arXiv subjects

Shan Gao

Publications and source records attributed to Shan Gao.

At least 37 records · Page 2Linked to original sources

arXiv2025

ReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models

Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically, achieving remarkable performance. However, existing LLM-based methods fail to adequately interpret spatial relationships among visual themes and design elements, leading to structural and diverse problems in layout generation. To address this issue, we introduce ReLayout, a novel method that leverages relation-CoT to generate more reasonable and aesthetically coherent layouts by fundamentally originating from design concepts. Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements, with the goal of decomposing the layout into smaller, structured, and recursive layouts, thereby enabling the generation of more structured layouts. Furthermore, based on these defined relationships, we introduce a layout prototype rebalance sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles. This sampler addresses uniformity issues in generation that arise from data bias in the prototype distribution balance process. Extensive experimental results verify that ReLayout outperforms baselines and can generate structural and diverse layouts that are more aligned with human aesthetics and more explainable.

cs.CV↗

arXiv2025

Comparing methods for handling missing data in electronic health records for dynamic risk prediction of central-line associated bloodstream infection

Electronic health records (EHR) often contain varying levels of missing data. This study compared different imputation strategies to identify the most suitable approach for predicting central line-associated bloodstream infection (CLABSI) in the presence of competing risks using EHR data. We analyzed 30862 catheter episodes at University Hospitals Leuven (2012-2013) to predict 7-day CLABSI risk using a landmark cause-specific supermodel, accounting for competing risks of hospital discharge and death. Imputation methods included simple methods (median/mode, last observation carried forward), multiple imputation, regression-based and mixed-effects models leveraging longitudinal structure, and random forest imputation to capture interactions and non-linearities. Missing indicators were also assessed alone and in combination with other imputation methods. Model performance was evaluated dynamically at daily landmarks up to 14 days post-catheter placement. The missing indicator approach showed the highest discriminative ability, achieving a mean AUROC of up to 0.782 and superior overall performance based on the scaled Brier score. Combining missing indicators with other methods slightly improved performance, with the mixed model approach combined with missing indicators achieving the highest AUROC (0.783) at day 4, and the missForestPredict approach combined with missing indicators yielding the best scaled Brier scores at earlier landmarks. This suggests that in EHR data, the presence or absence of information may hold valuable insights for patient risk prediction. However, the use of missing indicators requires caution, as shifts in EHR data over time can alter missing data patterns, potentially impacting model transportability.

stat.AP↗

arXiv2025

CIM-NET: A Video Denoising Deep Neural Network Model Optimized for Computing-in-Memory Architectures

While deep neural network (DNN)-based video denoising has demonstrated significant performance, deploying state-of-the-art models on edge devices remains challenging due to stringent real-time and energy efficiency requirements. Computing-in-Memory (CIM) chips offer a promising solution by integrating computation within memory cells, enabling rapid matrix-vector multiplication (MVM). However, existing DNN models are often designed without considering CIM architectural constraints, thus limiting their acceleration potential during inference. To address this, we propose a hardware-algorithm co-design framework incorporating two innovations: (1) a CIM-Aware Architecture, CIM-NET, optimized for large receptive field operation and CIM's crossbar-based MVM acceleration; and (2) a pseudo-convolutional operator, CIM-CONV, used within CIM-NET to integrate slide-based processing with fully connected transformations for high-quality feature extraction and reconstruction. This framework significantly reduces the number of MVM operations, improving inference speed on CIM chips while maintaining competitive performance. Experimental results indicate that, compared to the conventional lightweight model FastDVDnet, CIM-NET substantially reduces MVM operations with a slight decrease in denoising performance. With a stride value of 8, CIM-NET reduces MVM operations to 1/77th of the original, while maintaining competitive PSNR (35.11 dB vs. 35.56 dB

cs.CV↗

arXiv2025

Stability and List-Replicability for Agnostic Learners

Two seminal papers--Alon, Livni, Malliaris, Moran (STOC 2019) and Bun, Livni, and Moran (FOCS 2020)--established the equivalence between online learnability and globally stable PAC learnability in binary classification. However, Chase, Chornomaz, Moran, and Yehudayoff (STOC 2024) recently showed that this equivalence does not hold in the agnostic setting. Specifically, they proved that in the agnostic setting, only finite hypothesis classes are globally stable learnable. Therefore, agnostic global stability is too restrictive to capture interesting hypothesis classes. To address this limitation, Chase et al. introduced two relaxations of agnostic global stability. In this paper, we characterize the classes that are learnable under their proposed relaxed conditions, resolving the two open problems raised in their work. First, we prove that in the setting where the stability parameter can depend on the excess error (the gap between the learner's error and the best achievable error by the hypothesis class), agnostic stability is fully characterized by the Littlestone dimension. Consequently, as in the realizable case, this form of learnability is equivalent to online learnability. As part of the proof of this theorem, we strengthen the celebrated result of Bun et al. by showing that classes with infinite Littlestone dimension are not stably PAC learnable, even if we allow the stability parameter to depend on the excess error. For the second relaxation proposed by Chase et al., we prove that only finite hypothesis classes are globally stable learnable, even if we restrict the agnostic setting to distributions with small population loss.

cs.LG↗

arXiv2025

Prediction of CO2 reduction reaction intermediates and products on transition metal-doped r-GeSe monolayers:A combined DFT and machine learning approach

The electrocatalytic CO2 reduction reaction (CO2RR) is a complex multi-proton-electron transfer process that generates a vast network of reaction intermediates. Accurate prediction of free energy changes (G) of these intermediates and products is essential for evaluating catalytic performance. We combined density functional theory (DFT) and machine learning (ML) to screen 25 single-atom catalysts (SACs) on defective r-GeSe monolayers for CO2 reduction to methanol, methane, and formic acid. Among nine ML models evaluated with 14 intrinsic and DFT-based features, the XGBoost performed best (R2 = 0.92 and MAE = 0.24 eV), aligning closely with DFT calculations and identifying Ni, Ru, and Rh@GeSe as prospective catalysts. Feature importance analysis in free energy and product predictions highlighted the significance of CO2 activation with O-C-O and IPC-O1 as the key attributes. Furthermore, by incorporating non-DFT-based features, rapid predictions became possible, and the XGBoost model retained its predictive performance with R2 = 0.89 and MAE = 0.29 eV. This accuracy was further validated using Ir@GeSe. Our work highlights effective SACs for CO2RR, and provides valuable insights for efficient catalyst design.

physics.chem-ph↗

arXiv2025

Comment on "Hilbert's Sixth Problem: Derivation of Fluid Equations via Boltzmann's Kinetic Theory" by Deng, Hani, and Ma

Deng, Hani, and Ma [arXiv:2503.01800] claim to resolve Hilbert's Sixth Problem by deriving the Navier-Stokes-Fourier equations from Newtonian mechanics via an iterated limit: a Boltzmann-Grad limit ($\varepsilon \to 0$, $N \varepsilon^{d-1} = α$ fixed) yielding the Boltzmann equation, followed by a hydrodynamic limit ($α\to \infty$) to obtain fluid dynamics. Though mathematically rigorous, their approach harbors two critical physical flaws. First, the vanishing volume fraction ($N \varepsilon^d \to 0$) confines the system to a dilute gas, incapable of embodying dense fluid properties even as $α$ scales, rendering the resulting equations a rescaled gas model rather than a true continuum. Second, the Boltzmann equation's reliance on molecular chaos collapses in fluid-like regimes, where recollisions and correlations invalidate its derivation from Newtonian dynamics. These inconsistencies expose a disconnect between the formalism and the physical essence of fluids, failing to capture emergent, density-driven phenomena central to Hilbert's vision. We contend that the Sixth Problem remains open, urging a rethink of classical kinetic theory's limits and the exploration of alternative frameworks to unify microscale mechanics with macroscale fluid behavior.

math.AP↗

arXiv2025

Spatially-Heterogeneous Causal Bayesian Networks for Seismic Multi-Hazard Estimation: A Variational Approach with Gaussian Processes and Normalizing Flows

Post-earthquake hazard and impact estimation are critical for effective disaster response, yet current approaches face significant limitations. Traditional models employ fixed parameters regardless of geographical context, misrepresenting how seismic effects vary across diverse landscapes, while remote sensing technologies struggle to distinguish between co-located hazards. We address these challenges with a spatially-aware causal Bayesian network that decouples co-located hazards by modeling their causal relationships with location-specific parameters. Our framework integrates sensing observations, latent variables, and spatial heterogeneity through a novel combination of Gaussian Processes with normalizing flows, enabling us to capture how same earthquake produces different effects across varied geological and topographical features. Evaluations across three earthquakes demonstrate Spatial-VCBN achieves Area Under the Curve (AUC) improvements of up to 35.2% over existing methods. These results highlight the critical importance of modeling spatial heterogeneity in causal mechanisms for accurate disaster assessment, with direct implications for improving emergency response resource allocation.

stat.ML↗

arXiv2025

Multi-resolution Score-Based Variational Graphical Diffusion for Causal Disaster System Modeling and Inference

Complex systems with intricate causal dependencies challenge accurate prediction. Effective modeling requires precise physical process representation, integration of interdependent factors, and incorporation of multi-resolution observational data. These systems manifest in both static scenarios with instantaneous causal chains and temporal scenarios with evolving dynamics, complicating modeling efforts. Current methods struggle to simultaneously handle varying resolutions, capture physical relationships, model causal dependencies, and incorporate temporal dynamics, especially with inconsistently sampled data from diverse sources. We introduce Temporal-SVGDM: Score-based Variational Graphical Diffusion Model for Multi-resolution observations. Our framework constructs individual SDEs for each variable at its native resolution, then couples these SDEs through a causal score mechanism where parent nodes inform child nodes' evolution. This enables unified modeling of both immediate causal effects in static scenarios and evolving dependencies in temporal scenarios. In temporal models, state representations are processed through a sequence prediction model to predict future states based on historical patterns and causal relationships. Experiments on real-world datasets demonstrate improved prediction accuracy and causal understanding compared to existing methods, with robust performance under varying levels of background knowledge. Our model exhibits graceful degradation across different disaster types, successfully handling both static earthquake scenarios and temporal hurricane and wildfire scenarios, while maintaining superior performance even with limited data.

cs.LG↗

arXiv2025

Multispectral radiation temperature inversion based on Transformer-LSTM-SVM

The key challenge in multispectral radiation thermometry is accurately measuring emissivity. Traditional constrained optimization methods often fail to meet practical requirements in terms of precision, efficiency, and noise resistance. However, the continuous advancement of neural networks in data processing offers a potential solution to this issue. This paper presents a multispectral radiation thermometry algorithm that combines Transformer, LSTM (Long Short-Term Memory), and SVM (Support Vector Machine) to mitigate the impact of emissivity, thereby enhancing accuracy and noise resistance. In simulations, compared to the BP neural network algorithm, GIM-LSTM, and Transformer-LSTM algorithms, the Transformer-LSTM-SVM algorithm demonstrates an improvement in accuracy of 1.23%, 0.46% and 0.13%, respectively, without noise. When 5% random noise is added, the accuracy increases by 1.39%, 0.51%, and 0.38%, respectively. Finally, experiments confirmed that the maximum temperature error using this method is less than 1%, indicating that the algorithm offers high accuracy, fast processing speed, and robust noise resistance. These characteristics make it well-suited for real-time high-temperature measurements with multi-wavelength thermometry equipment.

physics.optics↗

arXiv2025

Challenges and recommendations for Electronic Health Records data extraction and preparation for dynamic prediction modelling in hospitalized patients -- a practical guide

Dynamic predictive modelling using electronic health record (EHR) data has gained significant attention in recent years. The reliability and trustworthiness of such models depend heavily on the quality of the underlying data, which is, in part, determined by the stages preceding the model development: data extraction from EHR systems and data preparation. In this article, we identified over forty challenges encountered during these stages and provide actionable recommendations for addressing them. These challenges are organized into four categories: cohort definition, outcome definition, feature engineering, and data cleaning. This comprehensive list serves as a practical guide for data extraction engineers and researchers, promoting best practices and improving the quality and real-world applicability of dynamic prediction models in clinical settings.

cs.LG↗

arXiv2025

Less is More: On the Importance of Data Quality for Unit Test Generation

Unit testing is crucial for software development and maintenance. Effective unit testing ensures and improves software quality, but writing unit tests is time-consuming and labor-intensive. Recent studies have proposed deep learning (DL) techniques or large language models (LLMs) to automate unit test generation. These models are usually trained or fine-tuned on large-scale datasets. Despite growing awareness of the importance of data quality, there has been limited research on the quality of datasets used for test generation. To bridge this gap, we systematically examine the impact of noise on the performance of learning-based test generation models. We first apply the open card sorting method to analyze the most popular and largest test generation dataset, Methods2Test, to categorize eight distinct types of noise. Further, we conduct detailed interviews with 17 domain experts to validate and assess the importance, reasonableness, and correctness of the noise taxonomy. Then, we propose CleanTest, an automated noise-cleaning framework designed to improve the quality of test generation datasets. CleanTest comprises three filters: a rule-based syntax filter, a rule-based relevance filter, and a model-based coverage filter. To evaluate its effectiveness, we apply CleanTest on two widely-used test generation datasets, i.e., Methods2Test and Atlas. Our findings indicate that 43.52% and 29.65% of datasets contain noise, highlighting its prevalence. Finally, we conduct comparative experiments using four LLMs (i.e., CodeBERT, AthenaTest, StarCoder, and CodeLlama7B) to assess the impact of noise on test generation performance. The results show that filtering noise positively influences the test generation ability of the models.

cs.SE↗

arXiv2025

The photography transforms and their analytic inversion formulas

The light field reconstruction from the focal stack can be mathematically formulated as an ill-posed integral equation inversion problem. Although the previous research about this problem has made progress both in practice and theory, its forward problem and inversion in a general form still need to be studied. In this paper, to model the forward problem rigorously, we propose three types of photography transforms with different integral geometry characteristics that extend the forward operator to the arbitrary $n$-dimensional case. We prove that these photography transforms are equivalent to the Radon transform with the coupling relation between variables. We also obtain some properties of the photography transforms, including the Fourier slice theorem, the convolution theorem, and the convolution property of the dual operator, which are very similar to those of the classic Radon transform. Furthermore, the representation of the normal operator and the analytic inversion formula for the photography transforms are derived and they are quite different from those of the classic Radon transform.

math.FA↗

arXiv2025

A no-go result for QBism

In QBism the wave function does not represent an element of physical reality external to the agent, but represent an agent's personal probability assignments, reflecting his subjective degrees of belief about the future content of his experience. In this paper, I argue that this view of the wave function is not consistent with protective measurements. The argument does not rely on the realist assumption of the psi-ontology theorems, namely the existence of the underlying ontic state of a quantum system.

quant-ph↗

arXiv2025

Can the ontology of Bohmian mechanics consists only in particles? The PBR theorem says no

The meaning of the wave function is an important unresolved issue in Bohmian mechanics. On the one hand, according to the nomological view, the wave function of the universe or the universal wave function is nomological, like a law of nature. On the other hand, the PBR theorem proves that the wave function in quantum mechanics or the effective wave function in Bohmian mechanics is ontic, representing the ontic state of a physical system in the universe. It is usually thought that the nomological view of the universal wave function is compatible with the ontic view of the effective wave function, and thus the PBR theorem has no implications for the nomological view. In this paper, I argue that this is not the case, and these two views are in fact incompatible. This means that if the effective wave function is ontic as the PBR theorem proves, then the universal wave function cannot be nomological, and the ontology of Bohmian mechanics cannot consist only in particles. This incompatibility result holds true not only for Humeanism and dispositionalism but also for primitivism about laws of nature, which attributes a fundamental ontic role to the universal wave function. Moreover, I argue that although the nomological view can be held by rejecting one key assumption of the PBR theorem, the rejection will lead to serious problems, such as that the results of measurements and their probabilities cannot be explained in ontology in Bohmian mechanics. Finally, I briefly discuss three psi-ontologies, namely a physical field in a fundamental high-dimensional space, a multi-field in three-dimensional space, and RDMP (Random Discontinuous Motion of Particles) in three-dimensional space, and argue that the RDMP ontology can answer the objections to the psi-ontology raised by the proponents of the nomological view.

quant-ph↗

arXiv2025

The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation

Test cases are essential for validating the reliability and quality of software applications. Recent studies have demonstrated the capability of Large Language Models (LLMs) to generate useful test cases for given source code. However, the existing work primarily relies on human-written plain prompts, which often leads to suboptimal results since the performance of LLMs can be highly influenced by the prompts. Moreover, these approaches use the same prompt for all LLMs, overlooking the fact that different LLMs might be best suited to different prompts. Given the wide variety of possible prompt formulations, automatically discovering the optimal prompt for each LLM presents a significant challenge. Although there are methods on automated prompt optimization in the natural language processing field, they are hard to produce effective prompts for the test case generation task. First, the methods iteratively optimize prompts by simply combining and mutating existing ones without proper guidance, resulting in prompts that lack diversity and tend to repeat the same errors in the generated test cases. Second, the prompts are generally lack of domain contextual knowledge, limiting LLMs' performance in the task.

cs.SE↗

arXiv2024

The Current Challenges of Software Engineering in the Era of Large Language Models

With the advent of large language models (LLMs) in the artificial intelligence (AI) area, the field of software engineering (SE) has also witnessed a paradigm shift. These models, by leveraging the power of deep learning and massive amounts of data, have demonstrated an unprecedented capacity to understand, generate, and operate programming languages. They can assist developers in completing a broad spectrum of software development activities, encompassing software design, automated programming, and maintenance, which potentially reduces huge human efforts. Integrating LLMs within the SE landscape (LLM4SE) has become a burgeoning trend, necessitating exploring this emergent landscape's challenges and opportunities. The paper aims at revisiting the software development life cycle (SDLC) under LLMs, and highlighting challenges and opportunities of the new paradigm. The paper first summarizes the overall process of LLM4SE, and then elaborates on the current challenges based on a through discussion. The discussion was held among more than 20 participants from academia and industry, specializing in fields such as software engineering and artificial intelligence. Specifically, we achieve 26 key challenges from seven aspects, including software requirement & design, coding assistance, testing code generation, code review, code maintenance, software vulnerability management, and data, training, and evaluation. We hope the achieved challenges would benefit future research in the LLM4SE field.

cs.SE↗

arXiv2024

APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments

Datasets play a pivotal role in training visual models, facilitating the development of abstract understandings of visual features through diverse image samples and multidimensional attributes. However, in the realm of aesthetic evaluation of artistic images, datasets remain relatively scarce. Existing painting datasets are often characterized by limited scoring dimensions and insufficient annotations, thereby constraining the advancement and application of automatic aesthetic evaluation methods in the domain of painting. To bridge this gap, we introduce the Aesthetics Paintings and Drawings Dataset (APDD), the first comprehensive collection of paintings encompassing 24 distinct artistic categories and 10 aesthetic attributes. Building upon the initial release of APDDv1, our ongoing research has identified opportunities for enhancement in data scale and annotation precision. Consequently, APDDv2 boasts an expanded image corpus and improved annotation quality, featuring detailed language comments to better cater to the needs of both researchers and practitioners seeking high-quality painting datasets. Furthermore, we present an updated version of the Art Assessment Network for Specific Painting Styles, denoted as ArtCLIP. Experimental validation demonstrates the superior performance of this revised model in the realm of aesthetic evaluation, surpassing its predecessor in accuracy and efficacy. The dataset and model are available at https://github.com/BestiVictory/APDDv2.git.

cs.CV↗

arXiv2024

AM$^3$: An Open-Source Tool for Time-Dependent Lepto-Hadronic Modeling of Astrophysical Sources

We present the AM$^3$ ("Astrophysical Multi-Messenger Modeling") software. AM$^3$ is a documented open source software that efficiently solves the coupled integro-differential equations describing the temporal evolution of the spectral densities of particles interacting in astrophysical environments, in-cluding photons, electrons, positrons, protons, neutrons, pions, muons, and neutrinos. The software has been extensively used to simulate the multi-wavelength and neutrino emission from active galactic nuclei (including blazars), gamma-ray bursts, and tidal disruption events. The simulations include all relevant non-thermal processes, namely synchrotron emission, inverse Compton scattering, photon-photon annihilation, proton-proton and proton-photon pion production, and photo-pair production. The software self-consistently calculates the full cascade of primary and secondary particles, including non-linear feedback processes and predictions in the time domain. It also allows to track separately the particle densities produced by means of each distinct interaction processes, including the different hadronic channels. With its efficient hybrid solver combining analytical and numerical techniques, AM$^3$ combines efficiency and accuracy at a user-adjustable level. We describe the technical details of the numerical framework and present three examples of applications to different astrophysical environments.

astro-ph.HE↗