Searcharxiv⌕ Search

arXiv subjects

Zhifei Zhang

Publications and source records attributed to Zhifei Zhang.

At least 73 records · Page 4Linked to original sources

Self-similar algebraic spiral solution of 2-D incompressible Euler equations

In this paper, we prove the existence of self-similar algebraic spiral solutions for 2-D incompressible Euler equations for the initial vorticity of the form $|y|^{-\frac1μ}\ \mathringω(θ)$ with $μ>\frac12$ and $\mathringω\in L^1(\mathbb T)$ satisfying $m$-fold symmetry ($m\geq 2$) and a dominant condition. As an important application, we prove the existence of weak solution when $\mathringω$ is a Radon measure on $\mathbb T$ with $m$-fold symmetry, which is related to the vortex sheet solution.

math.AP↗

ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration

Recent progress in generative models has significantly improved image restoration capabilities, particularly through powerful diffusion models that offer remarkable recovery of semantic details and local fidelity. However, deploying these models at ultra-high resolutions faces a critical trade-off between quality and efficiency due to the computational demands of long-range attention mechanisms. To address this, we introduce ZipIR, a novel framework that enhances efficiency, scalability, and long-range modeling for high-res image restoration. ZipIR employs a highly compressed latent representation that compresses image 32x, effectively reducing the number of spatial tokens, and enabling the use of high-capacity models like the Diffusion Transformer (DiT). Toward this goal, we propose a Latent Pyramid VAE (LP-VAE) design that structures the latent space into sub-bands to ease diffusion training. Trained on full images up to 2K resolution, ZipIR surpasses existing diffusion-based methods, offering unmatched speed and quality in restoring high-resolution images from severely degraded inputs.

cs.CV↗

TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting

This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpainting. While standard diffusion models generate high-quality results, they incur high computational costs. We overcome this by training an inpainting adapter on a few-step distilled text-to-image model, DMD2, using a novel 3-step adversarial training scheme to ensure realistic, structurally consistent, and visually harmonious inpainted regions. To evaluate TurboFill, we propose two benchmarks: DilationBench, which tests performance across mask sizes, and HumanBench, based on human feedback for complex prompts. Experiments show that TurboFill outperforms both multi-step BrushNet and few-step inpainting methods, setting a new benchmark for high-performance inpainting tasks. Our project page: https://liangbinxie.github.io/projects/TurboFill/

cs.CV↗

Derivation of the compressible Euler equations from the dynamics of interacting Bose gas in the hard-core limit regime

We investigate the dynamics of short-range interacting Bose gases with varying degrees of diluteness and interaction strength. By applying a combined mean-field and semiclassical space-time rescaling to the dynamics in both the Gross--Pitaevskii and hard-core limit regimes, we prove that the local one-particle mass, momentum, and energy densities of the many-body system can be quantitatively approximated by solutions to the compressible Euler system in the strong sense, up to the first blow-up time of the fluid description, as the number of particles tends to infinity. In the hard-core limit regime, two novel results are presented. First, we rigorously prove, for the first time, that the internal energy of the fluid takes the form $4π\mathfrak{c}_{0}ρ^{2}$ (equivalently, pressure $P=2π\mathfrak{c}_{0}ρ^{2}$), arising solely from the kinetic energy density of the many-body system, rather than the interaction energy density, marking a fundamental difference from the Gross--Pitaevskii and other mean-field regimes. Second, the newly discovered coupling constant $\mathfrak{c}_{0}$ is the electrostatic capacity of the interaction potential, corresponding to the scattering length of the hard-core potential. Furthermore, in other limiting regimes, including those beyond the Gross--Pitaevskii regime, we find that the limiting equation is described by an eikonal system, offering a rigorous first-principle justification for using the ``geometric optics approximation'' to describe the dynamics of ultracold Bose gases.

math.AP↗

Localization for Lipschitz monotone quasi-periodic Schrödinger operators on $\mathbb{Z}^d$ via Rellich functions analysis

We establish the Anderson localization and exponential dynamical localization for a class of quasi-periodic Schrödinger operators on $\mathbb{Z}^d$ with bounded or unbounded Lipschitz monotone potentials via multi-scale analysis based on Rellich function analysis in the perturbative regime. We show that at each scale, the resonant Rellich function uniformly inherits the Lipschitz monotonicity property of the potential via a novel Schur complement argument.

math-ph↗

Anderson localized states for the nonlinear Maryland model on $\mathbb{Z}^d$

In this paper, we investigate Anderson localization for a nonlinear perturbation of the Maryland model $H=\varepsilonΔ+\cotπ(θ+j\cdotα)δ_{j,j'}$ on $\mathbb{Z}^d$. Specifically, if $\varepsilon,δ$ are sufficiently small, we construct a large number of time quasi-periodic and space exponentially decaying solutions (i.e., Anderson localized states) for the equation $i\frac{\partial u}{\partial t}=Hu+δ|u|^{2p}u$ with a Diophantine $α$. Our proof combines eigenvalue estimates of the Maryland model with the Craig-Wayne-Bourgain method, which originates from KAM theory for Hamiltonian PDEs.

math.AP↗

Quantifying the Dynamics of Harm Caused by Retracted Research

Despite enormous efforts devoted to understand the characteristics and impacts of retracted papers, little is known about the mechanisms underlying the dynamics of their harm and the dynamics of its propagation. Here, we propose a citation-based framework to quantify the harm caused by retracted papers, aiming to uncover why their harm persists and spreads so widely. We uncover an ''attention escape'' mechanism, wherein retracted papers postpone significant harm, more prominently affect indirectly citing papers, and inflict greater harm on citations in journals with an impact factor less than 10. This mechanism allows retracted papers to inflict harm outside the attention of authors and publishers, thereby evading their intervention. This study deepens understanding of the harm caused by retracted papers, emphasizes the need to activate and enhance the attention of authors and publishers, and offers new insights and a foundation for strategies to mitigate their harm and prevent its spread.

cs.DL↗

Blow-up of the 3-D compressible Navier-Stokes equations for monatomic gases

In this paper, we prove the blow-up of the $3$-D isentropic compressible Navier-Stokes equations for the adiabatic exponent $γ=5/3$, which corresponds to the law of monatomic gases. This is the degenerate case in the sense of [Merle, Raphaël, Rodnianski and Szeftel, Ann. of Math. (2), 196 (2022), 567-778; Ann. of Math. (2), 196 (2022), 779-889]. Motivated by these breakthrough works, we first establish the existence of a sequence of smooth, self-similar imploding solutions to the compressible Euler equations for $γ=5/3$. Subsequently, we utilize these self-similar profiles to construct smooth, asymptotically self-similar blow-up solutions to the compressible Navier-Stokes equations for monatomic gases.

math.AP↗

Multitwine: Multi-Object Compositing with Text and Layout Control

We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like `taking a selfie', our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a more balanced integration of textual and visual inputs for text-driven object compositing. As a result, we obtain a versatile model with state-of-the-art performance in both tasks. We further present a data generation pipeline leveraging visual and language models to effortlessly synthesize multimodal, aligned training data.

cs.CV↗

Tollmien-Schlichting waves near neutral stable curve

In this paper, we study the linear stability of boundary layer flows over a flat plate. Tollmien, Schlichting, Lin et al. found that there exists a neutral curve, which consists of two branches: lower branch $α_{low}(Re)$ and upper branch $α_{up}(Re)$. Here, $α$ is the wave number and $Re$ is the Reynolds number. For any $α\in(α_{low},α_{up})$, there exist unstable modes known as Tollmien-Schlichting (T-S) waves to the linearized Navier-Stokes system. These waves play a key role during the early stage of boundary layer transition. In a breakthrough work (Duke math Jour, 165(2016)), Grenier, Guo, and Nguyen provided a rigorous construction of the unstable T-S waves. In this paper, we confirm the existence of the neutral stable curve. To achieve this, we develop a more delicate method for solving the Orr-Sommerfeld equation by borrowing some ideas from the triple-deck theory. This approach allows us to construct the T-S waves in a neighborhood of the neutral curve.

math.AP↗

Corrector estimates and homogenization errors of unsteady flow ruled by Darcy's law

Focusing on Darcy's law incorporating memory effects, this paper studies non-stationary Stokes equations on perforated domains. We establish a sharp homogenization error for both velocity and pressure in terms of the energy norm. The main challenge lies in gauging the boundary layers induced by the incompressibility condition. To address this, we construct boundary-layer correctors using Bogovskii's operator. Also, the present work provides detailed regularity estimates for these correctors, where a significant difficulty arises from the incompatibility between initial and boundary values. The methodologies developed herein hold great potential for tackling the same issue in other evolutionary models beyond a homogenization setting.

math.AP↗

TransPixeler: Advancing Text-to-Video Generation with Transparency

Text-to-video generative models have made significant strides, enabling diverse applications in entertainment, advertising, and education. However, generating RGBA video, which includes alpha channels for transparency, remains a challenge due to limited datasets and the difficulty of adapting existing models. Alpha channels are crucial for visual effects (VFX), allowing transparent elements like smoke and reflections to blend seamlessly into scenes. We introduce TransPixeler, a method to extend pretrained video models for RGBA generation while retaining the original RGB capabilities. TransPixar leverages a diffusion transformer (DiT) architecture, incorporating alpha-specific tokens and using LoRA-based fine-tuning to jointly generate RGB and alpha channels with high consistency. By optimizing attention mechanisms, TransPixar preserves the strengths of the original RGB model and achieves strong alignment between RGB and alpha channels despite limited training data. Our approach effectively generates diverse and consistent RGBA videos, advancing the possibilities for VFX and interactive content creation.

cs.CV↗

Incompressible and vanishing vertical viscosity limit for the compressible Navier-Stokes system with Dirichlet boundary conditions

In this paper, we show the incompressible and vanishing vertical viscosity limits for the strong solutions to the isentropic compressible Navier-Stokes system with anistropic dissipation, in a domain with Dirichlet boundary conditions in the general setting of ill-prepared initial data. We establish the uniform regularity estimates with respect to the Mach number $ε$ and the vertical viscosity $ν$ so that the solution exists on a uniform time interval $[0,T_0]$ independent of these parameters. The key steps toward this goal are the careful construction of the approximate solution in the presence of both fast oscillations and two kinds of boundary layers together with the stability analysis of the remainder. In the process, it is also shown that the solutions of the compressible systems converge to those of the incompressible system with only horizontal dissipation, after removing the fast waves whose horizontal derivative is bounded in $L_{T_0}^2L_x^2$ by $\min\{1, (ε/ν)^{\frac14}\}.$

math.AP↗

Generative Video Propagation

Large-scale video generation models have the inherent ability to realistically model natural scenes. In this paper, we demonstrate that through a careful design of a generative video propagation framework, various video tasks can be addressed in a unified way by leveraging the generative power of such models. Specifically, our framework, GenProp, encodes the original video with a selective content encoder and propagates the changes made to the first frame using an image-to-video generation model. We propose a data generation scheme to cover multiple video tasks based on instance-level video segmentation datasets. Our model is trained by incorporating a mask prediction decoder head and optimizing a region-aware loss to aid the encoder to preserve the original content while the generation model propagates the modified region. This novel design opens up new possibilities: In editing scenarios, GenProp allows substantial changes to an object's shape; for insertion, the inserted objects can exhibit independent motion; for removal, GenProp effectively removes effects like shadows and reflections from the whole video; for tracking, GenProp is capable of tracking objects and their associated effects together. Experiment results demonstrate the leading performance of our model in various video tasks, and we further provide in-depth analyses of the proposed framework.

cs.CV↗

Fine structure of rupture set for semilinear elliptic equation with singular nonlinearity

In this paper, we study the stationary solutions of semilinear elliptic equation with singular nonlinearity $$ Δu=u^{-p}+f,\,\,u\geq 0\text{ in }Ω\subset\mathbb{R}^n, $$ where $ n\geq 2 $, $ p>1 $, $ Ω$ is a bounded domain, and $ f\in L^q(Ω) $ with $ \frac{1}{2}+\frac{1}{2p}<\frac{q}{n} $. We establish a sharp estimate for the Minkowski content of the rupture set $ \{u=0\} $ and demonstrate that this set is $ (n-2) $-rectifiable. For this, we examine the stratification of the rupture set based on the symmetry properties of tangent functions, leading to the proof of $ k $-rectifiability for each $ k $-stratum. As a significant byproduct of our analysis, we improve the integrability of $ D^ju $ with $ j\in\mathbb{Z}_+ $ to the optimal Lorentz space $ L^{\frac{2(p+1)}{j(p+1)-2},\infty} $, under the assumption that $ D^{j-1}f $ is bounded. As an application of our results in the static case of the equation, for a class of suitable weak solutions to the three-dimensional evolutional problem $$ \partial_tu=Δu-u^{-p},\,\,u\geq 0\text{ in }(Ω\subset\mathbb{R}^3)\times(0,T), $$ where $ p>3 $ and $ T>0 $, we show that $ \{u(\cdot,t)=0\} $ is $ 1 $-rectifiable for a.e. $ t\in(0,T) $.

math.AP↗

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image generation, editing, customization, composition, etc. Although designed for image-level tasks, we leverage videos as a scalable source for universal supervision. UniReal learns world dynamics from large-scale videos, demonstrating advanced capability in handling shadows, reflections, pose variation, and object interaction, while also exhibiting emergent capability for novel applications.

cs.CV↗

The second order Huang-Yang formula to the 3D Fermi gas: the Gross-Pitaevskii regime

For a system of $N$ Fermions of spin $1/2$, with its interaction potential of scattering length $a$, the classical Huang-Yang formula states that the energy density $e(ρ)$ is of the form \begin{equation*} e(ρ)=\frac{3}{5}(3π^2)^{\frac{2}{3}}ρ^{\frac{5}{3}}+2πaρ^2 +\frac{12}{35}(11-2\ln2)3^{\frac{1}{3}}π^{\frac{2}{3}}a^2ρ^{\frac{7}{3}} +o(ρ^{\frac{7}{3}}). \end{equation*} We consider a general system of $N$ Fermions of spin $1/\mathbf{q}$ with the scattering length of the interaction potential at the scale $a\propto N^{-1}$, that is, in the Gross-Pitaevskii regime. We prove the 2nd order ground state energy approximation corresponding to the Huang-Yang formula. The thermodynamic limit case shares a similar logic, and could be dealt with in a separate paper.

math-ph↗

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

Personalized image generation has emerged from the recent advancements in generative models. However, these generated personalized images often suffer from localized artifacts such as incorrect logos, reducing fidelity and fine-grained identity details of the generated results. Furthermore, there is little prior work tackling this problem. To help improve these identity details in the personalized image generation, we introduce a new task: reference-guided artifacts refinement. We present Refine-by-Align, a first-of-its-kind model that employs a diffusion-based framework to address this challenge. Our model consists of two stages: Alignment Stage and Refinement Stage, which share weights of a unified neural network model. Given a generated image, a masked artifact region, and a reference image, the alignment stage identifies and extracts the corresponding regional features in the reference, which are then used by the refinement stage to fix the artifacts. Our model-agnostic pipeline requires no test-time tuning or optimization. It automatically enhances image fidelity and reference identity in the generated image, generalizing well to existing models on various tasks including but not limited to customization, generative compositing, view synthesis, and virtual try-on. Extensive experiments and comparisons demonstrate that our pipeline greatly pushes the boundary of fine details in the image synthesis models.

cs.CV↗