arXiv subjects

Han Zhang

Publications and source records attributed to Han Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2025

Instability in Diffusion ODEs: An Explanation for Inaccurate Image Reconstruction

Diffusion reconstruction plays a critical role in various applications such as image editing, restoration, and style transfer. In theory, the reconstruction should be simple - it just inverts and regenerates images by numerically solving the Probability Flow-Ordinary Differential Equation (PF-ODE). Yet in practice, noticeable reconstruction errors have been observed, which cannot be well explained by numerical errors. In this work, we identify a deeper intrinsic property in the PF-ODE generation process, the instability, that can further amplify the reconstruction errors. The root of this instability lies in the sparsity inherent in the generation distribution, which means that the probability is concentrated on scattered and small regions while the vast majority remains almost empty. To demonstrate the existence of instability and its amplification on reconstruction error, we conduct experiments on both toy numerical examples and popular open-sourced diffusion models. Furthermore, based on the characteristics of image data, we theoretically prove that the instability's probability converges to one as the data dimensionality increases. Our findings highlight the inherent challenges in diffusion-based reconstruction and can offer insights for future improvements.

cs.LG↗

arXiv2025

Foundation Model-Aided Deep Reinforcement Learning for RIS-Assisted Wireless Communication

Reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for enhancing wireless communication by dynamically controlling signal propagation in the environment. However, their efficient deployment relies on accurate channel state information (CSI), which leads to high channel estimation overhead due to their passive nature and the large number of reflective elements. In this work, we solve this challenge by proposing a novel framework that leverages a pre-trained open-source foundation model (FM) named large wireless model (LWM) to process wireless channels and generate versatile and contextualized channel embeddings. These embeddings are then used for the joint optimization of the BS beamforming and RIS configurations. To be more specific, for joint optimization, we design a deep reinforcement learning (DRL) model to automatically select the BS beamforming vector and RIS phase-shift matrix, aiming to maximize the spectral efficiency (SE). This work shows that a pre-trained FM for radio signal understanding can be fine-tuned and integrated with DRL for effective decision-making in wireless networks. It highlights the potential of modality-specific FMs in real-world network optimization. According to the simulation results, the proposed method outperforms the DRL-based approach and beam sweeping-based approach, achieving 9.89% and 43.66% higher SE, respectively.

eess.SP↗

arXiv2025

Conditional Denoising Diffusion for ISAC Enhanced Channel Estimation in Cell-Free 6G

Cell-free Integrated Sensing and Communication (ISAC) aims to revolutionize 6th Generation (6G) networks. By combining distributed access points with ISAC capabilities, it boosts spectral efficiency, situational awareness, and communication reliability. Channel estimation is a critical step in cell-free ISAC systems to ensure reliable communication, but its performance is usually limited by challenges such as pilot contamination and noisy channel estimates. This paper presents a novel framework leveraging sensing information as a key input within a Conditional Denoising Diffusion Model (CDDM). In this framework, we integrate CDDM with a Multimodal Transformer (MMT) to enhance channel estimation in ISAC-enabled cell-free systems. The MMT encoder effectively captures inter-modal relationships between sensing and location data, enabling the CDDM to iteratively denoise and refine channel estimates. Simulation results demonstrate that the proposed approach achieves significant performance gains. As compared with Least Squares (LS) and Minimum Mean Squared Error (MMSE) estimators, the proposed model achieves normalized mean squared error (NMSE) improvements of 8 dB and 9 dB, respectively. Moreover, we achieve a 27.8% NMSE improvement compared to the traditional denoising diffusion model (TDDM), which does not incorporate sensing channel information. Additionally, the model exhibits higher robustness against pilot contamination and maintains high accuracy under challenging conditions, such as low signal-to-noise ratios (SNRs). According to the simulation results, the model performs well for users near sensing targets by leveraging the correlation between sensing and communication channels.

eess.SP↗

arXiv2025

Mobile Traffic Prediction using LLMs with Efficient In-context Demonstration Selection

Mobile traffic prediction is an important enabler for optimizing resource allocation and improving energy efficiency in mobile wireless networks. Building on the advanced contextual understanding and generative capabilities of large language models (LLMs), this work introduces a context-aware wireless traffic prediction framework powered by LLMs. To further enhance prediction accuracy, we leverage in-context learning (ICL) and develop a novel two-step demonstration selection strategy, optimizing the performance of LLM-based predictions. The initial step involves selecting ICL demonstrations using the effectiveness rule, followed by a second step that determines whether the chosen demonstrations should be utilized, based on the informativeness rule. We also provide an analytical framework for both informativeness and effectiveness rules. The effectiveness of the proposed framework is demonstrated with a real-world fifth-generation (5G) dataset with different application scenarios. According to the numerical results, the proposed framework shows lower mean squared error and higher R2-Scores compared to the zero-shot prediction method and other demonstration selection methods, such as constant ICL demonstration selection and distance-only-based ICL demonstration selection.

cs.NI↗

arXiv2025

VChatter: Exploring Generative Conversational Agents for Simulating Exposure Therapy to Reduce Social Anxiety

Many people struggle with social anxiety, feeling fear, or even physically uncomfortable in social situations like talking to strangers. Exposure therapy, a clinical method that gradually and repeatedly exposes individuals to the source of their fear and helps them build coping mechanisms, can reduce social anxiety but traditionally requires human therapists' guidance and constructions of situations. In this paper, we developed a multi-agent system VChatter to explore large language models(LLMs)-based conversational agents for simulating exposure therapy with users. Based on a survey study (N=36) and an expert interview, VChatter includes an Agent-P, which acts as a psychotherapist to design the exposure therapy plans for users, and two Agent-Hs, which can take on different interactive roles in low, medium, and high exposure scenarios. A six-day qualitative study (N=10) showcases VChatter's usefulness in reducing users' social anxiety, feelings of isolation, and avoidance of social interactions. We demonstrated the feasibility of using LLMs-based conversational agents to simulate exposure therapy for addressing social anxiety and discussed future concerns for designing agents tailored to social anxiety.

cs.HC↗

arXiv2025

Epsilon-VAE: Denoising as Visual Decoding

In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for high-quality generation. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. In this work, we offer a new perspective by proposing denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder. We evaluate our approach by assessing both reconstruction (rFID) and generation quality (FID), comparing it to state-of-the-art autoencoding approaches. By adopting iterative reconstruction through diffusion, our autoencoder, namely Epsilon-VAE, achieves high reconstruction quality, which in turn enhances downstream generation quality by 22% at the same compression rates or provides 2.3x inference speedup through increasing compression rates. We hope this work offers new insights into integrating iterative generation and autoencoding for improved compression and generation.

cs.CV↗

arXiv2025

Optimization-Based Trajectory Planning for Tractor-Trailer Vehicles on Curvy Roads: A Progressively Increasing Sampling Number Method

In this work, we propose an optimization-based trajectory planner for tractor-trailer vehicles on curvy roads. The lack of analytical expression for the trailer's errors to the center line pose a great challenge to the trajectory planning for tractor-trailer vehicles. To address this issue, we first use geometric representations to characterize the lateral and orientation errors in Cartesian frame, where the errors would serve as the components of the cost function and the road edge constraints within our optimization process. Next, we generate a coarse trajectory to warm-start the subsequent optimization problems. On the other hand, to achieve a good approximation of the continuous-time kinematics, optimization-based methods usually discretize the kinematics with a large sampling number. This leads to an increase in the number of the variables and constraints, thus making the optimization problem difficult to solve. To address this issue, we design a Progressively Increasing Sampling Number Optimization (PISNO) framework. More specifically, we first find a nearly feasible trajectory with a small sampling number to warm-start the optimization process. Then, the sampling number is progressively increased, and the corresponding intermediate Optimal Control Problem (OCP) is solved in each iteration. Next, we further resample the obtained solution into a finer sampling period, and then use it to warm-start the intermediate OCP in next iteration. This process is repeated until reaching a threshold sampling number. Simulation and experiment results show the proposed method exhibits a good performance and less computational consumption over the benchmarks.

cs.RO↗

arXiv2025

Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks

To enhance the reliability and credibility of graph neural networks (GNNs) and improve the transparency of their decision logic, a new field of explainability of GNNs (XGNN) has emerged. However, two major limitations severely degrade the performance and hinder the generalizability of existing XGNN methods: they (a) fail to capture the complete decision logic of GNNs across diverse distributions in the entire dataset's sample space, and (b) impose strict prerequisites on edge properties and GNN internal accessibility. To address these limitations, we propose OPEN, a novel c\textbf{O}mprehensive and \textbf{P}rerequisite-free \textbf{E}xplainer for G\textbf{N}Ns. OPEN, as the first work in the literature, can infer and partition the entire dataset's sample space into multiple environments, each containing graphs that follow a distinct distribution. OPEN further learns the decision logic of GNNs across different distributions by sampling subgraphs from each environment and analyzing their predictions, thus eliminating the need for strict prerequisites. Experimental results demonstrate that OPEN captures nearly complete decision logic of GNNs, outperforms state-of-the-art methods in fidelity while maintaining similar efficiency, and enhances robustness in real-world scenarios.

cs.LG↗

arXiv2025

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models

Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks. However, traditional AES systems face three major challenges: (1) reliance on handcrafted features that limit generalizability, (2) difficulty in capturing fine-grained traits like coherence and argumentation, and (3) inability to handle multimodal contexts. In the era of Multimodal Large Language Models (MLLMs), we propose EssayJudge, the first multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits. By leveraging MLLMs' strengths in trait-specific scoring and multimodal context understanding, EssayJudge aims to offer precise, context-rich evaluations without manual feature engineering, addressing longstanding AES limitations. Our experiments with 18 representative MLLMs reveal gaps in AES performance compared to human evaluation, particularly in discourse-level traits, highlighting the need for further advancements in MLLM-based AES research.

cs.CL↗

arXiv2025

CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring

Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments. However, traditional AES methods struggle with evaluation generalizability and multimodal perception, while even recent Multimodal Large Language Model (MLLM)-based approaches can produce hallucinated justifications and scores misaligned with human judgment. To address the limitations, we introduce CAFES, the first collaborative multi-agent framework specifically designed for AES. It orchestrates three specialized agents: an Initial Scorer for rapid, trait-specific evaluations; a Feedback Pool Manager to aggregate detailed, evidence-grounded strengths; and a Reflective Scorer that iteratively refines scores based on this feedback to enhance human alignment. Extensive experiments, using state-of-the-art MLLMs, achieve an average relative improvement of 21% in Quadratic Weighted Kappa (QWK) against ground truth, especially for grammatical and lexical diversity. Our proposed CAFES framework paves the way for an intelligent multimodal AES system. The code will be available upon acceptance.

cs.CL↗

arXiv2025

SMFusion: Semantic-Preserving Fusion of Multimodal Medical Images for Enhanced Clinical Diagnosis

Multimodal medical image fusion plays a crucial role in medical diagnosis by integrating complementary information from different modalities to enhance image readability and clinical applicability. However, existing methods mainly follow computer vision standards for feature extraction and fusion strategy formulation, overlooking the rich semantic information inherent in medical images. To address this limitation, we propose a novel semantic-guided medical image fusion approach that, for the first time, incorporates medical prior knowledge into the fusion process. Specifically, we construct a publicly available multimodal medical image-text dataset, upon which text descriptions generated by BiomedGPT are encoded and semantically aligned with image features in a high-dimensional space via a semantic interaction alignment module. During this process, a cross attention based linear transformation automatically maps the relationship between textual and visual features to facilitate comprehensive learning. The aligned features are then embedded into a text-injection module for further feature-level fusion. Unlike traditional methods, we further generate diagnostic reports from the fused images to assess the preservation of medical information. Additionally, we design a medical semantic loss function to enhance the retention of textual cues from the source images. Experimental results on test datasets demonstrate that the proposed method achieves superior performance in both qualitative and quantitative evaluations while preserving more critical medical information.

cs.CV↗

arXiv2025

Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction

Under extreme operating conditions, characterized by high particle multiplicity and heavily overlapping shower energy deposits, classical particle flow algorithms encounter pronounced limitations in resolution, efficiency, and accuracy. To address this challenge, this paper proposes and systematically evaluates a deep learning reconstruction framework: For multichannel sparse features, we design a hybrid loss function combining weighted mean squared error with structural similarity index, effectively balancing pixel-level accuracy and structural fidelity. By integrating 3D convolutions, Squeeze-and-Excitation channel attention, and Offset self-attention modules into baseline convolutional neural networks, we enhance the model's capability to capture cross-modal spatiotemporal correlations and energy-displacement nonlinearities. Validated on custom-constructed simulation data and Pythia jet datasets, the framework's 90K-parameter lightweight variant approaches the performance of 5M-parameter baselines, while the 25M-parameter 3D model achieves state-of-the-art results in both interpolation and extrapolation tasks. Comprehensive experiments quantitatively evaluate component contributions and provide performance-parameter trade-off guidelines. All core code and data processing scripts are open-sourced on a GitHub repository to facilitate community reproducibility and extension.

physics.ins-det↗

arXiv2025

Large-area topological wireless power transfer

Topological wireless power transfer (WPT) technologies have attracted considerable interest due to their high transmission efficiency and robustness in coupled array configurations. However, conventional periodic and quasi-periodic topological chains exhibit limited adaptability in complex application scenarios, such as large-area simultaneous multi-load charging. In this work, we experimentally demonstrate a large-area topological defect state by constructing a gapless chain of uniformly coupled resonators at the interface of two topologically distinct Su-Schrieffer-Heeger (SSH) configurations. This topological defect state exhibits strong localization at multiple target sites, enabling efficient and concurrent wireless power delivery to spatially distributed loads. Furthermore, the unique wavefunction distribution enhances robustness against positional variations, ensuring stable energy transfer despite fluctuations in device placement. The proposed large-area topological framework offers fundamental insights into harnessing diverse topological states for advanced WPT applications, particularly in scenarios demanding spatial flexibility and multi-target energy delivery.

physics.app-ph↗

arXiv2025

Towards Human-Centered Early Prediction Models for Academic Performance in Real-World Contexts

Supporting student success requires collaboration among multiple stakeholders. Researchers have explored machine learning models for academic performance prediction; yet key challenges remain in ensuring these models are interpretable, equitable, and actionable within real-world educational support systems. First, many models prioritize predictive accuracy but overlook human-centered machine learning principles, limiting trust among students and reducing their usefulness for educators and institutional decision-makers. Second, most models require at least a month of data before making reliable predictions, delaying opportunities for early intervention. Third, current models primarily rely on sporadically collected, classroom-derived data, missing broader behavioral patterns that could provide more continuous and actionable insights. To address these gaps, we present three modeling approaches-LR, 1D-CNN, and MTL-1D-CNN-to classify students as low or high academic performers. We evaluate them based on explainability, fairness, and generalizability to assess their alignment with key social values. Using behavioral and self-reported data collected within the first week of two Spring terms, we demonstrate that these models can identify at-risk students as early as week one. However, trade-offs across human-centered machine learning principles highlight the complexity of designing predictive models that effectively support multi-stakeholder decision-making and intervention strategies. We discuss these trade-offs and their implications for different stakeholders, outlining how predictive models can be integrated into student support systems. Finally, we examine broader socio-technical challenges in deploying these models and propose future directions for advancing human-centered, collaborative academic prediction systems.

cs.HC↗

arXiv2025

Intelligent Attacks and Defense Methods in Federated Learning-enabled Energy-Efficient Wireless Networks

Federated learning (FL) is a promising technique for learning-based functions in wireless networks, thanks to its distributed implementation capability. On the other hand, distributed learning may increase the risk of exposure to malicious attacks where attacks on a local model may spread to other models by parameter exchange. Meanwhile, such attacks can be hard to detect due to the dynamic wireless environment, especially considering local models can be heterogeneous with non-independent and identically distributed (non-IID) data. Therefore, it is critical to evaluate the effect of malicious attacks and develop advanced defense techniques for FL-enabled wireless networks. In this work, we introduce a federated deep reinforcement learning-based cell sleep control scenario that enhances the energy efficiency of the network. We propose multiple intelligent attacks targeting the learning-based approach and we propose defense methods to mitigate such attacks. In particular, we have designed two attack models, generative adversarial network (GAN)-enhanced model poisoning attack and regularization-based model poisoning attack. As a counteraction, we have proposed two defense schemes, autoencoder-based defense, and knowledge distillation (KD)-enabled defense. The autoencoder-based defense method leverages an autoencoder to identify the malicious participants and only aggregate the parameters of benign local models during the global aggregation, while KD-based defense protects the model from attacks by controlling the knowledge transferred between the global model and local models.

cs.LG↗

arXiv2025

Fast Higher-Order Interpolation and Restriction in ExaHyPE Avoiding Non-physical Reflections

Wave equations help us to understand phenomena ranging from earthquakes to tsunamis. These phenomena materialise over very large scales. It would be computationally infeasible to track them over a regular mesh. Yet, since the phenomena are localised, adaptive mesh refinement (AMR) can be used to construct meshes with a higher resolution close to the regions of interest. ExaHyPE is a software engine created to solve wave problems using AMR, and we use it as baseline to construct our numerical relativity application called ExaGRyPE. To advance the mesh in time, we have to interpolate and restrict along resolution transitions in each and every time step. ExaHyPE's vanilla code version uses a d-linear tensor-product approach. In benchmarks of a stationary black hole this performs slowly and leads to errors in conserved quantities near AMR boundaries. We therefore introduce a set of higher-order interpolation schemes where the derivatives are calculated at each coarse grid cell to approximate the enclosed fine cells. The resulting methods run faster than the tensor-product approach. Most importantly, when running the stationary black hole simulation using the higher order methods the errors near the AMR boundaries are removed.

cs.CE↗

arXiv2025

HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations

Image retargeting aims to change the aspect-ratio of an image while maintaining its content and structure with less visual artifacts. Existing methods still generate many artifacts or fail to maintain original content or structure. To address this, we introduce HALO, an end-to-end trainable solution for image retargeting. Since humans are more sensitive to distortions in salient areas than non-salient areas of an image, HALO decomposes the input image into salient/non-salient layers and applies different wrapping fields to different layers. To further minimize the structure distortion in the output images, we propose perceptual structure similarity loss which measures the structure similarity between input and output images and aligns with human perception. Both quantitative results and a user study on the RetargetMe dataset show that HALO achieves SOTA. Especially, our method achieves an 18.4% higher user preference compared to the baselines on average.

cs.CV↗

arXiv2025

VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices

Many Internet-of-Things (IoT) devices rely on cloud computation resources to perform machine learning inferences. This is expensive and may raise privacy concerns for users. Consumers of these devices often have hardware such as gaming consoles and PCs with graphics accelerators that are capable of performing these computations, which may be left idle for significant periods of time. While this presents a compelling potential alternative to cloud offloading, concerns about the integrity of inferences, the confidentiality of model parameters, and the privacy of users' data mean that device vendors may be hesitant to offload their inferences to a platform managed by another manufacturer. We propose VeriSplit, a framework for offloading machine learning inferences to locally-available devices that address these concerns. We introduce masking techniques to protect data privacy and model confidentiality, and a commitment-based verification protocol to address integrity. Unlike much prior work aimed at addressing these issues, our approach does not rely on computation over finite field elements, which may interfere with floating-point computation supports on hardware accelerators and require modification to existing models. We implemented a prototype of VeriSplit and our evaluation results show that, compared to performing computation locally, our secure and private offloading solution can reduce inference latency by 28%--83%.

cs.CR↗