arXiv subjects

Yulin Pan

Publications and source records attributed to Yulin Pan.

At least 19 recordsLinked to original sources

arXiv2026

Variational Goal-Oriented Optimal Experimental Design for Mixed-Distribution Quantities of Interest: Application to Ship Roll Safety

Goal-oriented optimal experimental design (GO-OED) selects experiments according to the expected information gain (EIG) about a quantity of interest (QoI) rather than the full parameter vector. This work develops a variational GO-OED formulation for mixed discrete-continuous QoI laws arising in probabilistic mechanics when thresholding or event-based transformations map a positive-probability set of uncertain inputs to a common value while other inputs produce continuously varying responses. The motivating application is ship roll safety assessment in random waves, where the QoI is the temporal exceedance probability above a prescribed roll-angle threshold. This quantity is zero when no exceedance occurs and varies continuously over positive values otherwise. A purely continuous variational approximation does not dominate a posterior QoI law containing an atom, yielding an infinite Kullback-Leibler divergence and a trivial Barber-Agakov lower bound of $-\infty$. Scoring atom samples using continuous density values instead changes the objective and does not produce a valid lower-bound estimator. We introduce a mixed variational approximation that models the conditional atom probability and continuous component separately, with a normalizing flow used for the latter. An analytical example recovers the correct EIG landscape, while the ship roll application provides stable EIG lower-bound estimates and identifies informative wave conditions for temporal-exceedance-probability inference.

stat.ME↗

arXiv2026

Dissipation-driven champion solitons in one-dimensional shallow-water waves

In this paper, we identify a new mechanism for rogue wave formation in a shallow-water setting. We study a bidirectional shallow-water wave field in the context of the Kaup-Boussinesq equation, and introduce a weak high-wavenumber dissipative perturbation that breaks the underlying integrability of the system. In this setting, dominant solitons grow through successive interactions with weaker, co-propagating solitons, leading to the formation of a "champion soliton" in each direction of propagation. This behaviour is in contrast to the general intuition that dissipation damps coherent structures, and instead shows that weak dissipation can induce their intensification. Moreover, we find that weak dissipation alone is not sufficient for champion soliton formation; the presence of random waves plays a crucial role in the intensification process, catalysing the transfer of energy into dominant coherent structures. While champion solitons have previously been studied in non-integrable systems, these works primarily consider perturbations introduced through modifications of the nonlinear terms (e.g., higher-order Korteweg-de Vries and Schr\"odinger-type models). In the present work, high-wavenumber dissipation provides a more physically natural perturbation, since such small-scale damping is a common feature in many systems.

nlin.PS↗

arXiv2026

Distribution and Transport of Fragmenting Microplastics in a 3D Global Eulerian Model

Fragmentation, the breakage of matter into smaller pieces, is an important mechanism responsible for generating microplastics (MPs). We present the first global three-dimensional Eulerian model that resolves fragmentation alongside MP transport. The evolution of particle size is modeled as a transfer from larger- to smaller-size bins, governed by a fragmentation kinetics framework. Relative to a reference simulation without fragmentation, two distinct effects are identified: (1) the surface concentration field of MPs becomes horizontally dispersed, and (2) MPs sink to depths of 500 m where the reference simulation shows negligible concentration. The vertical shift can be explained by the loss of buoyancy when particle size decreases, which facilitates horizontal sub-mixed layer transport once the particles sink below 100 m depth. Neutrally buoyant particles (with diameter d < 1 um) are continuously produced in the ocean by the fragmentation of larger particles and accumulate in the major oceanic gyres. Ultimately, the concentration of these neutrally buoyant MPs peaks at the gyre centers, a behavior that is not captured by prior models. Furthermore, the globally integrated size spectrum exhibits a steepening power-law slope over time that continues to evolve throughout our 25-year simulation. Comparisons with the AOMI Level-3wm observational dataset demonstrate a meaningful improvement in predictive skill relative to previous models: including fragmentation elevates the spatial correlation between modeled and observed surface concentrations from 45% to 58%.

physics.ao-ph↗

arXiv2026

Effect of Biofouling on Microplastic Transport in a 3-D Global Eulerian Model

Biofouling -- the occupation of microplastic (MP) surfaces by marine microbes -- alters particles' buoyancy and transport, yet its effect on the global distribution of MPs has not been well quantified. We present the first three-dimensional global Eulerian model to fully couple MP transport with biofouling, by augmenting the concentration field with an extra dimension representing the biomass attachment density on MP surfaces. This approach embeds time-dependent particle properties directly into the Eulerian concentration field, overcoming a fundamental challenge of tracking property evolution in grid-based models. Idealized simulations show that biofouling significantly reshapes the vertical distribution of MPs when two conditions are met: the particles must be sufficiently buoyant when they are clean to remain near the sea surface, and the local plankton growth rate must exceed the decay rate. In three-dimensional global simulations, biofouling substantially alters the distribution of large MPs ($\gtrsim 10$ $\mu$m): biofouled particles are transported below the mixed layer to 500 m depth, and the subtropical surface garbage patches become more dispersed with reduced peak concentrations. This dispersion is due to a subsurface transport route, where biofouled particles sink into layers with reversed current and are carried outward from the gyre centers before regaining buoyancy. Small particles ($\lesssim 1$ $\mu$m) remain unaffected as they stay effectively neutrally buoyant even when biofouled. A comparison with a global trawler dataset shows that incorporating biofouling reduces the fraction of outlying model-observation data points from 25\% to 13\%, demonstrating a meaningful improvement in model skill.

physics.flu-dyn↗

arXiv2026

Wan-Image: Pushing the Boundaries of Generative Visual Intelligence

We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at aesthetic generation, they frequently encounter critical bottlenecks in rigorous design workflows that demand absolute controllability, complex typography rendering, and strict identity preservation. To address these challenges, Wan-Image features a natively unified multi-modal architecture by synergizing the cognitive capabilities of large language models with the high-fidelity pixel synthesis of diffusion transformers, which seamlessly translates highly nuanced user intents into precise visual outputs. It is fundamentally powered by large-scale multi-modal data scaling, a systematic fine-grained annotation engine, and curated reinforcement learning data to surpass basic instruction following and unlock expert-level professional capabilities. These include ultra-long complex text rendering, hyper-diverse portrait generation, palette-guided generation, multi-subject identity preservation, coherent sequential visual generation, precise multi-modal interactive editing, native alpha-channel generation, and high-efficiency 4K synthesis. Across diverse human evaluations, Wan-Image exceeds Seedream 5.0 Lite and GPT Image 1.5 in overall performance, reaching parity with Nano Banana Pro in challenging tasks. Ultimately, Wan-Image revolutionizes visual content creation across e-commerce, entertainment, education, and personal productivity, redefining the boundaries of professional visual synthesis.

cs.CV↗

arXiv2026

Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training

Recent unified models have made unprecedented progress in both understanding and generation. However, while most of them accept multi-modal inputs, they typically produce only single-modality outputs. This challenge of producing interleaved content is mainly due to training data scarcity and the difficulty of modeling long-range cross-modal context. To address this issue, we decompose interleaved generation into textual planning and visual consistency modeling, and introduce a framework consisting of a planner and a visualizer. The planner produces dense textual descriptions for visual content, while the visualizer synthesizes images accordingly. Under this guidance, we construct large-scale textual-proxy interleaved data (where visual content is represented in text) to train the planner, and curate reference-guided image data to train the visualizer. These designs give rise to Wan-Weaver, which exhibits emergent interleaved generation ability with long-range textual coherence and visual consistency. Meanwhile, the integration of diverse understanding and generation data into planner training enables Wan-Weaver to achieve robust task reasoning and generation proficiency. To assess the model's capability in interleaved generation, we further construct a benchmark that spans a wide range of use cases across multiple dimensions. Extensive experiments demonstrate that, even without access to any real interleaved data, Wan-Weaver achieves superior performance over existing methods.

cs.CV↗

arXiv2026

Local-in-Time Existence of $L^1$ solutions to the Gravity Water Wave Kinetic Equation

In this paper, we study the Cauchy problem for the four-wave kinetic equation describing the weak turbulence of gravity water waves. The mathematical challenges of this analysis stem primarily from two interrelated aspects: (1) the extreme algebraic complexity of the collision kernel, where controlling its growth in the highly non-local regime constitutes the primary analytical bottleneck, and (2) the construction of strong solutions under the resulting singular integral operators. First, we re-analyze the interaction kernel in this precise regime, where the interacting wave numbers satisfy $|k|, |k_3| \gg |k_1|, |k_2|$. We establish a rigorous upper bound of $\mathcal{O}(|k||k_3|)$, which rigorously verifies the asymptotic smallness of the interaction coefficient anticipated in the physics literature \cite{zakharov2010energy, geogjaev2017numerical, geogjaev2025properties}. Furthermore, this result improves upon the recent $\mathcal{O}\big((|k||k_3|)^{3/2}\big)$ estimate proposed in \cite{waterkernel2024}, demonstrating a strictly milder singularity of wave interactions in this limit. Physically, this regime governs the energy exchange between disparate scales, such as the modulation of short gravity waves by long ocean swells. Second, leveraging this crucial integrability gain alongside a refined structural decomposition of the collision operator, we establish the local-in-time existence of $L^1$ strong solutions to the gravity water kinetic equation for initial data in a suitably weighted $L^2 \cap L^\infty$ space. Specifically, we prove that for any initial data in this class, the resulting $L^1$ strong solution strictly propagates the weighted $L^2 \cap L^\infty$ regularity and conserves the fundamental physical properties of the kinetic model.

math.AP↗

arXiv2026

Bidirectional shallow-water wave turbulence

We study bidirectional one-dimensional (1-D) shallow-water waves within a class of Boussinesq equations, including the integrable Kaup-Boussinesq (KB) equation and a truncated-dispersion variant, which serves as a representative non-integrable model. For these two systems, the normal-form transformation yields an interaction coefficient of the same general structure, differing only through the dispersion relation. We derive this coefficient and numerically confirm that it vanishes on the resonant manifold for the KB equation, as expected in the literature. In contrast, the non-integrable model admits a non-vanishing interaction coefficient, producing a non-trivial wave kinetic equation (WKE), which is the first known in a 1-D shallow-water setting. The resulting WKE is non-homogeneous in nature due to the non-homogeneity of the corresponding dispersion relation; however, approximate Kolomogrov-Zakharov (KZ) solutions can be derived in a novel way under certain approximations. Numerical experiments in two settings validate the kinetic predictions and elucidate the underlying dynamics: (i) in free-evolution cases of the KB equation, despite complete integrability and the invariance of the discrete nonlinear spectrum guaranteed by isospectrality, an initial arbitrary wavenumber spectrum undergoes substantial evolution driven by quasi-resonant triad interactions; (ii) in forced-dissipated cases of the non-integrable equation, we find stationary power-law spectra that agree with the theoretical predictions.

nlin.CD↗

arXiv2025

Impact of Wave Interference on the Consistency Relations of Internal Gravity Waves near the Ocean Bottom

Consistency relations of internal gravity waves (IGWs) describe ratios of cross-spectral quantities as functions of frequency. It has been a common practice to evaluate the measured or simulated signals (e.g., time series of velocity, density, etc.) against the consistency relations, as a way to determine whether an oceanic field of interest is comprised of IGWs. One such study is carried out in Nelson et al. (JGR Oceans, 125(5), 2020, e2019JC015974), which certifies that the ocean interior field in a numerical simulation of a region southwest of Hawaii is dominated by IGWs, through evaluating the consistency relations derived from time series at a depth of 620 m. However, we find that when the same procedure is applied at greater depths (e.g., 2362 m, 3062 m, and 4987 m), a clear deviation of the simulated signal from the classical consistency relations is observed. In this paper, we identify the reason for the unexpected deviation and show that it is a general phenomenon due to interference of low vertical modes under the reflection by the ocean bottom. We further derive a new set of formulae to characterize the consistency relations of these low modes and validate these formulae using model output.

physics.ao-ph↗

arXiv2025

Space-time resonances in the spatiotemporal spectrum of nonlinear dispersive waves

In weakly nonlinear dispersive wave systems, long-time dynamics are typically governed by time resonances, where wave phases evolve coherently due to exact frequency matching. Recent advances in spatio-temporal spectrum measurements, however, reveal prominent features that go beyond the predictions of time resonance theory. In this work, we develop a theoretical framework to interpret these signatures by identifying and characterizing an alternative mechanism: space resonances. These arise when wave packets share the same group velocity and remain co-located, leading to long-lived interactions. We further show that gauge-breaking terms in the Hamiltonian give rise to space resonances supported on negative frequencies. By combining sea-surface elevation data, numerical simulations, and analytical theory, we derive the leading-order spatio-temporal spectrum for weakly interacting water waves, providing a unified explanation for its observed features.

nlin.PS↗

arXiv2025

Validity condition of normal form transformation for the $\beta$-FPUT system

In this work, we provide a validity condition for the normal form transformation to remove the non-resonant cubic terms in the $\beta$-FPUT system. We show that for a wave field with random phases, the normal form transformation is valid by dominant probability if $\beta \ll 1/N^{1+\epsilon}$, with $N$ the number of masses and $\epsilon$ an arbitrarily small constant. To obtain this condition, a bound is needed for a summation in the transformation equation, which we prove rigorously in the paper. The condition also suggests that the importance of the non-resonant terms in the evolution equation is governed by the parameter $\beta N$. We design numerical experiments to demonstrate that this is indeed the case for spectra at both thermal-equilibrium and out-of-equilibrium conditions. The methodology developed in this paper is applicable to other Hamiltonian systems where a normal form transformation needs to be applied.

math-ph↗

arXiv2025

Efficient Estimation of Temporal Exceeding Probability for Ship Responses in Broadband Wave Fields

In this paper, we develop an efficient method to evaluate the temporal exceeding probability of ship motion (percentage of time for the ship motion to be above a given high threshold) in an irregular wave field. Our method builds on our previous work of Gong et al. (Applied Ocean Research, 2022), which converts the calculation into a sampling problem in the space of wave group parameters, within which an acquisition-based sequential sampling method is developed to reduce the number of required samples. Two critical advancements are achieved in this paper relative to that work. (1) We develop a new wave group parameterization method, which allows the framework to be applied to general broadband wave fields. (2) We incorporate the variability regarding each parameterized wave group (e.g. varying wave form and initial condition of the ship encountering the group) into the final estimation of a single value of the temporal exceeding probability. Our complete framework is tested for a ship subject to a wave field with a JONSWAP spectrum, for different ship motion dynamical models, spectral bandwidths, and exceeding thresholds. The results show that for most cases our method provides a result with O(15%) error or below within 210 samples, with the ground truth obtained from a continuous simulation that is more than 2300 times more expensive than our method. We also demonstrate the benefits of sequential sampling (with an acquisition function updated due to (2)) compared to standard random or Latin hypercube (LH) samplings, in terms of the mean error of the results.

physics.flu-dyn↗

arXiv2025

Induced Diffusion of Internal Gravity Waves: Directionality and Role in Ocean Mixing

Induced diffusion (ID), an important mechanism of spectral energy transfer in the internal gravity wave (IGW) field, plays a significant role in driving turbulent dissipation in the ocean interior. In this study, we revisit the ID mechanism to elucidate its directionality and role in ocean mixing under varying IGW spectral forms, with particular attention to deviations from the standard Garrett-Munk (GM) spectrum. The original interpretation of ID as an action diffusion process, as proposed by McComas et al., suggests that ID is inherently bidirectional, with its direction governed by the vertical-wavenumber spectral slope $\sigma$ of the IGW action spectrum, $n \propto m^\sigma$. In contrast, by evaluating the wave kinetic equation, we reveal a more complete depiction of ID, comprising both diffusive and scale-separated transfers that are rooted in energy conservation within wave triads. Although the action diffusion may reverse direction depending on the sign of $\sigma$ (i.e., between red and blue spectral cases), the combined ID transfer consistently leads to a forward energy cascade at the dissipation scale, thereby contributing positively to turbulent dissipation. This supports the viewpoint of ID as a dissipative mechanism in physical oceanography. This study presents a physically grounded overview of ID and offers insights into the specific types of wave-wave interactions responsible for turbulent dissipation.

physics.ao-ph↗

arXiv2025

Data Assimilation-based Simultaneous Phase-Resolved Ocean Wave and Ship Motion Forecast

This paper presents a data-assimilation (DA)-based approach to forecast the phase-resolved wave evolution process and ship motion, which is developed by coupling the high-order spectral method (HOS), ensemble Kalman filter (EnKF), and a Cummins-equation-based ship model (CMI). With the developed EnKF-HOS-CMI method, the observation data for wave, ship, or both can be incorporated into the model, therefore producing the optimal analysis results. The developed method is validated and tested based on a synthetic problem on the motions of an irregular wave field and a box-shaped free-floating ship. We show that the EnKF-HOS-CMI method achieves much higher accuracy in the long-term simulation of nonlinear phase-resolved wave field and ship motion in comparison with the HOS-CMI method. Also, the ship parameters are estimated accurately by using a parameter-augmented state space in EnKF.

eess.SY↗

arXiv2025

Wan: Open and Advanced Large-Scale Video Generative Models

This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1.

cs.CV↗

arXiv2025

ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editing

Image generation has witnessed significant advancements in the past few years. However, evaluating the performance of image generation models remains a formidable challenge. In this paper, we propose ICE-Bench, a unified and comprehensive benchmark designed to rigorously assess image generation models. Its comprehensiveness could be summarized in the following key features: (1) Coarse-to-Fine Tasks: We systematically deconstruct image generation into four task categories: No-ref/Ref Image Creating/Editing, based on the presence or absence of source images and reference images. And further decompose them into 31 fine-grained tasks covering a broad spectrum of image generation requirements, culminating in a comprehensive benchmark. (2) Multi-dimensional Metrics: The evaluation framework assesses image generation capabilities across 6 dimensions: aesthetic quality, imaging quality, prompt following, source consistency, reference consistency, and controllability. 11 metrics are introduced to support the multi-dimensional evaluation. Notably, we introduce VLLM-QA, an innovative metric designed to assess the success of image editing by leveraging large models. (3) Hybrid Data: The data comes from real scenes and virtual generation, which effectively improves data diversity and alleviates the bias problem in model evaluation. Through ICE-Bench, we conduct a thorough analysis of existing generation models, revealing both the challenging nature of our benchmark and the gap between current model capabilities and real-world generation requirements. To foster further advancements in the field, we will open-source ICE-Bench, including its dataset, evaluation code, and models, thereby providing a valuable resource for the research community.

cs.CV↗

arXiv2025

VACE: All-in-One Video Creation and Editing

Diffusion Transformer has demonstrated powerful capability and scalability in generating high-quality images and videos. Further pursuing the unification of generation and editing tasks has yielded significant progress in the domain of image content creation. However, due to the intrinsic demands for consistency across both temporal and spatial dynamics, achieving a unified approach for video synthesis remains challenging. We introduce VACE, which enables users to perform Video tasks within an All-in-one framework for Creation and Editing. These tasks include reference-to-video generation, video-to-video editing, and masked video-to-video editing. Specifically, we effectively integrate the requirements of various tasks by organizing video task inputs, such as editing, reference, and masking, into a unified interface referred to as the Video Condition Unit (VCU). Furthermore, by utilizing a Context Adapter structure, we inject different task concepts into the model using formalized representations of temporal and spatial dimensions, allowing it to handle arbitrary video synthesis tasks flexibly. Extensive experiments demonstrate that the unified model of VACE achieves performance on par with task-specific models across various subtasks. Simultaneously, it enables diverse applications through versatile task combinations. Project page: https://ali-vilab.github.io/VACE-Page/.

cs.CV↗

arXiv2025

ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling

We report ACE++, an instruction-based diffusion framework that tackles various image generation and editing tasks. Inspired by the input format for the inpainting task proposed by FLUX.1-Fill-dev, we improve the Long-context Condition Unit (LCU) introduced in ACE and extend this input paradigm to any editing and generation tasks. To take full advantage of image generative priors, we develop a two-stage training scheme to minimize the efforts of finetuning powerful text-to-image diffusion models like FLUX.1-dev. In the first stage, we pre-train the model using task data with the 0-ref tasks from the text-to-image model. There are many models in the community based on the post-training of text-to-image foundational models that meet this training paradigm of the first stage. For example, FLUX.1-Fill-dev deals primarily with painting tasks and can be used as an initialization to accelerate the training process. In the second stage, we finetune the above model to support the general instructions using all tasks defined in ACE. To promote the widespread application of ACE++ in different scenarios, we provide a comprehensive set of models that cover both full finetuning and lightweight finetuning, while considering general applicability and applicability in vertical scenarios. The qualitative analysis showcases the superiority of ACE++ in terms of generating image quality and prompt following ability. Code and models will be available on the project page: https://ali-vilab. github.io/ACE_plus_page/.

cs.CV↗