXiv2025

Tetratomic states of microwave dressed and associated ultracold 23Na40K molecules

Ultracold diatomic molecules have achieved significant breakthroughs in recent years, enabling the exploration of quantum chemistry, precision measurements, and strongly correlated many-body physics. Extending ultracold molecular complexity to polyatomic molecules, such as triatomic and tetratomic molecules, has attracted considerable interest. However, the realization of ultracold polyatomic molecules remains technically challenging due to their complex energy-level structures. While only a few experiments have successfully demonstrated the formation of polyatomic molecules by magnetoassociation or electroassociation, here we present the first step toward producing tetratomic molecules through the development of a microwave association technique combined with microwave dressing. When the two lowest rotational states of the molecules are dressed by a microwave field, weakly bound tetramer states emerge in the entrance channel with free dark excited states $\ket{0}$ and a dressed state $\ket{+}$. The spectroscopy of these weakly bound tetramers is probed by another microwave field that drives transitions from the populated dressed states $\ket{+}$. By precisely discriminating the complex hyperfine structure of the dark excited level $\ket{0}$ from the dressed-state spectroscopy, the binding energy of the tetratomic molecules is measured and characterized. Our work contributes to the understanding of complex few-body physics within a system of microwave-dressed molecules and may open an avenue toward the creation and control of ultracold polyatomic molecules.

cond-mat.quant-gas↗

arXiv2025

SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Images

Multiple instance learning (MIL) has become the leading approach for extracting discriminative features from whole slide images (WSIs) in computational pathology. Attention-based MIL methods can identify key patches but tend to overlook contextual relationships. Transformer models are able to model interactions but require quadratic computational cost and are prone to overfitting. State space models (SSMs) offer linear complexity, yet shuffling patch order disrupts histological meaning and reduces interpretability. In this work, we introduce SemaMIL, which integrates Semantic Reordering (SR), an adaptive method that clusters and arranges semantically similar patches in sequence through a reversible permutation, with a Semantic-guided Retrieval State Space Module (SRSM) that chooses a representative subset of queries to adjust state space parameters for improved global modeling. Evaluation on four WSI subtype datasets shows that, compared to strong baselines, SemaMIL achieves state-of-the-art accuracy with fewer FLOPs and parameters.

cs.CV↗

arXiv2025

CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation

The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios. Despite the substantial domain gaps in RS images that are characterized by variabilities such as location, wavelength, and sensor type, research in this area remains underexplored: (1) Current cross-domain methods primarily focus on Domain Adaptation (DA), which adapts models to predefined domains rather than to unseen ones; (2) Few studies targeting the RSDG issue, especially for semantic segmentation tasks, where existing models are developed for specific unknown domains, struggling with issues of underfitting on other unknown scenarios; (3) Existing RS foundation models tend to prioritize in-domain performance over cross-domain generalization. To this end, we introduce the first vision foundation model for RSDG semantic segmentation, CrossEarth. CrossEarth demonstrates strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline and a model-level Multi-Task Training pipeline. In addition, for the semantic segmentation task, we have curated an RSDG benchmark comprising 32 cross-domain settings across various regions, spectral bands, platforms, and climates, providing a comprehensive framework for testing the generalizability of future RSDG models. Extensive experiments on this benchmark demonstrate the superiority of CrossEarth over existing state-of-the-art methods.

cs.CV↗

arXiv2025

SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution

Multi-contrast Magnetic Resonance Imaging super-resolution (MC-MRI SR) aims to enhance low-resolution (LR) contrasts leveraging high-resolution (HR) references, shortening acquisition time and improving imaging efficiency while preserving anatomical details. The main challenge lies in maintaining spatial-semantic consistency, ensuring anatomical structures remain well-aligned and coherent despite structural discrepancies and motion between the target and reference images. Conventional methods insufficiently model spatial-semantic consistency and underuse frequency-domain information, which leads to poor fine-grained alignment and inadequate recovery of high-frequency details. In this paper, we propose the Spatial-Semantic Consistent Model (SSCM), which integrates a Dynamic Spatial Warping Module for inter-contrast spatial alignment, a Semantic-Aware Token Aggregation Block for long-range semantic consistency, and a Spatial-Frequency Fusion Block for fine structure restoration. Experiments on public and private datasets show that SSCM achieves state-of-the-art performance with fewer parameters while ensuring spatially and semantically consistent reconstructions.

cs.CV↗

arXiv2025

Beyond Video-to-SFX: Video to Audio Synthesis with Environmentally Aware Speech

The generation of realistic, context-aware audio is important in real-world applications such as video game development. While existing video-to-audio (V2A) methods mainly focus on Foley sound generation, they struggle to produce intelligible speech. Meanwhile, current environmental speech synthesis approaches remain text-driven and fail to temporally align with dynamic video content. In this paper, we propose Beyond Video-to-SFX (BVS), a method to generate synchronized audio with environmentally aware intelligible speech for given videos. We introduce a two-stage modeling method: (1) stage one is a video-guided audio semantic (V2AS) model to predict unified audio semantic tokens conditioned on phonetic cues; (2) stage two is a video-conditioned semantic-to-acoustic (VS2A) model that refines semantic tokens into detailed acoustic tokens. Experiments demonstrate the effectiveness of BVS in scenarios such as video-to-context-aware speech synthesis and immersive audio background conversion, with ablation studies further validating our design. Our demonstration is available at~\href{https://xinleiniu.github.io/BVS-demo/}{BVS-Demo}.

cs.SD↗

arXiv2025

FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction

Reconstructing high-fidelity animatable human avatars from monocular videos remains challenging due to insufficient geometric information in single-view observations. While recent 3D Gaussian Splatting methods have shown promise, they struggle with surface detail preservation due to the free-form nature of 3D Gaussian primitives. To address both the representation limitations and information scarcity, we propose a novel method, \textbf{FMGS-Avatar}, that integrates two key innovations. First, we introduce Mesh-Guided 2D Gaussian Splatting, where 2D Gaussian primitives are attached directly to template mesh faces with constrained position, rotation, and movement, enabling superior surface alignment and geometric detail preservation. Second, we leverage foundation models trained on large-scale datasets, such as Sapiens, to complement the limited visual cues from monocular videos. However, when distilling multi-modal prior knowledge from foundation models, conflicting optimization objectives can emerge as different modalities exhibit distinct parameter sensitivities. We address this through a coordinated training strategy with selective gradient isolation, enabling each loss component to optimize its relevant parameters without interference. Through this combination of enhanced representation and coordinated information distillation, our approach significantly advances 3D monocular human avatar reconstruction. Experimental evaluation demonstrates superior reconstruction quality compared to existing methods, with notable gains in geometric accuracy and appearance fidelity while providing rich semantic information. Additionally, the distilled prior knowledge within a shared canonical space naturally enables spatially and temporally consistent rendering under novel views and poses.

cs.CV↗

arXiv2025

TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation

Referring Image Segmentation (RIS) is a task that segments image regions based on language expressions, requiring fine-grained alignment between two modalities. However, existing methods often struggle with multimodal misalignment and language semantic loss, especially in complex scenes containing multiple visually similar objects, where uniquely described targets are frequently mislocalized or incompletely segmented. To tackle these challenges, this paper proposes TFANet, a Three-stage Image-Text Feature Alignment Network that systematically enhances multimodal alignment through a hierarchical framework comprising three stages: Knowledge Plus Stage (KPS), Knowledge Fusion Stage (KFS), and Knowledge Intensification Stage (KIS). In the first stage, we design the Multiscale Linear Cross-Attention Module (MLAM), which facilitates bidirectional semantic exchange between visual features and textual representations across multiple scales. This establishes rich and efficient alignment between image regions and different granularities of linguistic descriptions. Subsequently, the KFS further strengthens feature alignment through the Cross-modal Feature Scanning Module (CFSM), which applies multimodal selective scanning to capture long-range dependencies and construct a unified multimodal representation. This is essential for modeling long-range cross-modal dependencies and enhancing alignment accuracy in complex scenes. Finally, in the KIS, we propose the Word-level Linguistic Feature-guided Semantic Deepening Module (WFDM) to compensate for semantic degradation introduced in earlier stages.

cs.CV↗

arXiv2025

Semi-Supervised Learning for Dose Prediction in Targeted Radionuclide: A Synthetic Data Study

Targeted Radionuclide Therapy (TRT) is a modern strategy in radiation oncology that aims to administer a potent radiation dose specifically to cancer cells using cancer-targeting radiopharmaceuticals. Accurate radiation dose estimation tailored to individual patients is crucial. Deep learning, particularly with pre-therapy imaging, holds promise for personalizing TRT doses. However, current methods require large time series of SPECT imaging, which is hardly achievable in routine clinical practice, and thus raises issues of data availability. Our objective is to develop a semi-supervised learning (SSL) solution to personalize dosimetry using pre-therapy images. The aim is to develop an approach that achieves accurate results when PET/CT images are available, but are associated with only a few post-therapy dosimetry data provided by SPECT images. In this work, we introduce an SSL method using a pseudo-label generation approach for regression tasks inspired by the FixMatch framework. The feasibility of the proposed solution was preliminarily evaluated through an in-silico study using synthetic data and Monte Carlo simulation. Experimental results for organ dose prediction yielded promising outcomes, showing that the use of pseudo-labeled data provides better accuracy compared to using only labeled data.

physics.med-ph↗

arXiv2025

Intermittent chaos in an optomechanical resonator

Chaos is a fundamental phenomenon in nonlinear dynamics, manifesting as irregular and unpredictable behavior across various physical systems. Among the diverse routes to chaos, intermittent chaos is a distinct transition pathway, characterized by the temporal or spatial alternation between periodic and chaotic motions. Here, we experimentally demonstrate, for the first time, optomechanically induced intermittent chaos in an optical whispering-gallery-mode microresonator. Specifically, the system evolves from stable periodic oscillation through an intermittent-chaos regime before fully developing into chaotic motion. As system parameters vary, the proportion of chaotic motion in the time-domain increases asymptotically until chaotic dynamics dominates entirely. Moreover, it is counterintuitive that, intermittent chaos can act as noise of a favorable intensity compared with purely periodic or fully chaotic states, and enhance rather than reduce system's responses in nonlinear ultrasonic detection. These findings not only deepen the comprehensive understanding of chaos formation but also broaden its potential applications in high-precision sensing and information processing.

quant-ph↗

arXiv2025

Observation of quantized vortex in an atomic Bose-Einstein condensate at Dirac point with emergent spin-orbit coupling

When two or more energy bands become degenerate at a singular point in the momentum space, such singularity, or ``Dirac points", gives rise to intriguing quantum phenomena as well as unusual material properties. Systems at the Dirac points can possess topological charges and their unique properties can be probed by various methods, such as transport measurement, interferometry and momentum spectroscopy. While the topology of Dirac point in the momentum space is well studied theoretically, observation of topological defects in a many-body quantum systems at Dirac point remain an elusive goal. Based on atomic Bose-Einstein condensate in a graphene-like optical honeycomb lattice, we directly observe emergence of quantized vortices at the Dirac point. The phase diagram of lattice bosons at the Dirac point is revealed. Our work provides a new way of generating vortices in a quantum gas, and the method is generic and can be applied to different types of optical lattices with topological singularity, especially twisted bilayer optical lattices.

cond-mat.quant-gas↗

arXiv2025

A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks

Traffic congestion propagation poses significant challenges to urban sustainability, disrupting spatial accessibility. The cascading effect of traffic congestion propagation can cause large-scale disruptions to networks. Existing studies have laid a solid foundation for characterizing the cascading effects. However, they typically rely on predefined graph structures and lack adaptability to diverse data granularities. To address these limitations, we propose a spatiotemporal adaptive local search (STALS) method, which feeds the dynamically adaptive adjacency matrices into the local search algorithm to learn propagation rules. Specifically, the STALS is composed of two data-driven modules. One is a dynamic adjacency matrix learning module, which learns the spatiotemporal relationship from congestion graphs by fusing four node features. The other one is the local search module, which introduces local dominance to identify multi-scale congestion bottlenecks and search their propagation pathways. We test our method on the four benchmark networks with an average of 15,000 nodes. The STALS remains a Normalized Mutual Information (NMI) score at 0.97 and an average execution time of 27.66s, outperforming six state-of-the-art methods in robustness and efficiency. We also apply the STALS to three large-scale traffic networks in New York City, the United States, Shanghai, China, and Urumqi, China. The ablation study reveals an average modularity of 0.78 across three cities, demonstrating the spatiotemporal-scale invariance of frequencytransformed features and the spatial heterogeneity of geometric topological features. By integrating dynamic graph learning with Geo-driven spatial analytics, STALS provides a scalable tool for congestion mitigation.

cs.SI↗

arXiv2025

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level. To achieve this goal, we replace the majority of self-attention layers in the common Transformer model architecture with Mamba layers that perform constant computation and require constant memory per generated token. We show that Nemotron-H models offer either better or on-par accuracy compared to other similarly-sized state-of-the-art open-sourced Transformer models (e.g., Qwen-2.5-7B/72B and Llama-3.1-8B/70B), while being up to 3$\times$ faster at inference. To further increase inference speed and reduce the memory required at inference time, we created Nemotron-H-47B-Base from the 56B model using a new compression via pruning and distillation technique called MiniPuzzle. Nemotron-H-47B-Base achieves similar accuracy to the 56B model, but is 20% faster to infer. In addition, we introduce an FP8-based training recipe and show that it can achieve on par results with BF16-based training. This recipe is used to train the 56B model. We are releasing Nemotron-H base model checkpoints with support in Hugging Face and NeMo.

cs.CL↗

arXiv2025

LGBP-OrgaNet: Learnable Gaussian Band Pass Fusion of CNN and Transformer Features for Robust Organoid Segmentation and Tracking

Organoids replicate organ structure and function, playing a crucial role in fields such as tumor treatment and drug screening. Their shape and size can indicate their developmental status, but traditional fluorescence labeling methods risk compromising their structure. Therefore, this paper proposes an automated, non-destructive approach to organoid segmentation and tracking. We introduced the LGBP-OrgaNet, a deep learning-based system proficient in accurately segmenting, tracking, and quantifying organoids. The model leverages complementary information extracted from CNN and Transformer modules and introduces the innovative feature fusion module, Learnable Gaussian Band Pass Fusion, to merge data from two branches. Additionally, in the decoder, the model proposes a Bidirectional Cross Fusion Block to fuse multi-scale features, and finally completes the decoding through progressive concatenation and upsampling. SROrga demonstrates satisfactory segmentation accuracy and robustness on organoids segmentation datasets, providing a potent tool for organoid research.

cs.CV↗

arXiv2025

A Novel Decoupled LVRT Control Strategy for Transient Voltage Stability Enhancement of IBRs Using Voltage-Angle Coupling Analysis

With the fast-increasing penetration of inverter-based resources (IBRs), the voltage support capability of the grid following (GFL) IBRs under low voltage ride through (LVRT) control significantly influences the transient voltage stability of the power system. The existing LVRT adjusts the q-axis current to regulate reactive power injection. However, under a large disturbance, the phase-locked loop (PLL) error invalidates the proportional relationship between the q-axis current and reactive power, consequently causing deviation in the actual reactive power injection of the IBR. Besides, the variation of IBR current, determined by the PLL phase and LVRT, also directly influences the transient voltage. To address this issue, the specific influence of PLL error on active and reactive power injection is first analyzed under LVRT control. In addition, by combining the LVRT and PLL dynamics, the mechanisms of three voltage problems caused by voltage angle coupling are revealed. overvoltage, low voltage, and DC-side overvoltage. The specific scenarios in which these voltage stability problems occur are also obtained by the voltage-vector-triangle graphic. Furthermore, a power angle decoupled LVRT control is proposed to eliminate the influence of voltage angle coupling. Finally, the mechanism analysis and effectiveness of the decoupled LVRT are verified in the case study.

eess.SY↗

arXiv2025

SoAy: A Solution-based LLM API-using Methodology for Academic Information Seeking

Applying large language models (LLMs) for academic API usage shows promise in reducing researchers' academic information seeking efforts. However, current LLM API-using methods struggle with complex API coupling commonly encountered in academic queries. To address this, we introduce SoAy, a solution-based LLM API-using methodology for academic information seeking. It uses code with a solution as the reasoning method, where a solution is a pre-constructed API calling sequence. The addition of the solution reduces the difficulty for the model to understand the complex relationships between APIs. Code improves the efficiency of reasoning. To evaluate SoAy, we introduce SoAyBench, an evaluation benchmark accompanied by SoAyEval, built upon a cloned environment of APIs from AMiner. Experimental results demonstrate a 34.58-75.99\% performance improvement compared to state-of-the-art LLM API-based baselines. All datasets, codes, tuned models, and deployed online services are publicly accessible at https://github.com/RUCKBReasoning/SoAy.

cs.CL↗