Searcharxiv⌕ Search

arXiv subjects

Zhifei Zhang

Publications and source records attributed to Zhifei Zhang.

At least 91 records · Page 5Linked to original sources

Global well-posedness and self-similar solution of the inhomogeneous Navier-Stokes system

In this paper, we study the global well-posedness of the 3-D inhomogeneous incompressible Navier-Stokes system (INS in short) with initial density $ρ_0$ being discontinuous and initial velocity $u_0$ belonging to some critical space. Firstly, if $ρ_0u_0$ is sufficiently small in the space $\dot{B}^{-1+\frac{3}{p}}_{p,\infty}(\mathbb{R}^3)$ and $ρ_0$ is close enough to a positive constant in $L^\infty$, we establish the global existence of strong solution to (INS) for $3<p<\infty$ and provide the uniqueness of the solution for $3<p<6$. This result corresponds to Cannone-Meyer-Planchon solution of the classical Navier-Stokes system. Furthermore, with the additional assumption that $u_0\in L^2(\mathbb{R}^3)$, we prove the weak-strong uniqueness between Cannone-Meyer-Planchon solution and Lions weak solution of (INS). Finally, we prove the global well-posedness of (INS) with $u_0\in \dot{B}^{\frac{1}{2}}_{2,\infty}(\mathbb{R}^3)$ being small and only an upper bound on the density. This gives the first existence result of the forward self-similar solution for (INS).

math.AP↗

A new proof of nonlinear Landau damping for the 3D Vlasov-Poisson system near Poisson equilibrium

This paper investigates nonlinear Landau damping in the 3D Vlasov-Poisson (VP) system. We study the asymptotic stability of the Poisson equilibrium $μ(v)=\frac{1}{π^2(1+|v|^2)^2}$ under small perturbations. Building on the foundational work of Ionescu, Pausader, Wang, and Widmayer \cite{AIonescu2022}, we provide a streamlined proof of nonlinear Landau damping for the 3D unscreened VP system. Our analysis leverages sharp decay estimates, novel decomposition techniques to demonstrate the stabilization of the particle distribution and the decay of electric field. These results reveal the free transport-like behavior for the perturbed density $ρ(t,x)$, and enhance the understanding of Landau damping in an unconfined setting near stable equilibria.

math.AP↗

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering, and cross-modal retrieval. Despite their superior capabilities, VLMs struggle with fine-grained image regional composition information perception. Specifically, they have difficulty accurately aligning the segmentation masks with the corresponding semantics and precisely describing the compositional aspects of the referred regions. However, compositionality - the ability to understand and generate novel combinations of known visual and textual components - is critical for facilitating coherent reasoning and understanding across modalities by VLMs. To address this issue, we propose FINECAPTION, a novel VLM that can recognize arbitrary masks as referential inputs and process high-resolution images for compositional image captioning at different granularity levels. To support this endeavor, we introduce COMPOSITIONCAP, a new dataset for multi-grained region compositional image captioning, which introduces the task of compositional attribute-aware regional image captioning. Empirical results demonstrate the effectiveness of our proposed model compared to other state-of-the-art VLMs. Additionally, we analyze the capabilities of current VLMs in recognizing various visual prompts for compositional region image captioning, highlighting areas for improvement in VLM design and training.

cs.CV↗

SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing

Effective editing of personal content holds a pivotal role in enabling individuals to express their creativity, weaving captivating narratives within their visual stories, and elevate the overall quality and impact of their visual content. Therefore, in this work, we introduce SwapAnything, a novel framework that can swap any objects in an image with personalized concepts given by the reference, while keeping the context unchanged. Compared with existing methods for personalized subject swapping, SwapAnything has three unique advantages: (1) precise control of arbitrary objects and parts rather than the main subject, (2) more faithful preservation of context pixels, (3) better adaptation of the personalized concept to the image. First, we propose targeted variable swapping to apply region control over latent feature maps and swap masked variables for faithful context preservation and initial semantic concept swapping. Then, we introduce appearance adaptation, to seamlessly adapt the semantic concept into the original image in terms of target location, shape, style, and content during the image generation process. Extensive results on both human and automatic evaluation demonstrate significant improvements of our approach over baseline methods on personalized swapping. Furthermore, SwapAnything shows its precise and faithful swapping abilities across single object, multiple objects, partial object, and cross-domain swapping tasks. SwapAnything also achieves great performance on text-based swapping and tasks beyond swapping such as object insertion.

cs.CV↗

Local large deviations for randomly forced nonlinear wave equations with localized damping

We study the large deviation principle (LDP) for locally damped nonlinear wave equations perturbed by a bounded noise. When the noise is sufficiently non-degenerate, we establish the LDP for empirical distributions with lower bound of a local type. The primary challenge is the lack of compactness due to the absence of smoothing effect. This is overcome by exploiting the asymptotic compactness for the dynamics of waves, introducing the concept of asymptotic exponential tightness for random measures, and establishing a new LDP approach for random dynamical systems.

math.AP↗

Thinking Outside the BBox: Unconstrained Generative Object Compositing

Compositing an object into an image involves multiple non-trivial sub-tasks such as object placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and shadow/reflection generation. Recent generative image compositing methods leverage diffusion models to handle multiple sub-tasks at once. However, existing models face limitations due to their reliance on masking the original object during training, which constrains their generation to the input mask. Furthermore, obtaining an accurate input mask specifying the location and scale of the object in a new image can be highly challenging. To overcome such limitations, we define a novel problem of unconstrained generative object compositing, i.e., the generation is not bounded by the mask, and train a diffusion-based model on a synthesized paired dataset. Our first-of-its-kind model is able to generate object effects such as shadows and reflections that go beyond the mask, enhancing image realism. Additionally, if an empty mask is provided, our model automatically places the object in diverse natural locations and scales, accelerating the compositing workflow. Our model outperforms existing object placement and compositing models in various quality metrics and user studies.

cs.CV↗

Quantitative stratification and sharp regularity estimates for supercritical semilinear elliptic equations

In this paper, we investigate the interior regularity theory for stationary solutions of the supercritical nonlinear elliptic equation $$ -Δu=|u|^{p-1}u\quad\text{in }Ω,\quad p>\frac{n+2}{n-2}, $$ where $ Ω\subset\mathbb{R}^n $ is a bounded domain with $ n\geq 3 $. Our primary focus is on the structure of stratification for the singular sets. We define the $ k $-th stratification $ S^k(u) $ of $ u $ based on the tangent functions and measures. We show that the Hausdorff dimension of $ S^k(u) $ is at most $ k $ and $ S^k(u) $ is $ k $-rectifiable, and establish estimates for volumes associated with points that have lower bounds on the regular scales. These estimates enable us to derive sharp interior estimates for the solutions. Specifically, if $ α_p=\frac{2(p+1)}{p-1} $ is not an integer, then for any $ j\in\mathbb{Z}_{\geq 0} $, we have $$ D^ju\in L_{\operatorname{loc}}^{q_j,\infty}(Ω), $$ which implies that for any $ Ω'\subset\subsetΩ$, $$ \sup\{λ>0:λ^{q_j}\mathcal{L}^n(\{x\inΩ':|D^ju(x)|>λ\})\}<+\infty, $$ where $ \mathcal{L}^n(\cdot) $ is the $ n $-dimensional Lebesgue measure, and $$ q_j=\frac{(p-1)(\lfloorα_p\rfloor+1)}{2+j(p-1)}, $$ with $ \lfloorα_p\rfloor $ being the integer part of $ α_p $. The proofs of these results rely on Reifenberg-type theorems developed by A. Naber and D. Valtorta to study the stratification of harmonic maps.

math.AP↗

Global derivation of the 1D Vlasov-Poisson equation from quantum many-body dynamics with screened Coulomb potential

We study the 1D quantum many-body dynamics with a screened Coulomb potential in the mean-field setting. Combining the quantum mean-field, semiclassical, and Debye length limits, we prove the global derivation of the 1D Vlasov-Poisson equation. We tackle the difficulties brought by the pure state data, whose Wigner transforms converge to Wigner measures. We find new weighted uniform estimates around which we build the proof. As a result, we obtain, globally, stronger limits, and hence the global existence of solutions to the 1D Vlasov-Poisson equation subject to such Wigner measure data, which satisfy conservation laws of mass, momentum, and energy, despite being measure solutions. This happens to solve the 1D case of an open problem regarding the conservation law of the Vlasov-Poisson equation raised in [18] by Diperna and Lions.

math.AP↗

Convergence rates in the nonrelativistic limit of the cubic Klein-Gordon equation

In this paper, we study the nonrelativistic limit of the cubic nonlinear Klein-Gordon equation in $\mathbb{R}^{3}$ with a small parameter $0<\varepsilon \ll 1$, which is inversely proportional to the speed of light. We show that the cubic nonlinear Klein-Gordon equation converges to the cubic nonlinear Schrödinger equation with a convergence rate of order $\varepsilon^{2}$. In particular, for the defocusing case and smooth initial data, we prove error estimates of the form $(1+t)\varepsilon^{2}$ at time $t$ which is valid up to long time of order $\varepsilon^{-1}$; while for nonsmooth initial data, we prove error estimates of the form $(1+t)\varepsilon$ at time $t$ which is valid up to long time of order $\varepsilon^{-\frac{1}{2}}$. These specific forms of error estimates coincide with the numerical results obtained in \cite{BZ19,SZ20}.

math.AP↗

WAS: Dataset and Methods for Artistic Text Segmentation

Accurate text segmentation results are crucial for text-related generative tasks, such as text image generation, text editing, text removal, and text style transfer. Recently, some scene text segmentation methods have made significant progress in segmenting regular text. However, these methods perform poorly in scenarios containing artistic text. Therefore, this paper focuses on the more challenging task of artistic text segmentation and constructs a real artistic text segmentation dataset. One challenge of the task is that the local stroke shapes of artistic text are changeable with diversity and complexity. We propose a decoder with the layer-wise momentum query to prevent the model from ignoring stroke regions of special shapes. Another challenge is the complexity of the global topological structure. We further design a skeleton-assisted head to guide the model to focus on the global structure. Additionally, to enhance the generalization performance of the text segmentation model, we propose a strategy for training data synthesis, based on the large multi-modal model and the diffusion model. Experimental results show that our proposed method and synthetic dataset can significantly enhance the performance of artistic text segmentation and achieve state-of-the-art results on other public datasets.

cs.CV↗

AI.vs.Clinician: Unveiling Intricate Interactions Between AI and Clinicians through an Open-Access Database

Artificial Intelligence (AI) plays a crucial role in medical field and has the potential to revolutionize healthcare practices. However, the success of AI models and their impacts hinge on the synergy between AI and medical specialists, with clinicians assuming a dominant role. Unfortunately, the intricate dynamics and interactions between AI and clinicians remain undiscovered and thus hinder AI from being translated into medical practice. To address this gap, we have curated a groundbreaking database called AI.vs.Clinician. This database is the first of its kind for studying the interactions between AI and clinicians. It derives from 7,500 collaborative diagnosis records on a life-threatening medical emergency -- Sepsis -- from 14 medical centers across China. For the patient cohorts well-chosen from MIMIC databases, the AI-related information comprises the model property, feature input, diagnosis decision, and inferred probabilities of sepsis onset presently and within next three hours. The clinician-related information includes the viewed examination data and sequence, viewed time, preliminary and final diagnosis decisions with or without AI assistance, and recommended treatment.

cs.HC↗

Establishing Rigorous and Cost-effective Clinical Trials for Artificial Intelligence Models

A profound gap persists between artificial intelligence (AI) and clinical practice in medicine, primarily due to the lack of rigorous and cost-effective evaluation methodologies. State-of-the-art and state-of-the-practice AI model evaluations are limited to laboratory studies on medical datasets or direct clinical trials with no or solely patient-centered controls. Moreover, the crucial role of clinicians in collaborating with AI, pivotal for determining its impact on clinical practice, is often overlooked. For the first time, we emphasize the critical necessity for rigorous and cost-effective evaluation methodologies for AI models in clinical practice, featuring patient/clinician-centered (dual-centered) AI randomized controlled trials (DC-AI RCTs) and virtual clinician-based in-silico trials (VC-MedAI) as an effective proxy for DC-AI RCTs. Leveraging 7500 diagnosis records from two-step inaugural DC-AI RCTs across 14 medical centers with 125 clinicians, our results demonstrate the necessity of DC-AI RCTs and the effectiveness of VC-MedAI. Notably, VC-MedAI performs comparably to human clinicians, replicating insights and conclusions from prospective DC-AI RCTs. We envision DC-AI RCTs and VC-MedAI as pivotal advancements, presenting innovative and transformative evaluation methodologies for AI models in clinical practice, offering a preclinical-like setting mirroring conventional medicine, and reshaping development paradigms in a cost-effective and fast-iterative manner. Chinese Clinical Trial Registration: ChiCTR2400086816.

cs.AI↗

Exponential mixing for random nonlinear wave equations: weak dissipation and localized control

We establish a new criterion for exponential mixing of random dynamical systems. Our criterion is applicable to a wide range of systems, including in particular dispersive equations. Its verification is in nature related to several topics, i.e., asymptotic compactness in dynamical systems, global stability of evolution equations, and localized control problems. As an initial application, we exploit the exponential mixing of random nonlinear wave equations with degenerate damping, critical nonlinearity, and physically localized noise. The essential challenge lies in the fact that the weak dissipation and randomness interact in the evolution.

math.AP↗

Global well-posedness of inhomogeneous Navier-Stokes equations with bounded density

In this paper, we solve Lions' open problem: {\it the uniqueness of weak solutions for the 2-D inhomogeneous Navier-Stokes equations (INS)}. We first prove the global existence of weak solutions to 2-D (INS) with bounded initial density and initial velocity in $L^2(\mathbb R^2)$. Moreover, if the initial density is bounded away from zero, then our weak solution equals to Lions' weak solution, which in particular implies the uniqueness of Lions' weak solution. We also extend a celebrated result by Fujita and Kato on the 3-D incompressible Navier-Stokes equations to 3-D (INS): {\it the global well-posedness of 3-D (INS) with bounded initial density and initial velocity being small in $\dot H^{1/2}(\mathbb R^3)$}. The proof of the uniqueness is based on a surprising finding that the estimate $t^{1/2}\nabla u\in L^2(0,T; L^\infty(\mathbb R^d))$ instead of $\nabla u\in L^1(0, T; L^\infty(\mathbb R^d))$ is enough to ensure the uniqueness of the solution.

math.AP↗

On the density patch problem for the 2-D inhomogeneous Navier-Stokes equations

In this paper, we first construct a class of global strong solutions for the 2-D inhomogeneous Navier-Stokes equations under very general assumption that the initial density is only bounded and the initial velocity is in $H^1(\mathbb{R}^2)$. With suitable assumptions on the initial density, which includes the case of density patch and vacuum bubbles, we prove that Lions' s weak solution is the same as the strong solution with the same initial data. In particular, this gives a complete resolution of the density patch problem proposed by Lions: {\it for the density patch data $ρ_0=1_{D}$ with a smooth bounded domain $D\subset\mathbb{R}^2$, the regularity of $D$ is preserved by the time evolution of Lions's weak solution.}

math.AP↗

On the spectrum of quasi-periodic Schrödinger operators on $\mathbb{Z}^d$ with $C^2$-cosine type potentials

In this paper, we establish the Anderson localization, strong dynamical localization and the $(\frac 12-)$-Hölder continuity of the integrated density of states (IDS) for some multi-dimensional discrete quasi-periodic (QP) Schrödinger operators with asymmetric $C^2$-cosine type potentials. We extend both the iteration scheme of \cite{CSZ23a} and the interlacing method of \cite{FV21} to handle asymmetric Rellich functions with collapsed gaps.

math-ph↗

On blow-up for the supercritical defocusing nonlinear wave equation

In this paper, we consider the defocusing nonlinear wave equation $-\partial_t^2u+Δu=|u|^{p-1}u$ in $\mathbb R\times \mathbb R^d$. Building on our companion work ({\it \small Self-similar imploding solutions of the relativistic Euler equations}), we prove that for $d=4, p\geq 29$ and $d\geq 5, p\geq 17$, there exists a smooth complex-valued solution that blows up in finite time.

math.AP↗

Mack modes in supersonic boundary layer

Understanding the transition mechanism of boundary layer flows is of great significance in physics and engineering, especially due to the current development of supersonic and hypersonic aircraft. In this paper, we construct multiple unstable acoustic modes so-called Mack modes, which play a crucial role during the early stage of transition in the supersonic boundary layer. To this end, we develop an inner-outer gluing iteration to solve a hyperbolic-elliptic mixed type and singular system.

math.AP↗