arXiv subjects

Jin Wang

Publications and source records attributed to Jin Wang.

At least 109 records · Page 6Linked to original sources

arXiv2026

Slip viscosity and strain-rate viscosity in Taylor-Couette laminar flows: Experimental falsification and end-wall effects

The viscous force should be shear force, the difference between the strain-rate viscosity and the slip viscosity is that the former has conjugate shear force, while the latter does not. The study in this paper verifies the physical authenticity of two viscosity models through Taylor Couette laminar flow experiments with inner and outer cylinders rotating at the same angular velocity, and numerically investigate the influence of relative cylinder spacing and rotational speed on the circumferential velocity under the slip model. The experimental results of LDV measurement with a relative cylinder spacing of 0.3 indicate that the maximum deviation from rigid-body rotation is about 0.86%, which is consistent with the theoretical prediction of slip viscosity model. The numerical simulations show that the end-walls have no effect under the strain-rate viscosity model; but when the slip viscosity model is introduced, the end-walls inevitably bring about the circumferential velocity profile changing along the axial direction, and result in a three-dimensional (3D) spiral streamline pattern influenced by the relative cylinder spacing and angular speed of cylinders.

physics.flu-dyn↗

arXiv2026

Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation

Generating high-quality 3D characters from single images remains a significant challenge in digital content creation, particularly due to complex body poses and self-occlusion. In this paper, we present RCM (Rotate your Character Model), an advanced image-to-video diffusion framework tailored for high-quality novel view synthesis (NVS) and 3D character generation. Compared to existing diffusion-based approaches, RCM offers several key advantages: (1) transferring characters with any complex poses into a canonical pose, enabling consistent novel view synthesis across the entire viewing orbit, (2) high-resolution orbital video generation at 1024x1024 resolution, (3) controllable observation positions given different initial camera poses, and (4) multi-view conditioning supporting up to 4 input images, accommodating diverse user scenarios. Extensive experiments demonstrate that RCM outperforms state-of-the-art methods in both novel view synthesis and 3D generation quality.

cs.CV↗

arXiv2026

HearSay Benchmark: Do Audio LLMs Leak What They Hear?

While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications remain largely unexplored. This paper takes the first step to investigate whether ALLMs inadvertently leak user privacy solely through acoustic voiceprints and introduces $\textit{HearSay}$, a comprehensive benchmark constructed from over 22,000 real-world audio clips. To ensure data quality, the benchmark is meticulously curated through a rigorous pipeline involving automated profiling and human verification, guaranteeing that all privacy labels are grounded in factual records. Extensive experiments on $\textit{HearSay}$ yield three critical findings: $\textbf{Significant Privacy Leakage}$: ALLMs inherently extract private attributes from voiceprints, reaching 92.89% accuracy on gender and effectively profiling social attributes. $\textbf{Insufficient Safety Mechanisms}$: Alarmingly, existing safeguards are severely inadequate; most models fail to refuse privacy-intruding requests, exhibiting near-zero refusal rates for physiological traits. $\textbf{Reasoning Amplifies Risk}$: Chain-of-Thought (CoT) reasoning exacerbates privacy risks in capable models by uncovering deeper acoustic correlations. These findings expose critical vulnerabilities in ALLMs, underscoring the urgent need for targeted privacy alignment. The codes and dataset are available at https://github.com/JinWang79/HearSay_Benchmark

cs.CL↗

arXiv2026

ChemBART: A Pre-trained BART Model Assisting Organic Chemistry Analysis

Recent advances in large language models (LLMs) have demonstrated transformative potential across diverse fields. While LLMs have been applied to molecular simplified molecular input line entry system (SMILES) in computer-aided synthesis planning (CASP), existing methodologies typically address single tasks, such as precursor prediction. We introduce ChemBART, a SMILES-based LLM pre-trained on chemical reactions, which enables a unified model for multiple downstream chemical tasks--achieving the paradigm of "one model, one pre-training, multiple tasks." By leveraging outputs from a mask-filling pre-training task on reaction expressions, ChemBART effectively solves a variety of chemical problems, including precursor/reagent generation, temperature-yield regression, molecular property classification, and optimizing the policy and value functions within a reinforcement learning framework, integrated with Monte Carlo tree search for multi-step synthesis route design. Unlike single-molecule pre-trained LLMs constrained to specific applications, ChemBART addresses broader chemical challenges and integrates them for comprehensive synthesis planning. Crucially, ChemBART-designed multi-step synthesis routes and reaction conditions directly inspired wet-lab validation, which confirmed shorter pathways with ~30% yield improvement over literature benchmarks. Our work validates the power of reaction-focused pre-training and showcases the broad utility of ChemBART in advancing the complete synthesis planning cycle.

cs.LG↗

arXiv2026

Evaluating transfer learning strategies for improving dairy cattle body weight prediction in small farms using depth-image and point-cloud data

Computer vision provides automated, non-invasive, and scalable tools for monitoring dairy cattle, thereby supporting management, health assessment, and phenotypic data collection. Although transfer learning is commonly used for predicting body weight from images, its effectiveness and optimal fine-tuning strategies remain poorly understood in livestock applications, particularly beyond the use of pretrained ImageNet or COCO weights. In addition, while both depth images and three-dimensional point-cloud data have been explored for body weight prediction, direct comparisons of these two modalities in dairy cattle are limited. Therefore, the objectives of this study were to 1) evaluate whether transfer learning from a large farm enhances body weight prediction on a small farm with limited data, and 2) compare the predictive performance of depth-image- and point-cloud-based approaches under three experimental designs. Top-view depth images and point-cloud data were collected from 1,201, 215, and 58 cows at large, medium, and small dairy farms, respectively. Four deep learning models were evaluated: ConvNeXt and MobileViT for depth images, and PointNet and DGCNN for point clouds. Transfer learning markedly improved body weight prediction on the small farm across all four models, outperforming single-source learning and achieving gains comparable to or greater than joint learning. These results indicate that pretrained representations generalize well across farms with differing imaging conditions and dairy cattle populations. No consistent performance difference was observed between depth-image- and point-cloud-based models. Overall, these findings suggest that transfer learning is well suited for small farm prediction scenarios where cross-farm data sharing is limited by privacy, logistical, or policy constraints, as it requires access only to pretrained model weights rather than raw data.

cs.CV↗

arXiv2026

Observation of robust macroscale structural superlubricity

Structural superlubricity (SSL) promises nearly frictionless and wearless sliding, but has until now been considered a special and extreme interfacial phenomenon limited to micro- and nanoscale contacts. Here, we demonstrate robust macroscale SSL within a single sub-millimeter graphite contact. Previously reported near-zero friction coefficients, where friction is nearly independent of normal load, have only been observed at microscale contacts under low loads. Our system expands both contact size and load into the macroscopic regime, exhibiting friction coefficients that fluctuate around zero and reach values as low as $10^{-6}$ across a broad load range from 1 mN to 0.5 N. Negative friction coefficients are also observed. Similar behavior is observed at graphite/MoS$_2$ interfaces, indicating that macroscale SSL is a generalizable phenomenon across flat layered materials. These findings overturn long-standing scaling limitations and establish macroscale SSL as a paradigm-shifting platform for next-generation mechanical and electromechanical systems.

cond-mat.mtrl-sci↗

arXiv2025

Understanding Cellular Noise with Optical Perturbation and Deep Learning

Noise plays a crucial role in the regulation of cellular and organismal function and behavior. Exploring noise's impact is key to understanding fundamental biological processes, such as gene expression, signal transduction, and the mechanisms of development and evolution. Currently, a comprehensive method to quantify dynamical behavior of cellular noise within these biochemical systems is lacking. In this study, we introduce an optically-controlled perturbation system utilizing the light-sensitive Phytochrome B (PhyB) from \textit{Arabidopsis thaliana}, which enables precise noise modulation with high spatial-temporal resolution. Our system exhibits exceptional sensitivity to light, reacting consistently to pulsed light signals, distinguishing it from other photoreceptor-based promoter systems that respond to a single light wavelength. To characterize our system, we developed a stochastic model for phytochromes that accounts for photoactivation/deactivation, thermal reversion, and the dynamics of the light-activated gene promoter system. To precisely control our system, we determined the rate constants for this model using an omniscient deep neural network that can directly map rate constant combinations to time-dependent state joint distributions. By adjusting the activation rates through light intensity and degradation rates via N-terminal mutagenesis, we illustrate that out optical-controlled perturbation can effectively modulate molecular expression level as well as noise. Our results highlight the potential of employing an optically-controlled gene perturbation system as a noise-controlled stimulus source. This approach, when combined with the analytical capabilities of a sophisticated deep neural network, enables the accurate estimation of rate constants from observational data in a broad range of biochemical reaction networks.

q-bio.MN↗

arXiv2025

Quantum Coherence in Reflected and Refracted Beams: A Van Cittert-Zernike Approach

Recent advances in quantum optics have highlighted the critical role of spatial propagation in controlling the quantum coherence of light beams. However, the evolution of quantum coherence for light beams undergoing fundamental optical processes at dielectric interfaces remains unexplored. Furthermore, manipulating multiphoton correlations typically requires complex interactions that challenge few-photon level implementation. Here, we introduce a quantum van Cittert-Zernike theorem for light beams, describing how their coherence-polarization properties are influenced by reflection and refraction, as well as how these properties evolve upon subsequent propagation. Our work demonstrates that the quantum statistics of photonic systems can be controllably modified through the inherent polarization coupling arising from reflection and refraction at an interface, without relying on conventional light-matter interactions. Our approach reveals regimes where thermal light can exhibit sub-Poissonian statistics with fluctuations below the shot-noise level through post-selected measurements, and this statistical property can be tuned by the incident angle. Remarkably, this quantum statistical modification is governed by a scaling law linking beam collimation to far-field thermalization. Our work establishes a robust, decoherence-avoiding mechanism for quantum state control, advancing the fundamental understanding of coherence in quantum optics and opening new avenues for applications in quantum information and metrology.

quant-ph↗

arXiv2025

FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation

Federated Learning (FL) has shown considerable promise in Machine Learning (ML) across numerous devices for privacy protection, efficient data utilization, and dynamic collaboration. However, mobile devices typically have limited and heterogeneous computational capabilities, and different devices may even have different tasks. This client heterogeneity is a major bottleneck hindering the practical application of FL. Existing work mainly focuses on mitigating FL's computation and communication overhead of a single task while overlooking the computing resource heterogeneity issue of different devices in FL. To tackle this, we design FedAPTA, a federated multi-task learning framework. FedAPTA overcomes computing resource heterogeneity through the developed layer-wise model pruning technique, which reduces local model size while considering both data and device heterogeneity. To aggregate structurally heterogeneous local models of different tasks, we introduce a heterogeneous model recovery strategy and a task-aware model aggregation method that enables the aggregation through infilling local model architecture with the shared global model and clustering local models according to their specific tasks. We deploy FedAPTA on a realistic FL platform and benchmark it against nine SOTA FL methods. The experimental outcomes demonstrate that the proposed FedAPTA considerably outperforms the state-of-the-art FL methods by up to 4.23\%. Our code is available at https://github.com/Zhenzovo/FedAPTA.

cs.DC↗

arXiv2025

Structured Multi-Step Reasoning for Entity Matching Using Large Language Model

Entity matching is a fundamental task in data cleaning and data integration. With the rapid adoption of large language models (LLMs), recent studies have explored zero-shot and few-shot prompting to improve entity matching accuracy. However, most existing approaches rely on single-step prompting and offer limited investigation into structured reasoning strategies. In this work, we investigate how to enhance LLM-based entity matching by decomposing the matching process into multiple explicit reasoning stages. We propose a three-step framework that first identifies matched and unmatched tokens between two records, then determines the attributes most influential to the matching decision, and finally predicts whether the records refer to the same real-world entity. In addition, we explore a debate-based strategy that contrasts supporting and opposing arguments to improve decision robustness. We evaluate our approaches against multiple existing baselines on several real-world entity matching benchmark datasets. Experimental results demonstrate that structured multi-step reasoning can improve matching performance in several cases, while also highlighting remaining challenges and opportunities for further refinement of reasoning-guided LLM approaches.

cs.DB↗

arXiv2025

Thermalization and Mpemba-like patterns in effective temperature dynamics of strongly coupled dissipative quantum chaotic systems

Anomalous thermalization, particularly the crossings of temperature trajectories from different initial states termed Mpemba crossings (MPCs), have intrigued scientists for decades. While recent studies in quantum systems suggest that initial conditions play a decisive role in its emergence, they offer limited insight into MPCs in complex, highly nonequilibrium systems. In this study, we investigate temperature dynamics in the strongly coupled, quantum chaotic Sachdev-Ye-Kitaev (SYK) model, which is dual to the low-energy dynamics of 2D dilaton gravity. Our findings reveal a dynamically driven nonequilibrium mechanism underlying MPCs during rapid thermalization, with implications for gravitational systems. We explore quench dynamics in SYK systems under three conditions: coupling to a single SYK thermal bath, coupling to two thermal baths at different temperatures, and dissipative SYKs modeled by the Lindblad equation. We find that strong system-bath coupling induces oscillating effective temperatures and trajectory crossings in transient states due to nonequilibrium statistics, phenomena absent in quasi-static thermodynamics and Lindbladian SYKs. These MPCs highlight a unique feature of anomalous thermalization of strongly coupled quantum chaotic systems driven far from equilibrium. Besides, the results also provide qualitative insights into the nonequilibrium thermodynamics of black holes strongly interacting with their environment, such as primordial black holes in the early universe.

quant-ph↗

arXiv2025

Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentation

Few-shot segmentation (FSS) aims to segment novel classes under the guidance of limited support samples by a meta-learning paradigm. Existing methods mainly mine references from support images as meta guidance. However, due to intra-class variations among visual representations, the meta information extracted from support images cannot produce accurate guidance to segment untrained classes. In this paper, we argue that the references from support images may not be essential, the key to the support role is to provide unbiased meta guidance for both trained and untrained classes. We then introduce a Language-Driven Attribute Generalization (LDAG) architecture to utilize inherent target property language descriptions to build robust support strategy. Specifically, to obtain an unbiased support representation, we design a Multi-attribute Enhancement (MaE) module, which produces multiple detailed attribute descriptions of the target class through Large Language Models (LLMs), and then builds refined visual-text prior guidance utilizing multi-modal matching. Meanwhile, due to text-vision modal shift, attribute text struggles to promote visual feature representation, we design a Multi-modal Attribute Alignment (MaA) to achieve cross-modal interaction between attribute texts and visual feature. Experiments show that our proposed method outperforms existing approaches by a clear margin and achieves the new state-of-the art performance. The code will be released.

cs.CV↗

arXiv2025

Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation

Few-shot segmentation has garnered significant attention. Many recent approaches attempt to introduce the Segment Anything Model (SAM) to handle this task. With the strong generalization ability and rich object-specific extraction ability of the SAM model, such a solution shows great potential in few-shot segmentation. However, the decoding process of SAM highly relies on accurate and explicit prompts, making previous approaches mainly focus on extracting prompts from the support set, which is insufficient to activate the generalization ability of SAM, and this design is easy to result in a biased decoding process when adapting to the unknown classes. In this work, we propose an Unbiased Semantic Decoding (USD) strategy integrated with SAM, which extracts target information from both the support and query set simultaneously to perform consistent predictions guided by the semantics of the Contrastive Language-Image Pre-training (CLIP) model. Specifically, to enhance the unbiased semantic discrimination of SAM, we design two feature enhancement strategies that leverage the semantic alignment capability of CLIP to enrich the original SAM features, mainly including a global supplement at the image level to provide a generalize category indicate with support image and a local guidance at the pixel level to provide a useful target location with query image. Besides, to generate target-focused prompt embeddings, a learnable visual-text target prompt generator is proposed by interacting target text embeddings and clip visual features. Without requiring re-training of the vision foundation models, the features with semantic discrimination draw attention to the target region through the guidance of prompt with rich target information.

cs.CV↗

arXiv2025

HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models

3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VLMs directly embed the 3D point clouds into 3D tokens, following large 2D-VLMs with powerful reasoning capabilities. However, this framework has a great computational cost limiting its application, where we identify that the bottleneck lies in processing all 3D tokens in the Large Language Model (LLM) part. This raises the question: how can we reduce the computational overhead introduced by 3D tokens while preserving the integrity of their essential information? To address this question, we introduce Hierarchical Compensatory Compression (HCC-3D) to efficiently compress 3D tokens while maintaining critical detail retention. Specifically, we first propose a global structure compression (GSC), in which we design global queries to compress all 3D tokens into a few key tokens while keeping overall structural information. Then, to compensate for the information loss in GSC, we further propose an adaptive detail mining (ADM) module that selectively recompresses salient but under-attended features through complementary scoring. Extensive experiments demonstrate that HCC-3D not only achieves extreme compression ratios (approximately 98%) compared to previous 3D-VLMs, but also achieves new state-of-the-art performance, showing the great improvements on both efficiency and performance.

cs.CV↗

arXiv2025

Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic Consistency

Cross-modal Knowledge Distillation has demonstrated promising performance on paired modalities with strong semantic connections, referred to as Symmetric Cross-modal Knowledge Distillation (SCKD). However, implementing SCKD becomes exceedingly constrained in real-world scenarios due to the limited availability of paired modalities. To this end, we investigate a general and effective knowledge learning concept under weak semantic consistency, dubbed Asymmetric Cross-modal Knowledge Distillation (ACKD), aiming to bridge modalities with limited semantic overlap. Nevertheless, the shift from strong to weak semantic consistency improves flexibility but exacerbates challenges in knowledge transmission costs, which we rigorously verified based on optimal transport theory. To mitigate the issue, we further propose a framework, namely SemBridge, integrating a Student-Friendly Matching module and a Semantic-aware Knowledge Alignment module. The former leverages self-supervised learning to acquire semantic-based knowledge and provide personalized instruction for each student sample by dynamically selecting the relevant teacher samples. The latter seeks the optimal transport path by employing Lagrangian optimization. To facilitate the research, we curate a benchmark dataset derived from two modalities, namely Multi-Spectral (MS) and asymmetric RGB images, tailored for remote sensing scene classification. Comprehensive experiments exhibit that our framework achieves state-of-the-art performance compared with 7 existing approaches on 6 different model architectures across various datasets.

cs.CV↗

arXiv2025

AnomalyAID: Reliable Interpretation for Semi-supervised Network Anomaly Detection

Semi-supervised Learning plays a crucial role in network anomaly detection applications, however, learning anomaly patterns with limited labeled samples is not easy. Additionally, the lack of interpretability creates key barriers to the adoption of semi-supervised frameworks in practice. Most existing interpretation methods are developed for supervised/unsupervised frameworks or non-security domains and fail to provide reliable interpretations. In this paper, we propose AnomalyAID, a general framework aiming to (1) make the anomaly detection process interpretable and improve the reliability of interpretation results, and (2) assign high-confidence pseudo labels to unlabeled samples for improving the performance of anomaly detection systems with limited supervised data. For (1), we propose a novel interpretation approach that leverages global and local interpreters to provide reliable explanations, while for (2), we design a new two-stage semi-supervised learning framework for network anomaly detection by aligning both stages' model predictions with special constraints. We apply AnomalyAID over two representative network anomaly detection tasks and extensively evaluate AnomalyAID with representative prior works. Experimental results demonstrate that AnomalyAID can provide accurate detection results with reliable interpretations for semi-supervised network anomaly detection systems.

cs.LG↗

arXiv2025

Accurate humidity and pH synchronized measurement with temperature compensation based on polarization maintaining fiber

Real-time and accurate monitoring of humidity and pH is of great significance in daily life and industrial production. Existing humidity and pH measurement suffer from limitations such as low sensitivity, signal crosstalk, complex system structures, and inability to achieve real-time monitoring. In this work, the surface of a polarization maintaining fiber (PMF) was functionalized with a composite humidity-sensitive polymer composed of polyvinyl alcohol (PVA) and carbon nanosheets (CNs). A humidity-sensitive film with a microporous structure was prepared on the PMF cladding through high-temperature rapid film formation and laser processing, enhancing humidity sensitivity and stability. To enable pH sensing, poly(allylamine hydrochloride) (PAH) and poly (acrylic acid) (PAA) were successively adsorbed onto the PMF surface via electrostatic self-assembly, forming a pH-sensitive nanofilm structure. By connecting a temperature-compensated PMF within the same Sagnac loop and combining it with a multi-wavelength matrix, simultaneous real-time monitoring of humidity, pH, and temperature was achieved, effectively solving the issue of temperature crosstalk and extending toward a universal optical fiber multi-parameter measurement platform.

physics.app-ph↗

arXiv2025

DMVFC: Deep Learning Based Functionally Consistent Tractography Fiber Clustering Using Multimodal Diffusion MRI and Functional MRI

Tractography fiber clustering using diffusion MRI (dMRI) is a crucial method for white matter (WM) parcellation to enable analysis of brains structural connectivity in health and disease. Current fiber clustering strategies primarily use the fiber geometric characteristics (i.e., the spatial trajectories) to group similar fibers into clusters, while neglecting the functional and microstructural information of the fiber tracts. There is increasing evidence that neural activity in the WM can be measured using functional MRI (fMRI), providing potentially valuable multimodal information for fiber clustering to enhance its functional coherence. Furthermore, microstructural features such as fractional anisotropy (FA) can be computed from dMRI as additional information to ensure the anatomical coherence of the clusters. In this paper, we develop a novel deep learning fiber clustering framework, namely Deep Multi-view Fiber Clustering (DMVFC), which uses joint multi-modal dMRI and fMRI data to enable functionally consistent WM parcellation. DMVFC can effectively integrate the geometric and microstructural characteristics of the WM fibers with the fMRI BOLD signals along the fiber tracts. DMVFC includes two major components: (1) a multi-view pretraining module to compute embedding features from each source of information separately, including fiber geometry, microstructure measures, and functional signals, and (2) a collaborative fine-tuning module to simultaneously refine the differences of embeddings. In the experiments, we compare DMVFC with two state-of-the-art fiber clustering methods and demonstrate superior performance in achieving functionally meaningful and consistent WM parcellation results.

eess.IV↗