arXiv subjects

Yuhan Wang

Publications and source records attributed to Yuhan Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Point Cloud Neural Operator for Parametric PDEs on Complex and Variable Geometries

Surrogate models are critical for accelerating computationally expensive simulations in science and engineering, particularly for solving parametric partial differential equations (PDEs). Developing practical surrogate models poses significant challenges, particularly in handling geometrically complex and variable domains, which are often discretized as point clouds. In this work, we systematically investigate the formulation of neural operators -- maps between infinite-dimensional function spaces -- on point clouds to better handle complex and variable geometries while mitigating discretization effects. We introduce the Point Cloud Neural Operator (PCNO), designed to efficiently approximate solution maps of parametric PDEs on such domains. We evaluate the performance of PCNO on a range of pedagogical PDE problems, focusing on aspects such as boundary layers, adaptively meshed point clouds, and variable domains with topological variations. Its practicality is further demonstrated through three-dimensional applications, such as predicting pressure loads on various vehicle types and simulating the inflation process of intricate parachute structures.

math.NA↗

arXiv2025

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis

Customizable multilingual zero-shot singing voice synthesis (SVS) has various potential applications in music composition and short video dubbing. However, existing SVS models overly depend on phoneme and note boundary annotations, limiting their robustness in zero-shot scenarios and producing poor transitions between phonemes and notes. Moreover, they also lack effective multi-level style control via diverse prompts. To overcome these challenges, we introduce TCSinger 2, a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts. TCSinger 2 mainly includes three key modules: 1) Blurred Boundary Content (BBC) Encoder, predicts duration, extends content embedding, and applies masking to the boundaries to enable smooth transitions. 2) Custom Audio Encoder, uses contrastive learning to extract aligned representations from singing, speech, and textual prompts. 3) Flow-based Custom Transformer, leverages Cus-MOE, with F0 supervision, enhancing both the synthesis quality and style modeling of the generated singing voice. Experimental results show that TCSinger 2 outperforms baseline models in both subjective and objective metrics across multiple related tasks. Singing voice samples are available at https://aaronz345.github.io/TCSinger2Demo/.

eess.AS↗

arXiv2025

Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models

Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to select useful tools from large toolsets is a critical initial step. However, the performance of IR models in tool retrieval tasks remains underexplored and unclear. Most tool-use benchmarks simplify this step by manually pre-annotating a small set of relevant tools for each task, which is far from the real-world scenarios. In this paper, we propose ToolRet, a heterogeneous tool retrieval benchmark comprising 7.6k diverse retrieval tasks, and a corpus of 43k tools, collected from existing datasets. We benchmark six types of models on ToolRet. Surprisingly, even the models with strong performance in conventional IR benchmarks, exhibit poor performance on ToolRet. This low retrieval quality degrades the task pass rate of tool-use LLMs. As a further step, we contribute a large-scale training dataset with over 200k instances, which substantially optimizes the tool retrieval ability of IR models.

cs.CL↗

arXiv2025

Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays

Unsupervised anomaly detection (UAD) in medical imaging is crucial for identifying pathological abnormalities without requiring extensive labeled data. However, existing diffusion-based UAD models rely solely on imaging features, limiting their ability to distinguish between normal anatomical variations and pathological anomalies. To address this, we propose Diff3M, a multi-modal diffusion-based framework that integrates chest X-rays and structured Electronic Health Records (EHRs) for enhanced anomaly detection. Specifically, we introduce a novel image-EHR cross-attention module to incorporate structured clinical context into the image generation process, improving the model's ability to differentiate normal from abnormal features. Additionally, we develop a static masking strategy to enhance the reconstruction of normal-like images from anomalies. Extensive evaluations on CheXpert and MIMIC-CXR/IV demonstrate that Diff3M achieves state-of-the-art performance, outperforming existing UAD methods in medical imaging. Our code is available at this http URL https://github.com/nth221/Diff3M

cs.CV↗

arXiv2025

The Atacama Cosmology Telescope: Quantifying Atmospheric Emission above Cerro Toco

At frequencies below 1 Hz, fluctuations in atmospheric emission in the Chajnantor region in northern Chile are the primary source of interference for bolometric millimeter-wave observations. This paper focuses on characterizing these fluctuations using measurements from the Atacama Cosmology Telescope (ACT) and the Atacama Pathfinder Experiment (APEX) water vapor radiometer. We show that the total precipitable water vapor (PWV) is not in general an accurate estimator of the level of fluctuations in millimeter-wave atmospheric emission. We also show that the microwave frequency spectrum of atmospheric fluctuations is in good agreement with predictions by the am code for frequency bands above 90 GHz. We introduce a new method for separating atmospheric and systematic fluctuations, allowing us to fit a robust atmospheric flatfield, as well as to study in the atmosphere in greater detail than previous works. We present a direct measurement of the temporal outer scale of turbulence of $τ_0\approx50$ s corresponding to a spatial scale of $L_0\approx500$ m. Lastly, we show the variance of fluctuations in ACT's mm-wave bands correlate with the variance of fluctuations in PWV measured by APEX, even though the observatories are $6$ km apart and observe different lines of sight.

astro-ph.IM↗

arXiv2025

Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model

The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e.g., MSE and PSNR) and perceptual quality. Recent research has increasingly concentrated on evaluating denoising algorithms within the DP framework. However, existing algorithms either prioritize perceptual quality by sacrificing acceptable distortion, or focus on minimizing MSE for faithful restoration. When the goal shifts or noisy measurements vary, adapting to different points on the DP plane needs retraining or even re-designing the model. Inspired by recent advances in solving inverse problems using score-based generative models, we explore the potential of flexibly and optimally traversing DP tradeoffs using a single pre-trained score-based model. Specifically, we introduce a variance-scaled reverse diffusion process and theoretically characterize the marginal distribution. We then prove that the proposed sample process is an optimal solution to the DP tradeoff for conditional Gaussian distribution. Experimental results on two-dimensional and image datasets illustrate that a single score network can effectively and flexibly traverse the DP tradeoff for general denoising problems.

cs.CV↗

arXiv2025

LL4G: Self-Supervised Dynamic Optimization for Graph-Based Personality Detection

Graph-based personality detection constructs graph structures from textual data, particularly social media posts. Current methods often struggle with sparse or noisy data and rely on static graphs, limiting their ability to capture dynamic changes between nodes and relationships. This paper introduces LL4G, a self-supervised framework leveraging large language models (LLMs) to optimize graph neural networks (GNNs). LLMs extract rich semantic features to generate node representations and to infer explicit and implicit relationships. The graph structure adaptively adds nodes and edges based on input data, continuously optimizing itself. The GNN then uses these optimized representations for joint training on node reconstruction, edge prediction, and contrastive learning tasks. This integration of semantic and structural information generates robust personality profiles. Experimental results on Kaggle and Pandora datasets show LL4G outperforms state-of-the-art models.

cs.CL↗

arXiv2025

Dexterous Non-Prehensile Manipulation for Ungraspable Object via Extrinsic Dexterity

Objects with large base areas become ungraspable when they exceed the end-effector's maximum aperture. Existing approaches address this limitation through extrinsic dexterity, which exploits environmental features for non-prehensile manipulation. While grippers have shown some success in this domain, dexterous hands offer superior flexibility and manipulation capabilities that enable richer environmental interactions, though they present greater control challenges. Here we present ExDex, a dexterous arm-hand system that leverages reinforcement learning to enable non-prehensile manipulation for grasping ungraspable objects. Our system learns two strategic manipulation sequences: relocating objects from table centers to edges for direct grasping, or to walls where extrinsic dexterity enables grasping through environmental interaction. We validate our approach through extensive experiments with dozens of diverse household objects, demonstrating both superior performance and generalization capabilities with novel objects. Furthermore, we successfully transfer the learned policies from simulation to a real-world robot system without additional training, further demonstrating its applicability in real-world scenarios. Project website: https://tangty11.github.io/ExDex/.

cs.RO↗

arXiv2025

A Data Balancing and Ensemble Learning Approach for Credit Card Fraud Detection

This research introduces an innovative method for identifying credit card fraud by combining the SMOTE-KMEANS technique with an ensemble machine learning model. The proposed model was benchmarked against traditional models such as logistic regression, decision trees, random forests, and support vector machines. Performance was evaluated using metrics, including accuracy, recall, and area under the curve (AUC). The results demonstrated that the proposed model achieved superior performance, with an AUC of 0.96 when combined with the SMOTE-KMEANS algorithm. This indicates a significant improvement in detecting fraudulent transactions while maintaining high precision and recall. The study also explores the application of different oversampling techniques to enhance the performance of various classifiers. The findings suggest that the proposed method is robust and effective for classification tasks on balanced datasets. Future research directions include further optimization of the SMOTE-KMEANS approach and its integration into existing fraud detection systems to enhance financial security and consumer protection.

cs.LG↗

arXiv2025

Causal invariant geographic network representations with feature and structural distribution shifts

The existing methods learn geographic network representations through deep graph neural networks (GNNs) based on the i.i.d. assumption. However, the spatial heterogeneity and temporal dynamics of geographic data make the out-of-distribution (OOD) generalisation problem particularly salient. The latter are particularly sensitive to distribution shifts (feature and structural shifts) between testing and training data and are the main causes of the OOD generalisation problem. Spurious correlations are present between invariant and background representations due to selection biases and environmental effects, resulting in the model extremes being more likely to learn background representations. The existing approaches focus on background representation changes that are determined by shifts in the feature distributions of nodes in the training and test data while ignoring changes in the proportional distributions of heterogeneous and homogeneous neighbour nodes, which we refer to as structural distribution shifts. We propose a feature-structure mixed invariant representation learning (FSM-IRL) model that accounts for both feature distribution shifts and structural distribution shifts. To address structural distribution shifts, we introduce a sampling method based on causal attention, encouraging the model to identify nodes possessing strong causal relationships with labels or nodes that are more similar to the target node. Inspired by the Hilbert-Schmidt independence criterion, we implement a reweighting strategy to maximise the orthogonality of the node representations, thereby mitigating the spurious correlations among the node representations and suppressing the learning of background representations. Our experiments demonstrate that FSM-IRL exhibits strong learning capabilities on both geographic and social network datasets in OOD scenarios.

cs.LG↗

arXiv2025

The Atacama Cosmology Telescope: DR6 Maps

We present Atacama Cosmology Telescope (ACT) Data Release 6 (DR6) maps of the Cosmic Microwave Background temperature and polarization anisotropy at arcminute resolution over three frequency bands centered on 98, 150 and 220 GHz. The maps are based on data collected with the AdvancedACT camera over the period 2017--2022 and cover 19,000 square degrees with a median combined depth of 10 uK arcmin. We describe the instrument, mapmaking and map properties and illustrate them with a number of figures and tables. The ACT DR6 maps and derived products are available on LAMBDA at https://lambda.gsfc.nasa.gov/product/act/actadv_prod_table.html. We also provide an interactive web atlas at https://phy-act1.princeton.edu/public/snaess/actpol/dr6/atlas and HiPS data sets in Aladin (e.g. https://alasky.cds.unistra.fr/ACT/DR4DR6/color_CMB).

astro-ph.CO↗

arXiv2025

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

Multiview diffusion models have shown considerable success in image-to-3D generation for general objects. However, when applied to human data, existing methods have yet to deliver promising results, largely due to the challenges of scaling multiview attention to higher resolutions. In this paper, we explore human multiview diffusion models at the megapixel level and introduce a solution called mesh attention to enable training at 1024x1024 resolution. Using a clothed human mesh as a central coarse geometric representation, the proposed mesh attention leverages rasterization and projection to establish direct cross-view coordinate correspondences. This approach significantly reduces the complexity of multiview attention while maintaining cross-view consistency. Building on this foundation, we devise a mesh attention block and combine it with keypoint conditioning to create our human-specific multiview diffusion model, MEAT. In addition, we present valuable insights into applying multiview human motion videos for diffusion training, addressing the longstanding issue of data scarcity. Extensive experiments show that MEAT effectively generates dense, consistent multiview human images at the megapixel level, outperforming existing multiview diffusion methods.

cs.CV↗

arXiv2025

Modern nuclear and astrophysical constraints of dense matter in a renormalized chiral approach

We explore the Quantum Chromodynamics (QCD) phase diagram's complexities, including quark deconfinement transitions, liquid-gas phase changes, and critical points, using the chiral mean-field (CMF) model that is able to capture all these features. We introduce a vector meson renormalization within the CMF framework, enabling precise adjustments of meson masses and coupling strengths related to vector meson interactions. Performing a new fit to the deconfinement potential, we are able to replicate recent lattice QCD results, low energy nuclear physics properties, neutron star observational data, and key phase diagram features as per modern constraints. This approach enhances our understanding of vector mesons' roles in mediating nuclear interactions and their impact on the equation of state, contributing to a more comprehensive understanding of the QCD phase diagram and its implications for nuclear and astrophysical phenomena.

nucl-th↗

arXiv2025

Interacting mesons as degrees of freedom in a chiral model

We study the equation of state of hot and dense hadronic matter using an extended Chiral Mean Field (CMF) model framework where the addition is the inclusion of interactions of thermally excited mesons. This is implemented by calculating the in-medium masses of pseudoscalar and vector mesons, obtained through the explicit chiral symmetry-breaking and vector interaction terms in the Lagrangian, respectively, prior to applying the mean-field approximation. As a result, the in-medium meson contributions generate a feedback term to the CMF's equations of motion, which then modifies the equation of state. With this improvement, we quantify the effect on the equation of state of strongly interacting matter through comparisons with state-of-the-art lattice QCD results and other hadronic models like the Hadron Resonance Gas model. We find that the results of the updated hadronic CMF model with an improved meson description (mCMF) provide a better agreement with lattice-QCD data for thermodynamic state variables across a wide range of temperatures and baryon chemical potentials.

nucl-th↗

arXiv2025

IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filter

3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance. Existing 3D MOT methods based on the Tracking-by-Detection framework typically use a single motion model to track an object throughout its entire tracking process. However, objects may change their motion patterns due to variations in the surrounding environment. In this paper, we introduce the Interacting Multiple Model filter in IMM-MOT, which accurately fits the complex motion patterns of individual objects, overcoming the limitation of single-model tracking in existing approaches. In addition, we incorporate a Damping Window mechanism into the trajectory lifecycle management, leveraging the continuous association status of trajectories to control their creation and termination, reducing the occurrence of overlooked low-confidence true targets. Furthermore, we propose the Distance-Based Score Enhancement module, which enhances the differentiation between false positives and true positives by adjusting detection scores, thereby improving the effectiveness of the Score Filter. On the NuScenes Val dataset, IMM-MOT outperforms most other single-modal models using 3D point clouds, achieving an AMOTA of 73.8%. Our project is available at https://github.com/Ap01lo/IMM-MOT.

cs.CV↗

arXiv2025

Neuro-Conceptual Artificial Intelligence: Integrating OPM with Deep Learning to Enhance Question Answering Quality

Knowledge representation and reasoning are critical challenges in Artificial Intelligence (AI), particularly in integrating neural and symbolic approaches to achieve explainable and transparent AI systems. Traditional knowledge representation methods often fall short of capturing complex processes and state changes. We introduce Neuro-Conceptual Artificial Intelligence (NCAI), a specialization of the neuro-symbolic AI approach that integrates conceptual modeling using Object-Process Methodology (OPM) ISO 19450:2024 with deep learning to enhance question-answering (QA) quality. By converting natural language text into OPM models using in-context learning, NCAI leverages the expressive power of OPM to represent complex OPM elements-processes, objects, and states-beyond what traditional triplet-based knowledge graphs can easily capture. This rich structured knowledge representation improves reasoning transparency and answer accuracy in an OPM-QA system. We further propose transparency evaluation metrics to quantitatively measure how faithfully the predicted reasoning aligns with OPM-based conceptual logic. Our experiments demonstrate that NCAI outperforms traditional methods, highlighting its potential for advancing neuro-symbolic AI by providing rich knowledge representations, measurable transparency, and improved reasoning.

cs.CL↗

arXiv2025

A Deep Learning Framework Integrating CNN and BiLSTM for Financial Systemic Risk Analysis and Prediction

This study proposes a deep learning model based on the combination of convolutional neural network (CNN) and bidirectional long short-term memory network (BiLSTM) for discriminant analysis of financial systemic risk. The model first uses CNN to extract local patterns of multidimensional features of financial markets, and then models the bidirectional dependency of time series through BiLSTM, to comprehensively characterize the changing laws of systemic risk in spatial features and temporal dynamics. The experiment is based on real financial data sets. The results show that the model is significantly superior to traditional single models (such as BiLSTM, CNN, Transformer, and TCN) in terms of accuracy, recall, and F1 score. The F1-score reaches 0.88, showing extremely high discriminant ability. This shows that the joint strategy of combining CNN and BiLSTM can not only fully capture the complex patterns of market data but also effectively deal with the long-term dependency problem in time series data. In addition, this study also explores the robustness of the model in dealing with data noise and processing high-dimensional data, providing strong support for intelligent financial risk management. In the future, the research will further optimize the model structure, introduce methods such as reinforcement learning and multimodal data analysis, and improve the efficiency and generalization ability of the model to cope with a more complex financial environment.

cs.LG↗

arXiv2025

Simultaneous Beamforming and Anti-Jamming With Intelligent Omni-Surfaces

Wireless transmission is vulnerable to malicious jamming attacks due to the openness of wireless channels, posing a severe threat to wireless communications. Current anti-jamming studies primarily focus on either enhancing desired signals or mitigating jamming, resulting in limited performance. To address this issue, intelligent omni-surface (IOS) is a promising solution. By jointly designing its reflective and refractive properties, the IOS can simultaneously nullify jamming and enhance desired signals. In this paper, we consider an IOS-aided multi-user anti-jamming communication system, aiming to improve desired signals and nullify jamming by optimizing IOS phase shifts and transmit beamforming. However, this is challenging due to the coupled and discrete IOS reflection and refraction phase shifts, the unknown jammer's beamformer, and imperfect jammer-related channel state information. To tackle this, we relax IOS phase shifts to continuous states and optimize with a coupling-aware algorithm using the Cauchy-Schwarz inequality and S-procedure, followed by a local search to recover discrete states. Simulation results show that the proposed scheme significantly improves the sum rate amid jamming attacks.

eess.SP↗