arXiv subjects

Chun Wang

Publications and source records attributed to Chun Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Dual Information Speech Language Models for Emotional Conversations

Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a promising solution. However, SLMs built by extending frozen LLMs struggle to capture paralinguistic information and exhibit reduced context understanding. We identify entangled information and improper training strategies as key issues. To address these issues, we propose two heterogeneous adapters and suggest a weakly supervised training strategy. Our approach disentangles paralinguistic and linguistic information, enabling SLMs to interpret speech through structured representations. It also preserves contextual understanding by avoiding the generation of task-specific vectors through controlled randomness. This approach trains only the adapters on common datasets, ensuring parameter and data efficiency. Experiments demonstrate competitive performance in emotional conversation tasks, showcasing the model's ability to effectively integrate both paralinguistic and linguistic information within contextual settings.

cs.CL↗

arXiv2025

Optimal Transport Regularization for Speech Text Alignment in Spoken Language Models

Spoken Language Models (SLMs), which extend Large Language Models (LLMs) to perceive speech inputs, have gained increasing attention for their potential to advance speech understanding tasks. However, despite recent progress, studies show that SLMs often struggle to generalize across datasets, even for trained languages and tasks, raising concerns about whether they process speech in a text-like manner as intended. A key challenge underlying this limitation is the modality gap between speech and text representations. The high variability in speech embeddings may allow SLMs to achieve strong in-domain performance by exploiting unintended speech variations, ultimately hindering generalization. To mitigate this modality gap, we introduce Optimal Transport Regularization (OTReg), a method that formulates speech-text alignment as an optimal transport problem and derives a regularization loss to improve SLM training. In each training iteration, OTReg first establishes a structured correspondence between speech and transcript embeddings by determining the optimal transport plan, then incorporates the regularization loss based on this transport plan to optimize SLMs in generating speech embeddings that align more effectively with transcript embeddings. OTReg is lightweight, requiring no additional labels or learnable parameters, and integrates seamlessly into existing SLM training procedures. Extensive multilingual ASR experiments demonstrate that OTReg enhances speech-text alignment, mitigates the modality gap, and consequently improves SLM generalization across diverse datasets.

cs.CL↗

arXiv2025

A North-South Metallicity Asymmetry in the Outer Galactic disk -- Evidence for the Pericentric Passage of the Sagittarius Dwarf Galaxy

We present maps of the mean metallicity distributions on the Galactocentric $R$--$Z$ plane at different azimuthal angles using red clump stars selected from the LAMOST and APOGEE surveys. In the inner disk ($R < $ 11\,kpc), the metallicity distribution is symmetric between the upper and lower disk. However, we find a North-South metallicity asymmetry in the outer disk ($R > 11$\,kpc), especially towards the anti-Galactic center ($-5^\circ < Φ< 15^\circ$) direction. By further dissecting the map in age space, we detect this asymmetry across all mono-age stellar populations. However, the asymmetry is less pronounced in older populations ($τ> 8$ Gyr) compared to younger ones ($τ< 6$\,Gyr). This reduced significance likely stems from three factors: larger age uncertainties, fewer stars in the outer disk, and the kinematically hotter nature of older populations. The observed metallicity asymmetry may be the consequence of the purturbation of the recent pericentric passage through the Galactic disk and tidal force of the well-known Sagittarius dwarf galaxy.

astro-ph.GA↗

arXiv2025

Contextual Optimization under Covariate Shift: A Robust Approach by Intersecting Wasserstein Balls

In contextual optimization, a decision-maker leverages contextual information, often referred to as covariates, to better resolve uncertainty and make informed decisions. In this paper, we examine the challenges of contextual decision-making under covariate shift, a phenomenon where the distribution of covariates differs between the training and test environments. Such shifts can lead to inaccurate upstream estimations for test covariates that lie far from the training data, ultimately resulting in suboptimal downstream decisions. To tackle these challenges, we propose a novel approach called Intersection Wasserstein-balls DRO (IW-DRO), which integrates multiple estimation methods into the distributionally robust optimization (DRO) framework. At the core of our approach is an innovative ambiguity set defined as the intersection of two Wasserstein balls, with their centers constructed using appropriate nonparametric and parametric estimators. On the computational side, we reformulate the IW-DRO problem as a tractable convex program and develop an approximate algorithm tailored for large-scale problems to enhance computational efficiency. From a theoretical perspective, we demonstrate that IW-DRO achieves superior performance compared to single Wasserstein-ball DRO models. We further establish performance guarantees by analyzing the coverage of the intersection ambiguity set and the measure concentration of both estimators under the Wasserstein distance. Notably, we derive a finite-sample concentration result for the Nadaraya-Watson kernel estimator under covariate shift. The proposed IW-DRO framework offers practical value for decision-makers operating in uncertain environments affected by covariate shifts.

math.OC↗

arXiv2025

Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent from the input. This issue is closely related to dataset biases, where frequent co-occurrences of objects lead to entangled semantic representations across modalities. As a result, models may erroneously activate object representations that are commonly associated with the input but not actually present. To address this, we propose a causality-driven disentanglement framework that mitigates hallucinations through causal intervention. Our approach includes a Causal-Driven Projector in the visual pathway and a Causal Intervention Module integrated into the final transformer layer of the language model. These components work together to reduce spurious correlations caused by biased training data. Experimental results show that our method significantly reduces hallucinations while maintaining strong performance on multiple multimodal benchmarks. Visualization analyses further confirm improved separability of object representations. The code is available at: https://github.com/IgniSavium/Causal-LLaVA

cs.AI↗

arXiv2025

FocusedAD: Character-centric Movie Audio Description

Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with general video captioning, AD demands plot-relevant narration with explicit character name references, posing unique challenges in movie understanding.To identify active main characters and focus on storyline-relevant regions, we propose FocusedAD, a novel framework that delivers character-centric movie audio descriptions. It includes: (i) a Character Perception Module(CPM) for tracking character regions and linking them to names; (ii) a Dynamic Prior Module(DPM) that injects contextual cues from prior ADs and subtitles via learnable soft prompts; and (iii) a Focused Caption Module(FCM) that generates narrations enriched with plot-relevant details and named characters. To overcome limitations in character identification, we also introduce an automated pipeline for building character query banks. FocusedAD achieves state-of-the-art performance on multiple benchmarks, including strong zero-shot results on MAD-eval-Named and our newly proposed Cinepile-AD dataset. Code and data will be released at https://github.com/Thorin215/FocusedAD .

cs.CV↗

arXiv2025

Seek and Solve Reasoning for Table Question Answering

The complexities of table structures and question logic make table-based question answering (TQA) tasks challenging for Large Language Models (LLMs), often requiring task simplification before solving. This paper reveals that the reasoning process during task simplification may be more valuable than the simplified tasks themselves and aims to improve TQA performance by leveraging LLMs' reasoning capabilities. We propose a Seek-and-Solve pipeline that instructs the LLM to first seek relevant information and then answer questions, integrating these two stages at the reasoning level into a coherent Seek-and-Solve Chain of Thought (SS-CoT). Additionally, we distill a single-step TQA-solving prompt from this pipeline, using demonstrations with SS-CoT paths to guide the LLM in solving complex TQA tasks under In-Context Learning settings. Our experiments show that our approaches result in improved performance and reliability while being efficient. Our findings emphasize the importance of eliciting LLMs' reasoning capabilities to handle complex TQA tasks effectively.

cs.CL↗

arXiv2025

The Vertical Metallicity Gradient of the Galactic Disk for Mono-Age Stellar Populations in LAMOST

The vertical metallicity gradient of the Galactic disk offers valuable insights into the disk's formation and chemical evolution over time. We utilized the LAMOST-LRS young stellar sample to investigate this gradient and found that it approaches zero as stellar effective temperature (or age) increases (or decreases) across various Galactocentric distances. To validate this result, we analyzed 295 open clusters younger than 3 Gyr and 976 classical cepheids within the Galactic disk. The findings confirmed that, within a given narrow age range, the vertical metallicity gradient is effectively zero. This relationship between metallicity and age supports the ``upside-down'' disk formation theory, as it indicates that the youngest and most metal-rich stars dominate the midplane, while older and more metal-poor stars formed at larger vertical heights and currently tend to be at these heights. Overall, our results align well with theoretical predictions, offering further insight into the chemical evolution and structural properties of the Milky Way.

astro-ph.GA↗

arXiv2024

The Stellar Disk Structure Rrevealed by the Mono-age Populations of the LAMOST Red Clump Sample

Understanding the structure of the Galactic disk is crucial for understanding the formation and evolutionary history of the Milky Way. This study examines the structure of the Galactic disk by analyzing a sample of 138,667 primary red clump (RC) stars from the LAMOST and Gaia datasets. We have categorized these RC stars into mono-age populations and investigated their spatial distributions within the R - Z plane, estimating scale heights and lengths through the fitting of their vertical and radial density profiles. Our analysis indicates that the vertical profiles of these mono-age populations fit a dual-component disk model, where both components exhibit significant flaring, particularly in the outer disk regions. Within a constant Galactocentric radius R, the scale heights of the first component, representing the morphologically thin disk, rise with age. In contrast, the scale heights of the second component, corresponding to the morphologically thick disk, remain comparatively stable across different age groups. Additionally, the radial density profiles of both disk components predominantly peak within a radial range of 7.5-8.5 kpc. These findings underscore the importance of age as a crucial factor in shaping the spatial distribution and structural evolution of the Galactic disk, offering valuable insights into its complex dynamics and history.

astro-ph.GA↗

arXiv2024

Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution

Optics-guided Thermal UAV image Super-Resolution (OTUAV-SR) has attracted significant research interest due to its potential applications in security inspection, agricultural measurement, and object detection. Existing methods often employ single guidance model to generate the guidance features from optical images to assist thermal UAV images super-resolution. However, single guidance models make it difficult to generate effective guidance features under favorable and adverse conditions in UAV scenarios, thus limiting the performance of OTUAV-SR. To address this issue, we propose a novel Guidance Disentanglement network (GDNet), which disentangles the optical image representation according to typical UAV scenario attributes to form guidance features under both favorable and adverse conditions, for robust OTUAV-SR. Moreover, we design an attribute-aware fusion module to combine all attribute-based optical guidance features, which could form a more discriminative representation and fit the attribute-agnostic guidance process. To facilitate OTUAV-SR research in complex UAV scenarios, we introduce VGTSR2.0, a large-scale benchmark dataset containing 3,500 aligned optical-thermal image pairs captured under diverse conditions and scenes. Extensive experiments on VGTSR2.0 demonstrate that GDNet significantly improves OTUAV-SR performance over state-of-the-art methods, especially in the challenging low-light and foggy environments commonly encountered in UAV scenarios. The dataset and code will be publicly available at https://github.com/Jocelyney/GDNet.

eess.IV↗

arXiv2024

Data standardization for robust lip sync

Lip sync is a fundamental audio-visual task. However, existing lip sync methods fall short of being robust in the wild. One important cause could be distracting factors on the visual input side, making extracting lip motion information difficult. To address these issues, this paper proposes a data standardization pipeline to standardize the visual input for lip sync. Based on recent advances in 3D face reconstruction, we first create a model that can consistently disentangle lip motion information from the raw images. Then, standardized images are synthesized with disentangled lip motion information, with all other attributes related to distracting factors set to predefined values independent of the input, to reduce their effects. Using synthesized images, existing lip sync methods improve their data efficiency and robustness, and they achieve competitive performance for the active speaker detection task.

cs.CV↗

arXiv2024

Toward Wireless Localization Using Multiple Reconfigurable Intelligent Surfaces

This paper investigates the capabilities and effectiveness of backward sensing centered on reconfigurable intelligent surfaces (RISs). We demonstrate that the direction of arrival (DoA) estimation of incident waves in the far-field regime can be accomplished using a single RIS by leveraging configurational diversity. Furthermore, we identify that the spatial diversity achieved through deploying multiple RISs enables accurate localization of multiple power sources. Physically accurate and mathematically concise models are introduced to characterize forward signal aggregations via RISs. By employing linearized approximations inherent in the far-field region, the measurement process for various configurations can be expressed as a system of linear equations. The mathematical essence of backward sensing lies in solving this system. A theoretical framework for determining key performance indicators is established through condition number analysis of the sensing operators. In the context of localization using multiple RISs, we examine relationships among the rank of sensing operators, the size of the region of interest (RoI), and the number of elements and measurements. For DoA estimations, we provide an upper bound for the relative error of the least squares reconstruction algorithm. These quantitative analyses offer essential insights for system design and optimization. Numerical experiments validate our findings. To demonstrate the practicality of our proposed RIS-centric sensing approach, we develop a proof-of-concept prototype using universal software radio peripherals (USRP) and employ a magnitude-only reconstruction algorithm tailored for this system. To our knowledge, this represents the first trial of its kind.

eess.SP↗

arXiv2024

Dreamer: Dual-RIS-aided Imager in Complementary Modes

Reconfigurable intelligent surfaces (RISs) have emerged as a promising auxiliary technology for radio frequency imaging. However, existing works face challenges of faint and intricate back-scattered waves and the restricted field-of-view (FoV), both resulting from complex target structures and a limited number of antennas. The synergistic benefits of multi-RIS-aided imaging hold promise for addressing these challenges. Here, we propose a dual-RIS-aided imaging system, Dreamer, which operates collaboratively in complementary modes (reflection-mode and transmission-mode). Dreamer significantly expands the FoV and enhances perception by deploying dual-RIS across various spatial and measurement patterns. Specifically, we perform a fine-grained analysis of how radio-frequency (RF) signals encode scene information in the scattered object modeling. Based on this modeling, we design illumination strategies to balance spatial resolution and observation scale, and implement a prototype system in a typical indoor environment. Moreover, we design a novel artificial neural network with a CNN-external-attention mechanism to translate RF signals into high-resolution images of human contours. Our approach achieves an impressive SSIM score exceeding 0.83, validating its effectiveness in broadening perception modes and enhancing imaging capabilities. The code to reproduce our results is available at https://github.com/fuhaiwang/Dreamer.

eess.SP↗

arXiv2024

Research on Education Big Data for Students Academic Performance Analysis based on Machine Learning

The application of the Internet in the field of education is becoming more and more popular, and a large amount of educational data is generated in the process. How to effectively use these data has always been a key issue in the field of educational data mining. In this work, a machine learning model based on Long Short-Term Memory Network (LSTM) was used to conduct an in-depth analysis of educational big data to evaluate student performance. The LSTM model efficiently processes time series data, allowing us to capture time-dependent and long-term trends in students' learning activities. This approach is particularly useful for analyzing student progress, engagement, and other behavioral patterns to support personalized education. In an experimental analysis, we verified the effectiveness of the deep learning method in predicting student performance by comparing the performance of different models. Strict cross-validation techniques are used to ensure the accuracy and generalization of experimental results.

cs.CY↗

arXiv2024

An Empirical Bayes Approach for Estimating Skill Models for Professional Darts Players

We perform an exploratory data analysis on a data-set for the top 16 professional darts players from the 2019 season. We use this data-set to fit player skill models which can then be used in dynamic zero-sum games (ZSGs) that model real-world matches between players. We propose an empirical Bayesian approach based on the Dirichlet-Multinomial (DM) model that overcomes limitations in the data. Specifically we introduce two DM-based skill models where the first model borrows strength from other darts players and the second model borrows strength from other regions of the dartboard. We find these DM-based models outperform simpler benchmark models with respect to Brier and Spherical scores, both of which are proper scoring rules. We also show in ZSGs settings that the difference between DM-based skill models and the simpler benchmark models is practically significant. Finally, we use our DM-model to analyze specific situations that arose in real-world darts matches during the 2019 season.

stat.AP↗

arXiv2024

Literature Review of Current Sustainability Assessment Frameworks and Approaches for Organizations

This systematic literature review explores sustainability assessment frameworks (SAFs) across diverse industries. The review focuses on SAF design approaches including the methods used for Sustainability Indicator (SI) selection, relative importance assessment, and interdependency analysis. Various methods, including literature reviews, stakeholder interviews, questionnaires, Pareto analysis, SMART approach, and adherence to sustainability standards, contribute to the complex SI selection process. Fuzzy-AHP stands out as a robust technique for assessing relative SI importance. While dynamic sustainability and performance indices are essential, methods like DEMATEL, VIKOR, correlation analysis, and causal models for interdependency assessment exhibit static limitations. The review presents strengths and limitations of SAFs, addressing gaps in design approaches and contributing to a comprehensive understanding. The insights of this review aim to benefit policymakers, administrators, leaders, and researchers, fostering sustainability practices. Future research recommendations include exploring multi-criteria decision-making models and hybrid approaches, extending sustainability evaluation across organizational levels and supply chains. Emphasizing adaptability to industry specifics and dynamic global adjustments is proposed for holistic sustainability practices, further enhancing organizational sustainability.

cs.CY↗

arXiv2024

XRMDN: An Extended Recurrent Mixture Density Network for Short-Term Probabilistic Rider Demand Forecasting with High Volatility

In the realm of Mobility-on-Demand (MoD) systems, the forecasting of rider demand is a cornerstone for operational decision-making and system optimization. Traditional forecasting methodologies primarily yield point estimates, thereby neglecting the inherent uncertainty within demand projections. Moreover, MoD demand levels are profoundly influenced by both endogenous and exogenous factors, leading to high and dynamic volatility. This volatility significantly undermines the efficacy of conventional time series forecasting methods. In response, we propose an Extended Recurrent Mixture Density Network (XRMDN), a novel deep learning framework engineered to address these challenges. XRMDN leverages a sophisticated architecture to process demand residuals and variance through correlated modules, allowing for the flexible incorporation of endogenous and exogenous data. This architecture, featuring recurrent connections within the weight, mean, and variance neural networks, adeptly captures demand trends, thus significantly enhancing forecasting precision, particularly in high-volatility scenarios. Our comprehensive experimental analysis, utilizing real-world MoD datasets, demonstrates that XRMDN surpasses the existing benchmark models across various metrics, notably excelling in high-demand volatility contexts. This advancement in probabilistic demand forecasting marks a significant contribution to the field, offering a robust tool for enhancing operational efficiency and customer satisfaction in MoD systems.

cs.LG↗

arXiv2024

Mapping the Galactic disk with the LAMOST and Gaia Red clump sample: VIII: Mapping the kinematics of the Galactic disk using mono-age and mono-abundance stellar populations

We present a comprehensive study of the kinematic properties of the different Galactic disk populations, as defined by the chemical abundance ratios and stellar ages, across a large disk volume (4.5 $\leq$ R $\leq$ 15.0 kpc and $|Z|$ $\leq$ 3.0 kpc), by using the LAMOST-Gaia red clump sample stars. We determine the median velocities for various spatial and population bins, finding large-scale bulk motions, such as the wave-like behavior in radial velocity, the north-south discrepancy in azimuthal velocity and the warp signal in vertical velocity, and the amplitudes and spatial-dependences of those bulk motions show significant variations for different mono-age and mono-abundance populations. The global spatial behaviors of the velocity dispersions clearly show a signal of spiral arms and, a signal of the disk perturbation event within 4 Gyr, as well as the disk flaring in the outer region (i.e., $R \ge 12$ kpc) mostly for young or alpha-poor stellar populations. Our detailed measurements of age/[$α$/Fe]-velocity dispersion relations for different disk volumes indicate that young/$α$-poor populations are likely originated from dynamically heated by both giant molecular clouds and spiral arms, while old/$α$-enhanced populations require an obvious contribution from other heating mechanisms such as merger and accretion, or born in the chaotic mergers of gas-rich systems and/or turbulent interstellar medium.

astro-ph.GA↗