arXiv subjects

Sicheng Liu

Publications and source records attributed to Sicheng Liu.

At least 19 recordsLinked to original sources

arXiv2026

UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation

Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coherence. Image-driven paradigms, which take UI screenshots as input, align more closely with real development workflows. However, current benchmarks focus primarily on visual fidelity and lack a systematic evaluation of the interaction capabilities in generated artifacts. To address this gap, we introduce UI2App, the first benchmark targeting interaction inference, the ability to recover application behavior from screenshots alone, without any textual or behavioral guidance. UI2App comprises 327 screenshots grouped into 45 state-coherent screenshot sets for runnable multi-route web applications. We design an end-to-end pipeline that evaluates each artifact along four dimensions: executability, navigation reachability, visual fidelity, and interaction inference. The interaction metric (IIS) assesses inferred interactions by functional correctness and state-management complexity, crediting any valid implementation rather than matching a single reference. Experiments on six frontier vision-language models reveal a marked capability mismatch between visual reconstruction and interaction realization: the visual-fidelity leader scores only 7.5 on IIS, ranking fourth and trailing the IIS leader by 5.2x. High-complexity interactions such as cross-page state remain a pervasive bottleneck, with half of the evaluated models scoring exactly zero on this dimension. Overall, the results indicate that inferring complete interaction behavior from static screenshots remains a key challenge for models.

cs.SE↗

arXiv2026

RDEx-CMOP: Feasibility-Aware Indicator-Guided Differential Evolution for Fixed-Budget Constrained Multiobjective Optimization

Constrained multiobjective optimisation requires fast feasibility attainment together with stable convergence and diversity preservation under strict evaluation budgets. This report documents RDEx-CMOP, the differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session) constrained multiobjective track. RDEx-CMOP integrates an {\epsilon}-level feasibility schedule, a SPEA2-style indicator-driven fitness assignment, and a fitness-oriented current-to-pbest/1 mutation operator. We evaluate RDEx-CMOP on the official CEC 2025 CMOP benchmark using the median-target U-score framework and the released trace data. Experimental results show that RDEx-CMOP achieves the highest total score and the best overall average rank among all released comparison algorithms, with strong target-attainment behaviour and near-zero final violation on most problems.

cs.NE↗

arXiv2026

RDEx-SOP: Exploitation-Biased Reconstructed Differential Evolution for Fixed-Budget Bound-Constrained Single-Objective Optimization

Bound-constrained single-objective numerical optimisation remains a key benchmark for assessing the robustness and efficiency of evolutionary algorithms. This report documents RDEx-SOP, an exploitation-biased success-history differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session). RDEx-SOP combines success-history parameter adaptation, an exploitation-biased hybrid branch, and lightweight local perturbations to balance fast convergence and final solution quality under a strict evaluation budget. We evaluate RDEx-SOP on the official CEC 2025 SOP benchmark with the U-score framework (Speed and Accuracy categories). Experimental results show that RDEx-SOP achieves strong overall performance and statistically competitive final outcomes across the 29 benchmark functions.

cs.NE↗

arXiv2026

RDEx-CSOP: Feasibility-Aware Reconstructed Differential Evolution with Adaptive epsilon-Constraint Ranking

Constrained single-objective numerical optimisation requires both feasibility maintenance and strong objective-value convergence under limited evaluation budgets. This report documents RDEx-CSOP, a constrained differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session). RDEx-CSOP combines success-history parameter adaptation with an exploitation-biased hybrid search and an {\epsilon}-constraint handling mechanism with a time-varying threshold. We evaluate RDEx-CSOP on the official CEC 2025 CSOP benchmark using the U-score framework (Speed, Accuracy, and Constraint categories). The results show that RDEx-CSOP achieves the highest total score and the best average rank among all released comparison algorithms, mainly through strong speed and competitive constraint-handling performance across the 28 benchmark functions.

cs.NE↗

arXiv2026

RDEx-MOP: Indicator-Guided Reconstructed Differential Evolution for Fixed-Budget Multiobjective Optimization

Multiobjective optimisation in the CEC 2025 MOP track is evaluated not only by final IGD values but also by how quickly an algorithm reaches the target region under a fixed evaluation budget. This report documents RDEx-MOP, the reconstructed differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session) bound-constrained multiobjective track. RDEx-MOP integrates indicator-based environmental selection, a niche-maintained Pareto-candidate set, and complementary differential evolution operators for exploration and exploitation. We evaluate RDEx-MOP on the official CEC 2025 MOP benchmark using the released checkpoint traces and the median-target U-score framework. Experimental results show that RDEx-MOP achieves the highest total score and the best average rank among all released comparison algorithms, including the earlier RDEx baseline.

cs.NE↗

arXiv2026

Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach

Graph Foundation Models (GFMs) have achieved remarkable success in generalizing across diverse domains. However, they mainly focus on Text-Attributed Graphs (TAGs), leaving Multimodal-Attributed Graphs (MAGs) largely untapped. Developing Multimodal Graph Foundation Models (MGFMs) allows for leveraging the rich multimodal information in MAGs, and extends applicability to broader types of downstream tasks. While recent MGFMs integrate diverse modality information, our empirical investigation reveals two fundamental limitations of existing MGFMs: (1)they fail to explicitly model modality interaction, essential for capturing intricate cross-modal semantics beyond simple aggregation, and (2)they exhibit sub-optimal modality alignment, which is critical for bridging the significant semantic disparity between distinct modal spaces. To address these challenges, we propose PLANET (graPh topoLogy-aware modAlity iNteraction and alignmEnT), a novel framework employing a Divide-and-Conquer strategy to decouple modality interaction and alignment across distinct granularities. At the embedding granularity, (1)Embedding-wise Domain Gating (EDG) performs local semantic enrichment by adaptively infusing topology-aware cross-modal context, achieving modality interaction. At the node granularity, (2)Node-wise Discretization Retrieval (NDR) ensures global modality alignment by constructing a Discretized Semantic Representation Space (DSRS) to bridge modality gaps. Extensive experiments demonstrate that PLANET significantly outperforms state-of-the-art baselines across diverse graph-centric and multimodal generative tasks.

cs.LG↗

arXiv2026

DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis

Recently, data-centric AI methodology has been a dominant paradigm in single-cell transcriptomics analysis, which treats data representation rather than model complexity as the fundamental bottleneck. In the review of current studies, earlier sequence methods treat cells as independent entities and adapt prevalent ML models to analyze their directly inherited sequence data. Despite their simplicity and intuition, these methods overlook the latent intercellular relationships driven by the functional mechanisms of biological systems and the inherent quality issues of the raw sequencing data. Therefore, a series of structured methods has emerged. Although they employ various heuristic rules to capture intricate intercellular relationships and enhance the raw sequencing data, these methods often neglect biological prior knowledge. This omission incurs substantial overhead and yields suboptimal graph representations, hindering the utility of ML models. To address these issues, we propose DOGMA, a data-centric framework designed for the structural reshaping and semantic enhancement of raw data through multi-level biological prior knowledge. Transcending reliance on purely data-driven heuristics, DOGMA provides a prior-guided graph construction pipeline that integrates statistical alignment with Cell Ontology and phylogenetic structure for biologically grounded cell-graph construction and robust cross-species alignment. Furthermore, Gene Ontology is utilized to bridge the feature-level semantic gap by incorporating functional priors. In complex multi-species and multi-organ benchmarks, DOGMA exhibits strong robustness in strict zero-shot cell-type evaluation and sample efficiency while using substantially lower GPU memory and inference time in downstream evaluation.

cs.LG↗

arXiv2025

Time-Averaged Drift Approximations are Inconsistent for Inference in Drift Diffusion Models

Drift diffusion models (DDMs) have found widespread use in computational neuroscience, cognitive science, mathematical psychology as well as other fields. They model evidence accumulation in simple decision tasks as a stochastic process drifting towards decision barriers. In models where the drift is both time-varying within a trial and variable across trials, the high computational cost for accurate likelihood evaluation has often led to the use of a computationally convenient surrogate for parameter inference, the time-averaged drift approximation (TADA). In each trial, TADA assumes that the time-varying drift rate can be replaced by its temporal average throughout the trial. This approach enables fast parameter inference using analytical likelihood formulas for DDMs with constant drift. In this work, we show that such an estimator is inconsistent: it does not converge to the true drift, posing a risk of biasing scientific conclusions when parameter estimates are obtained by TADA and similar approximations. We provide an elementary proof of this inconsistency in what is perhaps the simplest possible setting: a Brownian motion with piecewise constant drift hitting a one-sided upper boundary. Furthermore, numerical examples based on an attentional DDM (aDDM) show that using TADA leads to systematic misestimation of attentional effects in decision making and can lead to false conclusions in scientific hypothesis testing.

stat.ME↗

arXiv2025

Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models

Inspired by the success of LLMs, GFMs are designed to learn the optimal embedding functions from multi-domain text-attributed graphs for the downstream cross-task generalization capability. Among the diverse architectures, graph VQ-MAE stands out among the increasingly diverse landscape of GFM. This is attributed to its ability to jointly encode topology and textual attributes from multiple domains into discrete embedding spaces with clear semantic boundaries. Despite its potential, domain generalization conflicts cause imperceptible pitfalls. In this paper, we instantiate two of them, and they are just like two sides of the same GFM optimization coin - Side 1 Model Degradation: The encoder and codebook fail to capture the diversity of inputs; Side 2 Representation Collapse: The hidden embedding and codebook vector fail to preserve semantic separability due to constraints from narrow representation subspaces. These two pitfalls (sides) collectively impair the decoder and generate the low-quality reconstructed supervision, causing the GFM optimization dilemma during pre-training (coin). Through empirical investigation, we attribute the above challenges to Information Bottleneck and Regularization Deficit. To address them, we propose MoT - (1) Information Tinker for Two Pitfalls, which utilizes an edge-wise semantic fusion strategy and a mixture-of-codebooks with domain-aware routing to improve information capacity. (2) Regularization Tinker for Optimization Coin, which utilizes two additional regularizations to further improve gradient supervision in our proposed Information Tinker. Notably, as a flexible architecture, MoT adheres to the scaling laws of GFM, offering a controllable model scale. Compared to SOTA baselines, experiments on 22 datasets across 6 domains demonstrate that MoT achieves significant improvements in supervised, few-shot, and zero-shot scenarios.

cs.LG↗

arXiv2025

Interactions between Wind and Water Waves near Circular Flows

This manuscript concerns the dynamical interactions between wind and water waves, which are characterized through two-phase free interface problems for the Euler equations. We provide a comprehensive derivation on the linearized problems of general two-phase flows. Then, we study the instability issues of perturbing waves around circular steady solutions, and we demonstrate a semi-circle result on the possible locations of unstable modes. We also present necessary conditions and sufficient ones for the instability of wind-perturbing water waves near Taylor-Couette flows.

math.AP↗

arXiv2025

Temperature dependence of quasi-localized phonons-mediated non-Markovianity dynamics of SiV^- centers in diamond

Here we investigate the temperature-dependent non-Markovian dynamics of the SiV^- center in diamond, focusing on the roles of low- and high-frequency quasi-localized phonon modes. Low-frequency phonons exhibit stronger electron-phonon coupling, leading to long-lived dephasing rate, while high-frequency phonons induce rapid attenuation of oscillatory dephasing rate facilitating a persistent memory effect. The non-Markovianity measure N_C shows memory effects persisting at low temperatures but diminishing at high temperatures due to enhanced damping. The temperature dependence of N_C follows a monotonic decay, from which a transition temperature T_NM=110 K is determined. These results highlight the interplay between phonon activation and damping in shaping quantum coherence, offering insights for optimizing solid-state quantum systems.

physics.optics↗

arXiv2025

A Graph-Enhanced DeepONet Approach for Real-Time Estimating Hydrogen-Enriched Natural Gas Flow under Variable Operations

Blending green hydrogen into natural gas presents a promising approach for renewable energy integration and fuel decarbonization. Accurate estimation of hydrogen fraction in hydrogen-enriched natural gas (HENG) pipeline networks is crucial for operational safety and efficiency, yet it remains challenging due to complex dynamics. While existing data-driven approaches adopt end-to-end architectures for HENG flow state estimation, their limited adaptability to varying operational conditions hinders practical applications. To this end, this study proposes a graph-enhanced DeepONet framework for the real-time estimation of HENG flow, especially hydrogen fractions. First, a dual-network architecture, called branch network and trunk network, is employed to characterize operational conditions and sparse sensor measurements to estimate the HENG state at targeted locations and time points. Second, a graph-enhance branch network is proposed to incorporate pipeline topology, improving the estimation accuracy in large-scale pipeline networks. Experimental results demonstrate that the proposed method achieves superior estimation accuracy for HCNG flow under varying operational conditions compared to conventional approaches.

cs.LG↗

arXiv2025

IRS Assisted Decentralized Learning for Wideband Spectrum Sensing

The increasing demand for reliable connectivity in industrial environments necessitates effective spectrum utilization strategies, especially in the context of shared spectrum bands. However, the dynamic spectrum-sharing mechanisms often lead to significant interference and critical failures, creating a trade-off between spectrum scarcity and under-utilization. This paper addresses these challenges by proposing a novel Intelligent Reflecting Surface (IRS)-assisted spectrum sensing framework integrated with decentralized deep learning. The proposed model overcomes partial observation constraints and minimizes communication overhead while leveraging IRS technology to enhance spectrum sensing accuracy. Through comprehensive simulations, the framework demonstrates its ability to monitor wideband spectrum occupancy effectively, even under challenging signal-to-noise ratio (SNR) conditions. This approach offers a scalable and robust solution for spectrum management in next-generation wireless networks.

eess.SY↗

arXiv2025

On the 2D Plasma-Vacuum Interface Problems for Ideal Incompressible MHD

This manuscript concerns the stability conditions for the well-posedness of the two-dimensional plasma-vacuum interface problems for ideal incompressible magnetohydrodynamics (MHD) equations, which describe the dynamics of conducting perfect fluids in a vacuum region under the influence of magnetic fields. Due to the counterexamples constructed by C. Hao and the second author [Comm. Math. Phys. 376 (2020), 259-286], the plasma-vacuum problems violating the Rayleigh-Taylor sign condition and without surface tension are believed to be highly unstable or even ill-posed. However, based on a geometric perspective, we demonstrate that, although the initial data provided therein are ill-posed in the Lagrangian framework characterizing the regularity of flow maps, plasma-vacuum problems with such initial data can still be stable/well-posed in the Eulerian setting without involving flow maps, under the hypothesis that the total magnetic fields are non-degenerate on the free boundary. This discloses the essential difference between the Eulerian and Lagrangian frameworks of MHD free boundary problems and the stabilizing effect of the magnetic field. We also consider the surface tension effect and establish the local well-posedness theories in standard Sobolev spaces in this case. Furthermore, under either the non-degeneracy assumption on magnetic fields or the Rayleigh-Taylor sign condition on the effective pressure, we prove vanishing surface tension limits. These results indicate that both capillary forces and non-degenerate tangential magnetic fields can stabilize the motion of the plasma-vacuum interface, and the stabilizing effect of surface tension is stronger than that of the tangential magnetic fields.

math.AP↗

arXiv2025

Efficient Inference in First Passage Time Models

First passage time models describe the time it takes for a random process to exit a region of interest and are widely used across various scientific fields. Fast and accurate numerical methods for computing the likelihood function in these models are essential for efficient statistical inference of model parameters. Specifically, in computational cognitive neuroscience, generalized drift diffusion models (GDDMs) are an important class of first passage time models that describe the latent psychological processes underlying simple decision-making scenarios. GDDMs model the joint distribution over choices and response times as the first hitting time of a one-dimensional stochastic differential equation (SDE) to possibly time-varying upper and lower boundaries. They are widely applied to extract parameters associated with distinct cognitive and neural mechanisms. However, current likelihood computation methods struggle in common application scenarios in which drift rates dynamically vary within trials as a function of exogenous covariates (e.g., brain activity in specific regions or visual fixations). In this work, we propose a fast and flexible algorithm for computing the likelihood function of GDDMs based on a large class of SDEs satisfying the Cherkasov condition. Our method divides each trial into discrete stages, employs fast analytical results to compute stage-wise densities, and integrates these to compute the overall trial-wise likelihood. Numerical examples demonstrate that our method not only yields accurate likelihood evaluations for efficient statistical inference, but also considerably outperforms existing approaches in terms of speed.

stat.ME↗

arXiv2024

SITransformer: Shared Information-Guided Transformer for Extreme Multimodal Summarization

Extreme Multimodal Summarization with Multimodal Output (XMSMO) becomes an attractive summarization approach by integrating various types of information to create extremely concise yet informative summaries for individual modalities. Existing methods overlook the issue that multimodal data often contains more topic irrelevant information, which can mislead the model into producing inaccurate summaries especially for extremely short ones. In this paper, we propose SITransformer, a Shared Information-guided Transformer for extreme multimodal summarization. It has a shared information guided pipeline which involves a cross-modal shared information extractor and a cross-modal interaction module. The extractor formulates semantically shared salient information from different modalities by devising a novel filtering process consisting of a differentiable top-k selector and a shared-information guided gating unit. As a result, the common, salient, and relevant contents across modalities are identified. Next, a transformer with cross-modal attentions is developed for intra- and inter-modality learning with the shared information guidance to produce the extreme summary. Comprehensive experiments demonstrate that SITransformer significantly enhances the summarization quality for both video and text summaries for XMSMO. Our code will be publicly available at https://github.com/SichengLeoLiu/MMAsia24-XMSMO.

cs.CV↗

arXiv2024

Physical Vacuum Problems for the Full Compressible Euler Equations: Low-regularity Hadamard-style Local Well-posedness

This manuscript concerns the dynamics of non-isentropic compressible Euler equations in a physical vacuum. We establish the Hadamard-style local well-posedness in low-regularity weighted Sobolev spaces, where the gas-vacuum interface is allowed to have unbounded curvature, demonstrating existence, uniqueness, and continuous dependence on initial data. Additionally, we prove sharp a priori energy estimates and continuation criteria. The approach is based on the framework of Eulerian coordinates, avoiding the regularity issues of the flow map and the high nonlinearity induced by the Lagrangian transformation.

math.AP↗

arXiv2024

Optimal Hardening Strategy for Electricity-Hydrogen Networks with Hydrogen Leakage Risk Control against Extreme Weather

Defense hardening can effectively enhance the resilience of distribution networks against extreme weather disasters. Currently, most existing hardening strategies focus on reducing load shedding. However, for electricity-hydrogen distribution networks (EHDNs), the leakage risk of hydrogen should be controlled to avoid severe incidents such as explosions. To this end, this paper proposes an optimal hardening strategy for EHDNs under extreme weather, aiming to minimize load shedding while limiting the leakage risk of hydrogen pipelines. Specifically, modified failure uncertainty models for power lines and hydrogen pipelines are developed. These models characterize not only the effect of hardening, referred to as decision-dependent uncertainties (DDUs), but also the influence of disaster intensity correlations on failure probability distributions. Subsequently, a hardening decision framework is established, based on the two-stage distributionally robust optimization incorporating a hydrogen leakage chance constraint (HLCC). To enhance the computational efficiency of HLCC under discrete DDUs, an efficient second-order-cone transformation is introduced. Moreover, to address the intractable inverse of the second-order moment under DDUs, lifted variables are adopted to refine the main-cross moments. These reformulate the hardening problem as a two-stage mixed-integer second-order-cone programming, and finally solved by the column-and-constraint generation algorithm. Case studies demonstrate the effectiveness and superiority of the proposed method.

eess.SY↗