arXiv subjects

Ziyue Zeng

Publications and source records attributed to Ziyue Zeng.

11 recordsLinked to original sources

arXiv2026

GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression

Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultra-low bitrate. Current codecs tie each finite-rate correction to a fresh prior evaluation, so shortening the sampler also removes correction slots that carry target-dependent information. We propose GVCCTurbo, a BPP-driven scheduler that separates expensive prior refreshes from codebook corrections: after calibrating an atom-count operating point and skip-gap ratio once per protocol, it maps a target codebook-payload bitrate to a trajectory length and refresh period, making BPP a schedule input instead of a fixed consequence of sampler length. The same endpoint-prediction and finite-rate steering interface covers GVCC-style rectified-flow video and DDCM-style diffusion image compression, preserving zero-training deployment and compatibility with future distilled priors. Native 1080p curves position the complete zero-shot codec in the ultra-low-bitrate regime. In a controlled 720p Wan-GVCC study, the scheduler cuts prior evaluations from 20 to 9 for a $\sim\!44\%$ measured decoding-time reduction shared across the whole schedule family, at a small shared LPIPS cost on high-motion content; within that family, uniform refresh thinning (pure-skip) is a boundary point, and the BPP-aware interior point trades $2.9\%$ fewer codebook-payload bits for consistently higher PSNR at comparable LPIPS. These results support BPP-to-compute scheduling as a controllable extension of sampler-length tuning, without requiring the allocated point to dominate every boundary point.

cs.CV↗

arXiv2026

GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as the decoder, and the transmitted bitstream specifies its generation trajectory. Modern rectified-flow video models are typically sampled with deterministic ODE solvers, which leave no per-step stochastic channel for transmitting compressed information. GVCC addresses this by converting the deterministic flow sampler into an equivalent marginal-preserving stochastic process, so that information can be transmitted by encoding the per-step stochastic innovations. Unlike images, videos introduce longer temporal dependencies and more diverse conditioning modes. We instantiate GVCC in three practical modes: Text-to-Video (T2V) without a reference frame, autoregressive Image-to-Video (I2V) with tail latent correction, and First-Last-Frame-to-Video (FLF2V) with boundary-sharing Group of Pictures (GOP) chaining. On UVG, GVCC achieves the lowest LPIPS among evaluated baselines across three representative bitrate regimes (down to ${\sim}$0.003\,bpp), with 65\% LPIPS reduction over DCVC-RT at matched bitrate.

cs.CV↗

arXiv2026

Critical blow-up curve in a two-species chemotaxis system with two chemicals involving flux-limitation

We investigate the following two-species chemotaxis system with two chemicals involving flux-limitation \begin{align}\tag{$\star$} \begin{cases} u_t = Δu - \nabla \cdot \left(u(1+|\nabla v|^2)^{-\frac{p}{2}}\nabla v\right), & x \in Ω, \ t > 0, \\ 0 = Δv - μ_w + w, \quad μ_{w}=f_Ω w, & x \in Ω, \ t > 0, \\ w_t = Δw - \nabla \cdot \left(w (1+|\nabla z|^2)^{-\frac{q}{2}} \nabla z\right), & x \in Ω, \ t > 0, \\ 0 = Δz - μ_u + u, \quad μ_{u}=f_Ω u, & x \in Ω, \ t > 0, \\ \frac{\partial u}{\partial ν} = \frac{\partial v}{\partial ν} = \frac{\partial w}{\partial ν} = \frac{\partial z}{\partial ν} = 0, & x \in \partial Ω, \ t > 0, \\ u(x, 0) = u_0(x), \quad w(x, 0) = w_0(x), & x \in Ω, \end{cases} \end{align} where $p,q \in \mathbb{R}$ and $Ω\subset \mathbb{R}^n$ is a smooth bounded domain. In this paper, we identify a critical blow-up curve for system ($\star$) with $n\geq 3$. If $p<\frac{n-2}{n-1}$ and $q<\frac{n-2}{n-1}$, and $Ω=B_R(0) \subset \mathbb{R}^n$ with $n\geq 3$, there exist radially symmetric initial data such that the corresponding solution blows up in finite time; if either $p>\frac{n-2}{n-1}$ or $q>\frac{n-2}{n-1}$ with $n\geq 2$, then solutions exist globally and remain bounded.

math.AP↗

arXiv2026

Critical blow-up lines in a two-species quasilinear chemotaxis system with two chemicals

In this study, we explore the quasilinear two-species chemotaxis system with two chemicals \begin{align}\tag{$\star$} \begin{cases} u_t = \nabla \cdot(D(u)\nabla u) - \nabla \cdot \left(S(u) \nabla v\right), & x \in Ω, \ t > 0, \\ 0 = Δv - μ_w + w, \quad μ_w=\fint_Ωw, & x \in Ω, \ t > 0, \\ w_t = Δw - \nabla \cdot \left(w \nabla z\right), & x \in Ω, \ t > 0, \\ 0 = Δz - μ_u + u, \quad μ_u=\fint_Ωu, & x \in Ω, \ t > 0, \\ \frac{\partial u}{\partial ν} = \frac{\partial v}{\partial ν} = \frac{\partial w}{\partial ν} = \frac{\partial z}{\partial ν} = 0, & x \in \partial Ω, \ t > 0, \\ u(x, 0) = u_0(x), \quad w(x, 0) = w_0(x), & x \in Ω, \end{cases} \end{align} where $Ω\subset \mathbb{R}^n$ ($n \geq3$) is a smooth bounded domain. The functions $D(s)$ and $S(s)$ exhibit asymptotic behavior of the form \begin{align*} D(s) \simeq k_D s^p \ \text {and} \ S(s) \simeq k_S s^q, \quad s \gg 1 \end{align*} with $p,q \in \mathbb{R}$. We prove that \begin{itemize} \item when $Ω$ is a ball, if $q-p>2-\frac{n}{2}$ and $q>1-\frac{n}{2}$, there exist radially symmetric initial data $u_0$ and $w_0$, such that the corresponding solutions blow up in finite time; \item for any general smooth bounded domain $Ω\subset \mathbb{R}^n$, if $q-p<2-\frac{n}{2}$, all solutions are globally bounded; \item for any general smooth bounded domain $Ω\subset \mathbb{R}^n$, if $q<1-\frac{n}{2}$, all solutions are global. \end{itemize} We point out that our results implies that the system ($\star$) possess two critical lines $ q-p=2-\frac{n}{2}$ and $q=1-\frac{n}{2}$ to classify three dynamics among global boundedness, finite-time blow-up, and global existence of solutions to system ($\star$).

math.AP↗

arXiv2026

Finite-time blow-up in a quasilinear two-species chemotaxis system with two chemicals

This paper investigates the finite-time blow-up phenomena to a quasilinear two-species chemotaxis system with two chemicals \begin{align}\tag{$\star$} \begin{cases} u_t = \nabla \cdot \left(D_1(u) \nabla u\right) - \nabla \cdot \left(u \nabla v\right), & x \in Ω, \ t > 0, 0 = Δv - μ_2 + w, \quad μ_2=\fint_Ωw, & x \in Ω, \ t > 0, w_t = \nabla \cdot \left(D_2(w) \nabla w\right) - \nabla \cdot \left(w \nabla z\right), & x \in Ω, \ t > 0, 0 = Δz - μ_1 + u, \quad μ_1=\fint_Ωu, & x \in Ω, \ t > 0, \frac{\partial u}{\partial ν} = \frac{\partial v}{\partial ν} = \frac{\partial w}{\partial ν} = \frac{\partial z}{\partial ν} = 0, & x \in \partial Ω, \ t > 0, u(x, 0) = u_0(x), \quad w(x, 0) = w_0(x), & x \in Ω, \end{cases} \end{align} where $Ω\subset \mathbb{R}^n$ $(n \geqslant 3)$ is a smoothly bounded domain. The nonlinear diffusion functions $ D_1(s) $ and $ D_2(s) $ are of the following forms: \begin{align*} D_1(s)\simeq s^{m_1-1} \quad \text{and}\quad D_2(s) \simeq s^{m_2-1}, \quad m_1,m_2> 1 \end{align*} for $s\geqslant 1$. For the classical two-species chemotaxis system with two chemicals (i.e. the second and fourth equations are replaced by $0 = Δv - v + w$ and $0 = Δz - z + u$ ), Zhong [J. Math. Anal. Appl., 500 (2021), Paper No. 125130, pp. 22.] showed that the system possesses a globally bounded classical solution in the case that \[ m_1 + m_2 < \max\left\{m_1m_2 + \frac{2m_1}{ n},\ m_1m_2 + \frac{2m_2 }{ n}\right\}. \] Complementing the boundedness result, we prove that the system ($\star$) admits solutions that blow up in finite time, if \[ m_1 + m_2 > \max\left\{ m_1m_2 + \frac{2m_1}{ n},\ m_1m_2 + \frac{2m_2}{ n}\right\} \] with $n\geqslant 3$.

math.AP↗

arXiv2026

Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines

Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus requiring individual training for each target bitrate. This limitation may restrict their practical usage. Existing variable rate image compression approaches mitigate this issue but often rely on additional training, which increases computational costs and complicates deployment. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free framework for quantization strength control which enables flexible bitrate adjustment. By exploiting the scale parameter predicted by the hyperprior network, the proposed method adaptively modulates quantization step sizes across both channel and spatial dimensions. This allows the model to preserve semantically important regions while coarsely quantizing less critical areas. Our architectural design further enables continuous bitrate control through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate baseline. The code is available at https://github.com/qwert-top/AQVR-ICM.

eess.IV↗

arXiv2025

Explicit Residual-Based Scalable Image Coding for Humans and Machines

Scalable image compression is a technique that progressively reconstructs multiple versions of an image for different requirements. In recent years, images have increasingly been consumed not only by humans but also by image recognition models. This shift has drawn growing attention to scalable image compression methods that serve both machine and human vision (ICMH). Many existing models employ neural network-based codecs, known as learned image compression, and have made significant strides in this field by carefully designing the loss functions. In some cases, however, models are overly reliant on their learning capacity, and their architectural design is not sufficiently considered. In this paper, we enhance the coding efficiency and interpretability of ICMH framework by integrating an explicit residual compression mechanism, which is commonly employed in resolution scalable coding methods such as JPEG2000. Specifically, we propose two complementary methods: Feature Residual-based Scalable Coding (FR-ICMH) and Pixel Residual-based Scalable Coding (PR-ICMH). These proposed methods are applicable to various machine vision tasks. Moreover, they provide flexibility to choose between encoder complexity and compression performance, making it adaptable to diverse application requirements. Experimental results demonstrate the effectiveness of our proposed methods, with PR-ICMH achieving up to 29.57% BD-rate savings over the previous work.

eess.IV↗

arXiv2025

Seed Selection for Human-Oriented Image Reconstruction via Guided Diffusion

Conventional methods for scalable image coding for humans and machines require the transmission of additional information to achieve scalability. A recent diffusion-based approach avoids this by generating human-oriented images from machine-oriented images without extra bitrate. However, it utilizes a single random seed, which may lead to suboptimal image quality. In this paper, we propose a seed selection method that identifies the optimal seed from multiple candidates to improve image quality without increasing the bitrate. To reduce the computational cost, selection is performed based on intermediate outputs obtained from early steps of the reverse diffusion process. Experimental results demonstrate that our proposed method outperforms the baseline, which uses a single random seed without selection, across multiple evaluation metrics.

cs.CV↗

arXiv2024

Time Step Generating: A Universal Synthesized Deepfake Image Detector

Currently, high-fidelity text-to-image models are developed in an accelerating pace. Among them, Diffusion Models have led to a remarkable improvement in the quality of image generation, making it vary challenging to distinguish between real and synthesized images. It simultaneously raises serious concerns regarding privacy and security. Some methods are proposed to distinguish the diffusion model generated images through reconstructing. However, the inversion and denoising processes are time-consuming and heavily reliant on the pre-trained generative model. Consequently, if the pre-trained generative model meet the problem of out-of-domain, the detection performance declines. To address this issue, we propose a universal synthetic image detector Time Step Generating (TSG), which does not rely on pre-trained models' reconstructing ability, specific datasets, or sampling algorithms. Our method utilizes a pre-trained diffusion model's network as a feature extractor to capture fine-grained details, focusing on the subtle differences between real and synthetic images. By controlling the time step t of the network input, we can effectively extract these distinguishing detail features. Then, those features can be passed through a classifier (i.e. Resnet), which efficiently detects whether an image is synthetic or real. We test the proposed TSG on the large-scale GenImage benchmark and it achieves significant improvements in both accuracy and generalizability.

cs.CV↗

arXiv2024

Boundedness and finite-time blow-up in a repulsion-consumption system with flux limitation

We investigate the following repulsion-consumption system with flux limitation \begin{align}\tag{$\star$} \left\{ \begin{array}{ll} u_t=Δu+\nabla \cdot(uf(|\nabla v|^2) \nabla v), & x \in Ω, t>0, τv_t=Δv-u v, & x \in Ω, t>0, \end{array} \right. \end{align} under no-flux/Dirichlet boundary conditions, where $Ω\subset \mathbb{R}^n$ is a bounded domain and $f(ξ)$ generalizes the prototype given by $f(ξ)=(1+ξ)^{-α}$ ($ξ\geqslant 0$). We are mainly concerned with the global existence and finite time blow-up of system ($\star$). The main results assert that, for $α> \frac{n-2}{2n}$, then when $τ=1$ and under radial settings, or when $τ=0$ without radial assumptions, for arbitrary initial data, the problem ($\star$) possesses global bounded classical solutions; for $α<0$, $τ=0$, $n=2$ and under radial settings, for any initial data, whenever the boundary signal level large enough, the solutions of the corresponding problem blow up in finite time. Our results can be compared respectively with the blow-up phenomenon obtained by Ahn \& Winkler (2023) for the system with nonlinear diffusion and linear chemotactic sensitivity, and by Wang \& Winkler (2023) for the system with nonlinear diffusion and singular sensitivity .

math.AP↗

arXiv2024

Boundedness and finite-time blow-up in a repulsion-consumption system with nonlinear chemotactic sensitivity

This paper investigates the repulsion-consumption system \begin{align}\tag{$\star$} \left\{ \begin{array}{ll} u_t=Δu+\nabla \cdot(S(u) \nabla v), τv_t=Δv-u v, \end{array} \right. \end{align} under no-flux/Dirichlet conditions for $u$ and $v$ in a ball $B_R(0) \subset \mathbb R^n $. When $τ=\{0,1\}$ and $0 0$, we show that for any given radially symmetric initial data, the problem ($\star$) possesses a global bounded classical solution. Conversely, when $τ=0$, $n=2$ and $S(u) \geqslant k u^β$ for $u \geqslant 0$ with some $β>1$ and $k>0$, for any given initial data $u_0$, there exists a constant $M^{\star}=M^{\star}\left(u_0\right)>0$ with the property that whenever the boundary signal level $M\geqslant M^{\star}$, the corresponding radially symmetric solution blows up in finite time. Our results can be compared with that of the papers [J.~Ahn and M.~Winkler, {\it Calc. Var.} {\bf 64} (2023).] and [Y. Wang and M. Winkler, {\it Proc. Roy. Soc. Edinburgh Sect. A}, \textbf{153} (2023).], in which the authors studied the system ($\star$) with the first equation replaced respectively by $u_t=\nabla \cdot ((1+u)^{-α} \nabla u)+\nabla \cdot(u \nabla v)$ and $u_t=\nabla \cdot ((1+u)^{-α} \nabla u)+\nabla \cdot(\frac{u}{v} \nabla v)$. Among other things, they obtained that, under some conditions on $u_0(x)$ and the boundary signal level, there exists a classical solution blowing up in finite time whenever $α>0$.

math.AP↗