arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 775 records · Page 43Linked to original sources

arXiv2025

Challenge Summary U-MedSAM: Uncertainty-aware MedSAM for Medical Image Segmentation

Medical Image Foundation Models have proven to be powerful tools for mask prediction across various datasets. However, accurately assessing the uncertainty of their predictions remains a significant challenge. To address this, we propose a new model, U-MedSAM, which integrates the MedSAM model with an uncertainty-aware loss function and the Sharpness-Aware Minimization (SharpMin) optimizer. The uncertainty-aware loss function automatically combines region-based, distribution-based, and pixel-based loss designs to enhance segmentation accuracy and robustness. SharpMin improves generalization by finding flat minima in the loss landscape, thereby reducing overfitting. Our method was evaluated in the CVPR24 MedSAM on Laptop challenge, where U-MedSAM demonstrated promising performance.

eess.IV↗

arXiv2025

Towards An Integrated Approach for Expressive Piano Performance Synthesis from Music Scores

This paper presents an integrated system that transforms symbolic music scores into expressive piano performance audio. By combining a Transformer-based Expressive Performance Rendering (EPR) model with a fine-tuned neural MIDI synthesiser, our approach directly generates expressive audio performances from score inputs. To the best of our knowledge, this is the first system to offer a streamlined method for converting score MIDI files lacking expression control into rich, expressive piano performances. We conducted experiments using subsets of the ATEPP dataset, evaluating the system with both objective metrics and subjective listening tests. Our system not only accurately reconstructs human-like expressiveness, but also captures the acoustic ambience of environments such as concert halls and recording studios. Additionally, the proposed system demonstrates its ability to achieve musical expressiveness while ensuring good audio quality in its outputs.

cs.SD↗

arXiv2025

New results of Bollobás-type theorem for affine subspaces and projective subspaces

Bollobás-type theorem has received a lot of attention due to its application in graph theory. In 2015, Gábor Heged{ü}s gave an upper bound of bollobás-type affine subspace families for $q\neq 2$, and constructed an almost sharp affine subspaces pair families. In this note, we prove a new upper bound for bollobás-type affine subspaces without the requirement of $q\neq 2$, and construct a pair of families of affine subspaces, which shows that our upper bound is sharp. We also give an upper bound for bollobás-type projective subspaces, and prove that the Heged{ü}s's conjecture holds when $q=2$.

math.CO↗

arXiv2025

Guided Debugging of Auto-Translated Code Using Differential Testing

Large Language Models (LLMs) hold great promise in the task of code translation. However, the lack of explainability complicates the identification of the inevitable translation errors. In this paper, we propose tHinter, a debugging tool to locate translation errors in auto-translated code. The core idea of tHinter is that correctly translated, the source and translated code should present the same functionalities, giving the same output for the same input. Hence, lines in the translated code responsible for output differences are possibly translation errors. First, tHinter employs fuzzing to generate diverse test cases that thoroughly explore the translated code. Then, tHinter relies on a heuristic algorithm to pinpoint translation errors from coverage information and differential testing execution results of those test cases. This heuristic algorithm is designed to leverage both the statistics and the expertise of developers. Comprehensive experiments with real code show its effectiveness. It reduces 71% lines developers need to review during debugging and increases the likelihood of the LLM fixing translation errors in a single query by 59%. Developers generally consider it satisfactory and helpful.

cs.SE↗

arXiv2025

MADiff: Text-Guided Fashion Image Editing with Mask Prediction and Attention-Enhanced Diffusion

Text-guided image editing model has achieved great success in general domain. However, directly applying these models to the fashion domain may encounter two issues: (1) Inaccurate localization of editing region; (2) Weak editing magnitude. To address these issues, the MADiff model is proposed. Specifically, to more accurately identify editing region, the MaskNet is proposed, in which the foreground region, densepose and mask prompts from large language model are fed into a lightweight UNet to predict the mask for editing region. To strengthen the editing magnitude, the Attention-Enhanced Diffusion Model is proposed, where the noise map, attention map, and the mask from MaskNet are fed into the proposed Attention Processor to produce a refined noise map. By integrating the refined noise map into the diffusion model, the edited image can better align with the target prompt. Given the absence of benchmarks in fashion image editing, we constructed a dataset named Fashion-E, comprising 28390 image-text pairs in the training set, and 2639 image-text pairs for four types of fashion tasks in the evaluation set. Extensive experiments on Fashion-E demonstrate that our proposed method can accurately predict the mask of editing region and significantly enhance editing magnitude in fashion image editing compared to the state-of-the-art methods.

cs.CV↗

arXiv2025

FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training

Large-scale Vision-Language Pre-training (VLP) has demonstrated remarkable success in the general domain. However, in the fashion domain, items are distinguished by fine-grained attributes like texture and material, which are crucial for tasks such as retrieval. Existing models often fail to leverage these fine-grained attributes from both text and image modalities. To address the above issues, we propose a novel approach for the fashion domain, Fine-grained Attributes Enhanced VLP (FashionFAE), which focuses on the detailed characteristics of fashion data. An attribute-emphasized text prediction task is proposed to predict fine-grained attributes of the items. This forces the model to focus on the salient attributes from the text modality. Additionally, a novel attribute-promoted image reconstruction task is proposed, which further enhances the fine-grained ability of the model by leveraging the representative attributes from the image modality. Extensive experiments show that FashionFAE significantly outperforms State-Of-The-Art (SOTA) methods, achieving 2.9% and 5.2% improvements in retrieval on sub-test and full test sets, respectively, and a 1.6% average improvement in recognition tasks.

cs.CV↗

arXiv2025

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on resource-constrained edge devices. In this work, we propose the JAQ Framework, which jointly optimizes the three critical dimensions. However, effectively automating the design process across the vast search space of those three dimensions poses significant challenges, especially when pursuing extremely low-bit quantization. Specifical, the primary challenges include: (1) Memory overhead in software-side: Low-precision quantization-aware training can lead to significant memory usage due to storing large intermediate features and latent weights for back-propagation, potentially causing memory exhaustion. (2) Search time-consuming in hardware-side: The discrete nature of hardware parameters and the complex interplay between compiler optimizations and individual operators make the accelerator search time-consuming. To address these issues, JAQ mitigates the memory overhead through a channel-wise sparse quantization (CSQ) scheme, selectively applying quantization to the most sensitive components of the model during optimization. Additionally, JAQ designs BatchTile, which employs a hardware generation network to encode all possible tiling modes, thereby speeding up the search for the optimal compiler mapping strategy. Extensive experiments demonstrate the effectiveness of JAQ, achieving approximately 7% higher Top-1 accuracy on ImageNet compared to previous methods and reducing the hardware search time per iteration to 0.15 seconds.

cs.CV↗

arXiv2025

The Cosmic Evolution Early Release Science Survey (CEERS)

We present the Cosmic Evolution Early Release Science (CEERS) Survey, a 77.2 hour Director's Discretionary Early Release Science Program. CEERS demonstrates, tests, and validates efficient extragalactic surveys using coordinated, overlapping parallel observations with the JWST instrument suite, including NIRCam and MIRI imaging, NIRSpec low (R~100) and medium (R~1000) resolution spectroscopy, and NIRCam slitless grism (R~1500) spectroscopy. CEERS targets the Hubble Space Telescope-observed region of the Extended Groth Strip (EGS) field, supported by a rich set of multiwavelength data. CEERS facilitated immediate community science in both of the extragalactic core JWST science drivers ``First Light" and ``Galaxy Assembly," including: 1) The discovery and characterization of large samples of galaxies at z >~ 10 from ~90 arcmin^2 of NIRCam imaging, constraining their abundance and physical nature; 2) Deep spectra of >1000 galaxies, including dozens of galaxies at 6 3; and 4) Characterizing galaxy mid-IR emission with MIRI to study dust-obscured star-formation and supermassive black hole growth at z~1-3. As a legacy product for the community, the CEERS team has provided several data releases, accompanied by detailed notes on the data reduction procedures and notebooks to aid in reproducibility. In addition to an overview of the survey and quality of the data, we provide science highlights from the first two years with CEERS data.

astro-ph.GA↗

arXiv2025

PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping

3D Gaussian Splatting (3DGS) has emerged as a transformative method in the field of real-time novel synthesis. Based on 3DGS, recent advancements cope with large-scale scenes via spatial-based partition strategy to reduce video memory and optimization time costs. In this work, we introduce a parallel Gaussian splatting method, termed PG-SAG, which fully exploits semantic cues for both partitioning and Gaussian kernel optimization, enabling fine-grained building surface reconstruction of large-scale urban areas without downsampling the original image resolution. First, the Cross-modal model - Language Segment Anything is leveraged to segment building masks. Then, the segmented building regions is grouped into sub-regions according to the visibility check across registered images. The Gaussian kernels for these sub-regions are optimized in parallel with masked pixels. In addition, the normal loss is re-formulated for the detected edges of masks to alleviate the ambiguities in normal vectors on edges. Finally, to improve the optimization of 3D Gaussians, we introduce a gradient-constrained balance-load loss that accounts for the complexity of the corresponding scenes, effectively minimizing the thread waiting time in the pixel-parallel rendering stage as well as the reconstruction lost. Extensive experiments are tested on various urban datasets, the results demonstrated the superior performance of our PG-SAG on building surface reconstruction, compared to several state-of-the-art 3DGS-based methods. Project Web:https://github.com/TFWang-9527/PG-SAG.

cs.CV↗

arXiv2025

Universal Online Temporal Calibration for Optimization-based Visual-Inertial Navigation Systems

6-Degree of Freedom (6DoF) motion estimation with a combination of visual and inertial sensors is a growing area with numerous real-world applications. However, precise calibration of the time offset between these two sensor types is a prerequisite for accurate and robust tracking. To address this, we propose a universal online temporal calibration strategy for optimization-based visual-inertial navigation systems. Technically, we incorporate the time offset td as a state parameter in the optimization residual model to align the IMU state to the corresponding image timestamp using td, angular velocity and translational velocity. This allows the temporal misalignment td to be optimized alongside other tracking states during the process. As our method only modifies the structure of the residual model, it can be applied to various optimization-based frameworks with different tracking frontends. We evaluate our calibration method with both EuRoC and simulation data and extensive experiments demonstrate that our approach provides more accurate time offset estimation and faster convergence, particularly in the presence of noisy sensor data.

cs.RO↗

arXiv2024

Event-Triggered Observer-Based Fixed-Time Consensus Control for Uncertain Nonlinear Multiagent Systems with Unknown States

This paper introduces a novel approach for achieving fixed-time tracking consensus control in multiagent systems (MASs). Departing from the reliance on traditional controllers, our innovative controller integrates modified tuning and Lyapunov functions to guarantee stability and convergence. Furthermore, we have implemented an event-triggered strategy aimed at reducing the frequency of updates, alongside an output-feedback observer to manage unmeasured states effectively. To address the challenges posed by unknown functions and algebraic-loop problems, we opted for radial basis function neural networks (RBF NNs), chosen for their superior performance. Our methodology successfully mitigates Zeno's behavior and ensures stability within a narrowly defined set. The efficacy of our proposed solution is validated through two illustrative simulation examples.

eess.SY↗

arXiv2024

The Lyman Continuum Escape Fraction of Star-forming Galaxies at $2.4\lesssim z\lesssim3.0$ from UVCANDELS

The UltraViolet Imaging of the Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey Fields (UVCANDELS) survey is a Hubble Space Telescope (HST) Cycle-26 Treasury Program, allocated in total 164 orbits of primary Wide-Field Camera 3 Ultraviolet and Visible light F275W imaging with coordinated parallel Advanced Camera for Surveys F435W imaging, on four of the five premier extragalactic survey fields: GOODS-N, GOODS-S, EGS, and COSMOS. We introduce this survey by presenting a comprehensive analysis of the absolute escape fraction ($f_{\rm esc}^{\rm abs}$) of Lyman continuum (LyC) radiation through stacking the UV images of a population of star-forming galaxies with secure redshifts at $2.4\leq z\leq3.0$. Our stacking benefits from the catalogs of high-quality spectroscopic redshifts compiled from archival ground-based data and HST slitless spectroscopy, carefully vetted by dedicated visual inspection efforts. We develop a robust stacking method to apply to 10 samples of in total 56 galaxies, and perform detailed Monte Carlo (MC) simulations of the intergalactic medium (IGM) attenuation, to take into account the sample variance of the mean IGM transmission when measuring $f_{\rm esc}^{\rm abs}$. The full stack at $z\approx2.44$ from 28 galaxies places a stringent 1-$σ$ upper limit of $f_{\rm esc}^{\rm abs}\lesssim5\%$, whereas the full stack at $z\approx2.72$ of equal number of galaxies gives an upper limit of $f_{\rm esc}^{\rm abs}\lesssim26\%$ at 1-$σ$ confidence level. These new F275W and F435W imaging mosaics from UVCANDELS have been made publicly available on the Barbara A. Mikulski Archive for Space Telescopes (MAST).

astro-ph.GA↗

arXiv2024

Causal-aware Graph Neural Architecture Search under Distribution Shifts

Graph NAS has emerged as a promising approach for autonomously designing GNN architectures by leveraging the correlations between graphs and architectures. Existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph scenarios, mainly because the graph-architecture correlations they exploit might be spurious and varying across distributions. We propose to handle the distribution shifts in the graph architecture search process by discovering and exploiting the causal relationship between graphs and architectures to search for the optimal architectures that can generalize under distribution shifts. The problem remains unexplored with following challenges: how to discover the causal graph-architecture relationship that has stable predictive abilities across distributions, and how to handle distribution shifts with the discovered causal graph-architecture relationship to search the generalized graph architectures. To address these challenges, we propose Causal-aware Graph Neural Architecture Search (CARNAS), which is able to capture the causal graph-architecture relationship during the architecture search process and discover the generalized graph architecture under distribution shifts. Specifically, we propose Disentangled Causal Subgraph Identification to capture the causal subgraphs that have stable prediction abilities across distributions. Then, we propose Graph Embedding Intervention to intervene on causal subgraphs within the latent space, ensuring that these subgraphs encapsulate essential features for prediction while excluding non-causal elements. Additionally, we propose Invariant Architecture Customization to reinforce the causal invariant nature of the causal subgraphs, which are utilized to tailor generalized graph architectures. Extensive experiments demonstrate that CARNAS achieves advanced out-of-distribution generalization ability.

cs.LG↗

arXiv2024

Improving Generalization for AI-Synthesized Voice Detection

AI-synthesized voice technology has the potential to create realistic human voices for beneficial applications, but it can also be misused for malicious purposes. While existing AI-synthesized voice detection models excel in intra-domain evaluation, they face challenges in generalizing across different domains, potentially becoming obsolete as new voice generators emerge. Current solutions use diverse data and advanced machine learning techniques (e.g., domain-invariant representation, self-supervised learning), but are limited by predefined vocoders and sensitivity to factors like background noise and speaker identity. In this work, we introduce an innovative disentanglement framework aimed at extracting domain-agnostic artifact features related to vocoders. Utilizing these features, we enhance model learning in a flat loss landscape, enabling escape from suboptimal solutions and improving generalization. Extensive experiments on benchmarks show our approach outperforms state-of-the-art methods, achieving up to 5.12% improvement in the equal error rate metric in intra-domain and 7.59% in cross-domain evaluations.

cs.SD↗

arXiv2024

MSA-3D: Metallicity Gradients in Galaxies at $z\sim1$ with JWST/NIRSpec Slit-stepping Spectroscopy

The radial gradient of gas-phase metallicity is a powerful probe of the chemical and structural evolution of star-forming galaxies, closely tied to disk formation and gas kinematics in the early universe. We present spatially resolved chemical and dynamical properties for a sample of 25 galaxies at $0.5 \lesssim z \lesssim 1.7$ from the \msasd survey. These innovative observations provide 3D spectroscopy of galaxies at a spatial resolution approaching JWST's diffraction limit and a high spectral resolution of $R\simeq2700$. The metallicity gradients measured in our galaxy sample range from $-$0.03 to 0.02 dex~kpc$^{-1}$. Most galaxies exhibit negative or flat radial gradients, indicating lower metallicity in the outskirts or uniform metallicity throughout the entire galaxy. We confirm a tight relationship between stellar mass and metallicity gradient at $z\sim1$ with small intrinsic scatter of 0.02 dex~kpc$^{-1}$. Our results indicate that metallicity gradients become increasingly negative as stellar mass increases, likely because the more massive galaxies tend to be more ``disky". This relationship is consistent with the predictions from cosmological hydrodynamic zoom-in simulations with strong stellar feedback. This work presents the effort to harness the multiplexing capability of JWST NIRSpec/MSA in slit-stepping mode to map the chemical and kinematic profiles of high-redshift galaxies in large samples and at high spatial and spectral resolution.

astro-ph.GA↗

arXiv2024

Cognition Chain for Explainable Psychological Stress Detection on Social Media

Stress is a pervasive global health issue that can lead to severe mental health problems. Early detection offers timely intervention and prevention of stress-related disorders. The current early detection models perform "black box" inference suffering from limited explainability and trust which blocks the real-world clinical application. Thanks to the generative properties introduced by the Large Language Models (LLMs), the decision and the prediction from such models are semi-interpretable through the corresponding description. However, the existing LLMs are mostly trained for general purposes without the guidance of psychological cognitive theory. To this end, we first highlight the importance of prior theory with the observation of performance boosted by the chain-of-thoughts tailored for stress detection. This method termed Cognition Chain explicates the generation of stress through a step-by-step cognitive perspective based on cognitive appraisal theory with a progress pipeline: Stimulus $\rightarrow$ Evaluation $\rightarrow$ Reaction $\rightarrow$ Stress State, guiding LLMs to provide comprehensive reasoning explanations. We further study the benefits brought by the proposed Cognition Chain format by utilising it as a synthetic dataset generation template for LLMs instruction-tuning and introduce CogInstruct, an instruction-tuning dataset for stress detection. This dataset is developed using a three-stage self-reflective annotation pipeline that enables LLMs to autonomously generate and refine instructional data. By instruction-tuning Llama3 with CogInstruct, we develop CogLLM, an explainable stress detection model. Evaluations demonstrate that CogLLM achieves outstanding performance while enhancing explainability. Our work contributes a novel approach by integrating cognitive theories into LLM reasoning processes, offering a promising direction for future explainable AI research.

cs.AI↗

arXiv2024

Semantics-Aware Next-best-view Planning for Efficient Search and Detection of Task-relevant Plant Parts

Searching and detecting the task-relevant parts of plants is important to automate harvesting and de-leafing of tomato plants using robots. This is challenging due to high levels of occlusion in tomato plants. Active vision is a promising approach in which the robot strategically plans its camera viewpoints to overcome occlusion and improve perception accuracy. However, current active-vision algorithms cannot differentiate between relevant and irrelevant plant parts and spend time on perceiving irrelevant plant parts. This work proposed a semantics-aware active-vision strategy that uses semantic information to identify the relevant plant parts and prioritise them during view planning. The proposed strategy was evaluated on the task of searching and detecting the relevant plant parts using simulation and real-world experiments. In simulation experiments, the semantics-aware strategy proposed could search and detect 81.8% of the relevant plant parts using nine viewpoints. It was significantly faster and detected more plant parts than predefined, random, and volumetric active-vision strategies that do not use semantic information. The strategy proposed was also robust to uncertainty in plant and plant-part positions, plant complexity, and different viewpoint-sampling strategies. In real-world experiments, the semantics-aware strategy could search and detect 82.7% of the relevant plant parts using seven viewpoints, under complex greenhouse conditions with natural variation and occlusion, natural illumination, sensor noise, and uncertainty in camera poses. The results of this work clearly indicate the advantage of using semantics-aware active vision for targeted perception of plant parts and its applicability in the real world. It can significantly improve the efficiency of automated harvesting and de-leafing in tomato crop production.

cs.RO↗

arXiv2024

Set-Valued Sensitivity Analysis of Deep Neural Networks

This paper proposes a sensitivity analysis framework based on set valued mapping for deep neural networks (DNN) to understand and compute how the solutions (model weights) of DNN respond to perturbations in the training data. As a DNN may not exhibit a unique solution (minima) and the algorithm of solving a DNN may lead to different solutions with minor perturbations to input data, we focus on the sensitivity of the solution set of DNN, instead of studying a single solution. In particular, we are interested in the expansion and contraction of the set in response to data perturbations. If the change of solution set can be bounded by the extent of the data perturbation, the model is said to exhibit the Lipschitz like property. This "set-to-set" analysis approach provides a deeper understanding of the robustness and reliability of DNNs during training. Our framework incorporates both isolated and non-isolated minima, and critically, does not require the assumption that the Hessian of loss function is non-singular. By developing set-level metrics such as distance between sets, convergence of sets, derivatives of set-valued mapping, and stability across the solution set, we prove that the solution set of the Fully Connected Neural Network holds Lipschitz-like properties. For general neural networks (e.g., Resnet), we introduce a graphical-derivative-based method to estimate the new solution set following data perturbation without retraining.

cs.LG↗