arXiv subjects

Ran Zhang

Publications and source records attributed to Ran Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Zero-Shot Human Mobility Forecasting via Large Language Model with Hierarchical Reasoning

Human mobility forecasting is important for applications such as transportation planning, urban management, and personalized recommendations. However, existing methods often fail to generalize to unseen users or locations and struggle to capture dynamic intent due to limited labeled data and the complexity of mobility patterns. We propose ZHMF, a framework for zero-shot human mobility forecasting that combines a semantic enhanced retrieval and reflection mechanism with a hierarchical language model based reasoning system. The task is reformulated as a natural language question answering paradigm. Leveraging LLMs semantic understanding of user histories and context, our approach handles previously unseen prediction scenarios. We further introduce a hierarchical reflection mechanism for iterative reasoning and refinement by decomposing forecasting into an activity level planner and a location level selector, enabling collaborative modeling of long term user intentions and short term contextual preferences. Experiments on standard human mobility datasets show that our approach outperforms existing models. Ablation studies reveal the contribution of each module, and case studies illustrate how the method captures user intentions and adapts to diverse contextual scenarios.

cs.AI↗

arXiv2025

Energy-Equidistributed Moving Sampling Physics-informed Neural Networks for Solving Conservative Partial Differential Equations

This paper presents a novel Energy-Equidistributed adaptive sampling framework for multi-dimensional conservative PDEs, introducing both location-based and velocity-based formulations of Energy-Equidistributed moving mesh PDEs (EMMPDEs). The framework utilizes the energy density function as the monitor function, ensuring that mesh adaptation dynamically tracks energy evolution during temporal integration. These theoretical developments are integrated with deep neural networks to establish the Energy-Equidistributed Moving Sampling Physics-Informed Neural Networks (EEMS-PINNs), which integrate physics-informed learning with energy-adaptive mesh optimization. Extensive numerical experiments demonstrate that EEMS-PINNs effectively maintain solution accuracy in long-time simulations while preserving conserved energy. The framework's robustness is further evidenced by its stable performance in non-conservative systems. The code for this paper can be found at https://github.com/sufe-Ran-Zhang/EMMPDE.

math.NA↗

arXiv2025

Time-Aware Auto White Balance in Mobile Photography

Cameras rely on auto white balance (AWB) to correct undesirable color casts caused by scene illumination and the camera's spectral sensitivity. This is typically achieved using an illuminant estimator that determines the global color cast solely from the color information in the camera's raw sensor image. Mobile devices provide valuable additional metadata-such as capture timestamp and geolocation-that offers strong contextual clues to help narrow down the possible illumination solutions. This paper proposes a lightweight illuminant estimation method that incorporates such contextual metadata, along with additional capture information and image colors, into a compact model (~5K parameters), achieving promising results, matching or surpassing larger models. To validate our method, we introduce a dataset of 3,224 smartphone images with contextual metadata collected at various times of day and under diverse lighting conditions. The dataset includes ground-truth illuminant colors, determined using a color chart, and user-preferred illuminants validated through a user study, providing a comprehensive benchmark for AWB evaluation.

cs.CV↗

arXiv2025

Deblending Overlapping Galaxies in DECaLS Using Transformer-Based Algorithm: A Method Combining Multiple Bands and Data Types

In large-scale galaxy surveys, particularly deep ground-based photometric studies, galaxy blending is inevitable and poses a potential primary systematic uncertainty for upcoming surveys. Current deblenders predominantly rely on analytical modeling of galaxy profiles, facing limitations due to inflexible and imprecise models. We present a novel approach using a U-net structured transformer-based network for deblending astronomical images, which we term the CAT-deblender. It was trained using both RGB and grz-band images, spanning two distinct data formats from the Dark Energy Camera Legacy Survey (DECaLS) database, including galaxies with diverse morphologies. Our method requires only the approximate central coordinates of each target galaxy, bypassing assumptions on neighboring source counts. Post-deblending, our RGB images retain a high signal-to-noise peak, showing superior structural similarity to ground truth. For multi-band images, the ellipticity of central galaxies and median reconstruction error for the r-band consistently lie within +/-0.025 to +/-0.25, revealing minimal pixel residuals. In our comparison focused on flux recovery, our model shows a mere 1 percent error in magnitude recovery for quadruply blended galaxies, significantly outperforming SExtractor's higher error rate of 4.8 percent. By cross-matching with publicly accessible overlapping galaxy catalogs from the DECaLS database, we successfully deblended 433 overlapping galaxies. Furthermore, we demonstrated effective deblending of 63,733 blended galaxy images randomly selected from the DECaLS database.

astro-ph.GA↗

arXiv2025

DeepSeek-R1 vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?

Reasoning-enabled large language models (LLMs) excel in logical tasks, yet their utility for evaluating natural language generation remains unexplored. This study systematically compares reasoning LLMs with non-reasoning counterparts across machine translation and text summarization evaluation tasks. We evaluate eight models spanning state-of-the-art reasoning models (DeepSeek-R1, OpenAI o3), their distilled variants (8B-70B parameters), and equivalent non-reasoning LLMs. Experiments on WMT23 and SummEval benchmarks reveal architecture and task-dependent benefits: OpenAI o3-mini models show improved performance with increased reasoning on MT, while DeepSeek-R1 and generally underperforms compared to its non-reasoning variant except in summarization consistency evaluation. Correlation analysis demonstrates that reasoning token usage correlates with evaluation quality only in specific models, while almost all models generally allocate more reasoning tokens when identifying more quality issues. Distillation maintains reasonable performance up to 32B parameter models but degrades substantially at 8B scale. This work provides the first assessment of reasoning LLMs for NLG evaluation and comparison to non-reasoning models. We share our code to facilitate further research: https://github.com/NL2G/reasoning-eval.

cs.CL↗

arXiv2025

Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics

The rapid advancement of LLMs has led to the creation of diverse agentic systems in data analysis, utilizing LLMs' capabilities to improve insight generation and visualization. In this paper, we present an agentic system that automates the data-to-dashboard pipeline through modular LLM agents capable of domain detection, concept extraction, multi-perspective analysis generation, and iterative self-reflection. Unlike existing chart QA systems, our framework simulates the analytical reasoning process of business analysts by retrieving domain-relevant knowledge and adapting to diverse datasets without relying on closed ontologies or question templates. We evaluate our system on three datasets across different domains. Benchmarked against GPT-4o with a single-prompt baseline, our approach shows improved insightfulness, domain relevance, and analytical depth, as measured by tailored evaluation metrics and qualitative human assessment. This work contributes a novel modular pipeline to bridge the path from raw data to visualization, and opens new opportunities for human-in-the-loop validation by domain experts in business analytics. All code can be found here: https://github.com/77luvC/D2D_Data2Dashboard

cs.AI↗

arXiv2025

Distilling Textual Priors from LLM to Efficient Image Fusion

Multi-modality image fusion aims to synthesize a single, comprehensive image from multiple source inputs. Traditional approaches, such as CNNs and GANs, offer efficiency but struggle to handle low-quality or complex inputs. Recent advances in text-guided methods leverage large model priors to overcome these limitations, but at the cost of significant computational overhead, both in memory and inference time. To address this challenge, we propose a novel framework for distilling large model priors, eliminating the need for text guidance during inference while dramatically reducing model size. Our framework utilizes a teacher-student architecture, where the teacher network incorporates large model priors and transfers this knowledge to a smaller student network via a tailored distillation process. Additionally, we introduce spatial-channel cross-fusion module to enhance the model's ability to leverage textual priors across both spatial and channel dimensions. Our method achieves a favorable trade-off between computational efficiency and fusion quality. The distilled network, requiring only 10% of the parameters and inference time of the teacher network, retains 90% of its performance and outperforms existing SOTA methods. Extensive experiments demonstrate the effectiveness of our approach. The implementation will be made publicly available as an open-source resource.

cs.CV↗

arXiv2025

COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing

Zero-shot hashing (ZSH) has shown excellent success owing to its efficiency and generalization in large-scale retrieval scenarios. While considerable success has been achieved, there still exist urgent limitations. Existing works ignore the locality relationships of representations and attributes, which have effective transferability between seeable classes and unseeable classes. Also, the continuous-value attributes are not fully harnessed. In response, we conduct a COMprehensive Attribute Exploration for ZSH, named COMAE, which depicts the relationships from seen classes to unseen ones through three meticulously designed explorations, i.e., point-wise, pair-wise and class-wise consistency constraints. By regressing attributes from the proposed attribute prototype network, COMAE learns the local features that are relevant to the visual attributes. Then COMAE utilizes contrastive learning to comprehensively depict the context of attributes, rather than instance-independent optimization. Finally, the class-wise constraint is designed to cohesively learn the hash code, image representation, and visual attributes more effectively. Experimental results on the popular ZSH datasets demonstrate that COMAE outperforms state-of-the-art hashing techniques, especially in scenarios with a larger number of unseen label classes.

cs.CV↗

arXiv2025

Deep Cut-informed Graph Embedding and Clustering

Graph clustering aims to divide the graph into different clusters. The recently emerging deep graph clustering approaches are largely built on graph neural networks (GNN). However, GNN is designed for general graph encoding and there is a common issue of representation collapse in existing GNN-based deep graph clustering algorithms. We attribute two main reasons for such issues: (i) the inductive bias of GNN models: GNNs tend to generate similar representations for proximal nodes. Since graphs often contain a non-negligible amount of inter-cluster links, the bias results in error message passing and leads to biased clustering; (ii) the clustering guided loss function: most traditional approaches strive to make all samples closer to pre-learned cluster centers, which causes a degenerate solution assigning all data points to a single label thus making all samples similar and less discriminative. To address these challenges, we investigate graph clustering from a graph cut perspective and propose an innovative and non-GNN-based Deep Cut-informed Graph embedding and Clustering framework, namely DCGC. This framework includes two modules: (i) cut-informed graph encoding; (ii) self-supervised graph clustering via optimal transport. For the encoding module, we derive a cut-informed graph embedding objective to fuse graph structure and attributes by minimizing their joint normalized cut. For the clustering module, we utilize the optimal transport theory to obtain the clustering assignments, which can balance the guidance of "proximity to the pre-learned cluster center". With the above two tailored designs, DCGC is more suitable for the graph clustering task, which can effectively alleviate the problem of representation collapse and achieve better performance. We conduct extensive experiments to demonstrate that our method is simple but effective compared with benchmarks.

cs.LG↗

arXiv2025

Engineering-Oriented Design of Drift-Resilient MTJ Random Number Generator via Hybrid Control Strategies

Magnetic Tunnel Junctions (MTJs) have shown great promise as hardware sources for true random number generation (TRNG) due to their intrinsic stochastic switching behavior. However, practical deployment remains challenged by drift in switching probability caused by thermal fluctuations, device aging, and environmental instability. This work presents an engineering-oriented, drift-resilient MTJ-based TRNG architecture, enabled by a hybrid control strategy that combines self-stabilizing feedback with pulse width modulation. A key component is the Downcalibration-2 scheme, which updates the control parameter every two steps using only integer-resolution timing, ensuring excellent statistical quality without requiring bit discarding, pre-characterization, or external calibration. Extensive experimental measurements and numerical simulations demonstrate that this approach maintains stable randomness under dynamic temperature drift, using only simple digital logic. The proposed architecture offers high throughput, robustness, and scalability, making it well-suited for secure hardware applications, embedded systems, and edge computing environments.

physics.app-ph↗

arXiv2025

Trajectory Dispersion Control for Precision Landing Guidance of Reusable Rockets

This article is an engineering note, and formal abstract is omitted in accordance with the requirements of the journal. The main idea of this note is as follows. In endoatmospheric landing of reusable rockets, there exist various kinds of disturbances that can induce the trajectory dispersion. The trajectory dispersion propagates with flight time and ultimately determines landing accuracy. Therefore, to achieve high-precision landing, this note proposes a novel online trajectory dispersion control method. Based on a Parameterized Optimal Feedback Guidance Law (POFGL), two key components of the proposed method are designed: online trajectory dispersion prediction and real-time guidance parameter tuning for trajectory dispersion optimization. First, by formalizing a parameterized probabilistic disturbance model, the closed-loop trajectory dispersion under the POFGL is predicted online. Compared with the covariance control guidance method, a more accurate trajectory dispersion prediction is achieved by using generalized Polynomial Chaos (gPC) expansion and pseudospectral collocation methods. Second, to ensure computational efficiency, a gradient descent based real-time guidance parameter tuning law is designed to simultaneously optimize the performance index and meet the landing error dispersion constraint, which significantly reduces the conservativeness of guidance design compared with the robust trajectory optimization method. Numerical simulations indicate that the trajectory dispersion prediction method can achieve the same accuracy as the Monte Carlo method with smaller computational resource; the guidance parameter tuning law can improve the optimal performance index and meet the desired accuracy requirements through directly shaping the trajectory dispersion.

physics.space-ph↗

arXiv2025

Bayesian Reasoning Enabled by Spin-Orbit Torque Magnetic Tunnel Junctions

Bayesian networks play an increasingly important role in data mining, inference, and reasoning with the rapid development of artificial intelligence. In this paper, we present proof-of-concept experiments demonstrating the use of spin-orbit torque magnetic tunnel junctions (SOT-MTJs) in Bayesian network reasoning. Not only can the target probability distribution function (PDF) of a Bayesian network be precisely formulated by a conditional probability table as usual but also quantitatively parameterized by a probabilistic forward propagating neuron network. Moreover, the parameters of the network can also approach the optimum through a simple point-by point training algorithm, by leveraging which we do not need to memorize all historical data nor statistically summarize conditional probabilities behind them, significantly improving storage efficiency and economizing data pretreatment. Furthermore, we developed a simple medical diagnostic system using the SOT-MTJ as a random number generator and sampler, showcasing the application of SOT-MTJ-based Bayesian reasoning. This SOT-MTJ-based Bayesian reasoning shows great promise in the field of artificial probabilistic neural network, broadening the scope of spintronic device applications and providing an efficient and low-storage solution for complex reasoning tasks.

physics.app-ph↗

arXiv2025

Adaptive Movement Sampling Physics-Informed Residual Network (AM-PIRN) for Solving Nonlinear Option Pricing models

In this paper, we propose the Adaptive Movement Sampling Physics-Informed Residual Network (AM-PIRN) to address challenges in solving nonlinear option pricing PDE models, where solutions often exhibit significant curvature or shock waves over time. The AM-PIRN architecture is designed to concurrently minimize PDE residuals and achieve high-fidelity option price approximations by dynamically redistributing training points based on evolving PDE residuals, while maintaining a fixed total number of points. To enhance stability and training efficiency, we integrate a ResNet backbone, replacing conventional fully connected neural networks used in Physics-Informed Neural Networks (PINNs). Numerical experiments across nonlinear option pricing models demonstrate that AM-PIRN outperforms PINN, RAM-PINN, and WAM-PINN in both resolving PDE constraints and accurately estimating option prices. The method's advantages are particularly pronounced in complex or multi-dimensional models, where its adaptive sampling and robust architecture effectively mitigate challenges posed by sharp gradients and high nonlinearity.

cs.NI↗

arXiv2025

Weak Convergence Analysis for the Finite Element Approximation to Stochastic Allen-Cahn Equation Driven by Multiplicative White Noise

In this paper, we aim to study the optimal weak convergence order for the finite element approximation to a stochastic Allen-Cahn equation driven by multiplicative white noise. We first construct an auxiliary equation based on the splitting-up technique and derive prior estimates for the corresponding Kolmogorov equation and obtain the strong convergence order of 1 in time between the auxiliary and exact solutions. Then, we prove the optimal weak convergence order of the finite element approximation to the stochastic Allen-Cahn equation by deriving the weak convergence order between the finite element approximation and the auxiliary solution via the theory of Kolmogorov equation and Malliavin calculus. Finally, we present a numerical experiment to illustrate the theoretical analysis.

math.NA↗

arXiv2025

Graph-Guided Textual Explanation Generation Framework

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the model's internal reasoning process regarding its predicted answer. In contrast, highlight explanations--input fragments critical for the model's predicted answers--exhibit measurable faithfulness. Building on this foundation, we propose G-Tex, a Graph-Guided Textual Explanation Generation framework designed to enhance the faithfulness of NLEs. Specifically, highlight explanations are first extracted as faithful cues reflecting the model's reasoning logic toward answer prediction. They are subsequently encoded through a graph neural network layer to guide the NLE generation, which aligns the generated explanations with the model's underlying reasoning toward the predicted answer. Experiments on T5 and BART using three reasoning datasets show that G-Tex improves NLE faithfulness by up to 12.18% compared to baseline methods. Additionally, G-Tex generates NLEs with greater semantic and lexical similarity to human-written ones. Human evaluations show that G-Tex can decrease redundant content and enhance the overall quality of NLEs. Our work presents a novel method for explicitly guiding NLE generation to enhance faithfulness, serving as a foundation for addressing broader criteria in NLE and generated text.

cs.CL↗

arXiv2025

Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters

3D characters are essential to modern creative industries, but making them animatable often demands extensive manual work in tasks like rigging and skinning. Existing automatic rigging tools face several limitations, including the necessity for manual annotations, rigid skeleton topologies, and limited generalization across diverse shapes and poses. An alternative approach is to generate animatable avatars pre-bound to a rigged template mesh. However, this method often lacks flexibility and is typically limited to realistic human shapes. To address these issues, we present Make-It-Animatable, a novel data-driven method to make any 3D humanoid model ready for character animation in less than one second, regardless of its shapes and poses. Our unified framework generates high-quality blend weights, bones, and pose transformations. By incorporating a particle-based shape autoencoder, our approach supports various 3D representations, including meshes and 3D Gaussian splats. Additionally, we employ a coarse-to-fine representation and a structure-aware modeling strategy to ensure both accuracy and robustness, even for characters with non-standard skeleton structures. We conducted extensive experiments to validate our framework's effectiveness. Compared to existing methods, our approach demonstrates significant improvements in both quality and speed. More demos and code are available at https://jasongzy.github.io/Make-It-Animatable/.

cs.GR↗

arXiv2025

How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs

Recent research has focused on literary machine translation (MT) as a new challenge in MT. However, the evaluation of literary MT remains an open problem. We contribute to this ongoing discussion by introducing LITEVAL-CORPUS, a paragraph-level parallel corpus containing verified human translations and outputs from 9 MT systems, which totals over 2k translations and 13k evaluated sentences across four language pairs, costing 4.5k C. This corpus enables us to (i) examine the consistency and adequacy of human evaluation schemes with various degrees of complexity, (ii) compare evaluations by students and professionals, assess the effectiveness of (iii) LLM-based metrics and (iv) LLMs themselves. Our findings indicate that the adequacy of human evaluation is controlled by two factors: the complexity of the evaluation scheme (more complex is less adequate) and the expertise of evaluators (higher expertise yields more adequate evaluations). For instance, MQM (Multidimensional Quality Metrics), a complex scheme and the de facto standard for non-literary human MT evaluation, is largely inadequate for literary translation evaluation: with student evaluators, nearly 60% of human translations are misjudged as indistinguishable or inferior to machine translations. In contrast, BWS (BEST-WORST SCALING), a much simpler scheme, identifies human translations at a rate of 80-100%. Automatic metrics fare dramatically worse, with rates of at most 20%. Our overall evaluation indicates that published human translations consistently outperform LLM translations, where even the most recent LLMs tend to produce considerably more literal and less diverse translations compared to humans.

cs.CL↗

arXiv2025

Splitting finite element approximations for quasi-static electroporoelasticity equations

The electroporoelasticity model, which couples Maxwell's equations with Biot's equations, plays a critical role in applications such as water conservancy exploration, earthquake early warning, and various other fields. This work focuses on investigating its well-posedness and analyzing error estimates for a splitting backward Euler finite element method. We first define a weak solution consistent with the finite element framework. Then, we prove the uniqueness and existence of such a solution using the Galerkin method and derive a priori estimates for high-order regularity. Using a splitting technique, we define an approximate splitting solution and analyze its convergence order. Next, we apply Nedelec's curl-conforming finite elements, Lagrange elements, and the backward Euler method to construct a fully discretized scheme. We demonstrate the stability of the splitting numerical solution and provide error estimates for its convergence order in both temporal and spatial variables. Finally, we present numerical experiments to validate the theoretical results, showing that our method significantly reduces computational complexity compared to the classical finite element method.

math.NA↗