arXiv subjects

Yifu Wang

Publications and source records attributed to Yifu Wang.

At least 19 recordsLinked to original sources

arXiv2026

Spatial inhomogeneity for a three-dimensional doubly degenerate nutrient system with indirect consumption

This paper investigates the global dynamics of a doubly degenerate nutrient-taxis system with indirect consumption: \begin{equation*} \left\{ \begin{aligned} &u_{t}=\nabla \cdot (uv\nabla u)-\nabla \cdot (u^{2}v\nabla v)+\ell vw,&x\in Ω,\, t>0,\\ & v_{t}=Δv-vw,&x\in Ω,\, t>0,\\ &w_t=Δw-w+u,&x\inΩ,t>0 \end{aligned} \right. \end{equation*} posed on a smooth bounded domain $Ω\subset\mathbb{R}^{3}$ with no-flux boundary conditions. It is shown that for suitably regular initial data $(u_0,v_0,w_0)$, the associated initial-boundary value problem admits a global weak solution. Furthermore, in an appropriate topological setting, this solution converges to an equilibrium $(u_\infty, 0,w_\infty)$ as $t\rightarrow \infty$. Notably, when $u_0$ is nonconstant and the mass of $v_0$ is sufficiently small, the limiting profiles $u_{\infty}$ and $w_{\infty}$ are are spatially nonhomogeneous, capturing emergent patterning in nutrient-depleted environments. A cornerstone of our analysis is the introduction of novel functional inequalities, which provide estimates from below for the integral $\int_Ωu^{k}v|\nabla u|^2$ with some $k>-1$.

math.AP↗

arXiv2026

Minimizing the Arithmetic and Communication Complexity of Jacobi's Method for Eigenvalues and Singular Values: Part Two -- Parallel Algorithms

This paper presents several parallel versions of Jacobi's method for the symmetric eigenvalue problem and the SVD. A continuation of [Demmel, Luo, Schneider, & Wang 2025], we develop parallel Jacobi algorithms whose arithmetic cost is optimal and whose bandwidth or latency can match the corresponding lower bounds of parallel matrix multiplication. Our focus is a standard distributed-memory setting with variable processor layouts, including both 2D and 2.5D processor grids. In the 2D case, we demonstrate that a standard implementation of parallel Jacobi achieves a perfect speedup in arithmetic cost -- i.e., complexity $O(n^3/P)$ when done with $P$ processors -- while hitting the 2D matrix-multiplication lower bound for bandwidth and (nearly) the lower bound for latency. By employing a 2.5D processor grid and leveraging 2.5D matrix multiplication, equivalently by increasing the memory per processor, we demonstrate that parallel Jacobi can achieve even lower bandwidth/latency, though we also prove that these costs cannot simultaneously match the best-known bounds for parallel matrix multiplication in any Jacobi algorithm. Finally, we extend our results to one-sided Jacobi SVD.

math.NA↗

arXiv2026

P2Voxel: Pyramid Pivot Voxelization for 3D Mesh Tokenization

Triangle meshes provide explicit and accurate surface geometry, yet their irregular topology connectivity makes 3D mesh tokenization a geometric sampling problem: how to sample and organize geometric evidence into compact, structured and learnable tokens. Beyond field-centric volumetric sampling and edge-intersection surface sampling, we retarget mesh tokenization as \textit{local surface evidence sampling}: identifying the minimal geometric evidence inside each active voxel that is sufficient for deterministic surface recovery. To this end, we introduce \textbf{P2Voxel}, a pyramid pivot voxelization framework for compact and reconstruction-aware mesh tokenization. P2Voxel is built on three key innovations. Under the \textit{Local Planarity} assumption, Pivot Voxelization represents each active voxel with a surface pivot and an orientation sign, providing minimal local evidence that can induce the corner values required for deterministic reconstruction. Under the \textit{Spatial Complexity} assumption, Pyramid Pivot Voxelization exploits the spatial non-uniformity of real surfaces by allocating finer pivot tokens to geometrically complex regions while keeping smooth regions coarse and compact. Under the \textit{Block Reconstructability} assumption, a Pyramid VAE learns compact multi-resolution latent codes over locally reconstructable pivot blocks, avoiding the need to model the entire high-resolution voxelized shape as a dense global field. Together, these designs convert meshes into compact, structured, and learnable pyramid pivot tokens, enabling efficient mesh reconstruction for downstream 3D tasks.

cs.CV↗

arXiv2026

I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation

Despite remarkable progress in video generation, maintaining long-term scene consistency upon revisiting previously explored areas remains challenging. Existing solutions rely either on explicitly constructing 3D geometry, which suffers from error accumulation and scale ambiguity, or on naive camera Field-of-View (FoV) retrieval, which typically fails under complex occlusions. To overcome these limitations, we propose I3DM, a novel implicit 3D-aware memory mechanism for consistent video scene generation that bypasses explicit 3D reconstruction. At the core of our approach is a 3D-aware memory retrieval strategy, which leverages the intermediate features of a pre-trained Feed-Forward Novel View Synthesis (FF-NVS) model to score view relevance, enabling robust retrieval even in highly occluded scenarios. Furthermore, to fully utilize the retrieved historical frames, we introduce a 3D-aligned memory injection module. This module implicitly warps historical content to the target view and adaptively conditions the generation on reliable warping regions, leading to improved revisit consistency and accurate camera control. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches, achieving superior revisit consistency, generation fidelity, and camera control precision.

cs.CV↗

arXiv2026

Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation

Frame-wise action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response. However, maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging. Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from \textit{Latent--RGB Cycling}, where generated latents are repeatedly decoded to RGB and re-encoded for future conditioning, and the training--inference gap induced by the \textit{error-free hypothesis}, where clean training memory fails to match prediction-corrupted inference memory. To address these challenges, we present \textbf{Robust Dreamer}, a memory-augmented framework built around how to design 3D memory and how to use it robustly. First, we introduce \textbf{Latent Gaussian Memory}, which anchors diffusion latents inherited from the generation process to Gaussian primitives and recalls them via latent-space Gaussian splatting. This provides dense, geometry-aware, view-aligned conditioning while avoiding accumulated degradation from repeated VAE conversion. Second, we propose \textbf{Deviation Learning with Dynamic Deviation Archive}, which synthesizes rollout-induced latent deviations through a one-step approximation, stores them by autoregressive stage and denoising timestamp, and injects them into historical memory during training. This exposes the generator to realistic corrupted memory states and teaches internal correction before inference. Experiments on ScanNet, DL3DV, and OmniWorldGame demonstrate state-of-the-art long-horizon performance.

cs.CV↗

arXiv2026

InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model

We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation.

cs.CV↗

arXiv2026

Minimizing the Arithmetic and Communication Complexity of Jacobi's Method for Eigenvalues and Singular Values: Part One -- Serial Algorithms

We analyze several versions of Jacobi's method for the symmetric eigenvalue problem. Our goal is to reduce the asymptotic cost of the algorithm as much as possible, as measured by the number of arithmetic operations performed and associated (serial or parallel) communication, i.e., the amount of data moved between slow and fast memory or between processors in a network. The first half of this effort, which considers the serial setting, is presented here; this paper contains rigorous complexity bounds for a variety of serial Jacobi algorithms, built on both classic $O(n^3)$ matrix multiplication and fast, Strassen-like $O(n^{ω_0})$ alternatives. In the classical case, we show that a blocked implementation of Jacobi's method attains the communication lower bound for $O(n^3)$ matrix multiplication (and is therefore expected to be communication optimal among $O(n^3)$ eigensolvers). In the fast setting, we demonstrate that a recursive version of blocked Jacobi can go further, reaching essentially optimal complexity in both measures. We also derive analogous complexity bounds for (one-sided) Jacobi SVD algorithms. A forthcoming sequel to this paper will extend our complexity analysis to the parallel case.

math.NA↗

arXiv2026

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos.

cs.CV↗

arXiv2026

3DXTalker: Unifying Identity, Lip Sync, Emotion, and Spatial Dynamics in Expressive 3D Talking Avatars

Audio-driven 3D talking avatar generation is increasingly important in virtual communication, digital humans, and interactive media, where avatars must preserve identity, synchronize lip motion with speech, express emotion, and exhibit lifelike spatial dynamics, collectively defining a broader objective of expressivity. However, achieving this remains challenging due to insufficient training data with limited subject identities, narrow audio representations, and restricted explicit controllability. In this paper, we propose 3DXTalker, an expressive 3D talking avatar through data-curated identity modeling, audio-rich representations, and spatial dynamics controllability. 3DXTalker enables scalable identity modeling via 2D-to-3D data curation pipeline and disentangled representations, alleviating data scarcity and improving identity generalization. Then, we introduce frame-wise amplitude and emotional cues beyond standard speech embeddings, ensuring superior lip synchronization and nuanced expression modulation. These cues are unified by a flow-matching-based transformer for coherent facial dynamics. Moreover, 3DXTalker also enables natural head-pose motion generation while supporting stylized control via prompt-based conditioning. Extensive experiments show that 3DXTalker integrates lip synchronization, emotional expression, and head-pose dynamics within a unified framework, achieves superior performance in 3D talking avatar generation.

cs.CV↗

arXiv2026

StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics

Storyboarding is a core skill in visual storytelling for film, animation, and games. However, automating this process requires a system to achieve two properties that current approaches rarely satisfy simultaneously: inter-shot consistency and explicit editability. While 2D diffusion-based generators produce vivid imagery, they often suffer from identity drift along with limited geometric control; conversely, traditional 3D animation workflows are consistent and editable but require expert-heavy, labor-intensive authoring. We present StoryBlender, a grounded 3D storyboard generation framework governed by a Story-centric Reflection Scheme. At its core, we propose the StoryBlender system, which is built on a three-stage pipeline: (1) Semantic-Spatial Grounding, to construct a continuity memory graph to decouple global assets from shot-specific variables for long-horizon consistency; (2) Canonical Asset Materialization, to instantiate entities in a unified coordinate space to maintain visual identity; and (3) Spatial-Temporal Dynamics, to achieve layout design and cinematic evolution through visual metrics. By orchestrating multiple agents in a hierarchical manner within a verification loop, StoryBlender iteratively self-corrects spatial hallucinations via engine-verified feedback. The resulting native 3D scenes support direct, precise editing of cameras and visual assets while preserving unwavering multi-shot continuity. Experiments demonstrate that StoryBlender significantly improves consistency and editability over both diffusion-based and 3D-grounded baselines. Code, data, and demonstration video will be available on https://engineeringai-lab.github.io/StoryBlender/

cs.CV↗

arXiv2026

Energy and mass transport associated with impulsive spicular flows in solar coronal holes

How the solar atmosphere is heated from a temperature of about $5,000-6,000$\,K in the lower atmosphere to about $1-2$\,MK in the corona has challenged the astrophysical community for about 80 years. The same puzzle exists for the stellar coronae heating as well. In this study, we present a series of findings on solar spicules and their subsequent impact on the corona within a coronal hole environment, characterized by locally open magnetic field lines, combining insights from MHD simulations with observations. We find that the convective and turbulent motions around the solar surface cause plenty of shocks and small-scale magnetic reconnection in the lower atmosphere. The combined effects of shock compression and reconnection outflows then drive the formation of groups of spicules with a quasi-period of about $300$\,s and width of $\sim 200-500$\,km. The spicule upflows provide an averaged mass flux above $10^{-9}$\,kg\,m$^{-2}$\,s$^{-1}$ in the lower corona to sustain the solar wind in coronal holes, and they continuously trigger further new local slow-mode waves and shocks. These waves supply an energy flux of $10-100$\,W\,m$^{-2}$ in the lower corona, and they are dissipated by heat conduction and compression heating to sustain the corona temperature of about $1$\,MK. The results also indicate that the upward propagating disturbances (PDs) observed in extreme ultraviolet (EUV) passbands are caused by both spicule upflows and slow-mode waves and shocks. Our findings help to understand the long standing problem of coronal heating and the origin of solar winds in coronal hole regions.

astro-ph.SR↗

arXiv2026

Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches

3D Content Generation is at the heart of many computer graphics applications, including video gaming, film-making, virtual and augmented reality, etc. This paper proposes a novel deep-learning based approach for automatically generating interactive and playable 3D game scenes, all from the user's casual prompts such as a hand-drawn sketch. Sketch-based input offers a natural, and convenient way to convey the user's design intention in the content creation process. To circumvent the data-deficient challenge in learning (i.e. the lack of large training data of 3D scenes), our method leverages a pre-trained 2D denoising diffusion model to generate a 2D image of the scene as the conceptual guidance. In this process, we adopt the isometric projection mode to factor out unknown camera poses while obtaining the scene layout. From the generated isometric image, we use a pre-trained image understanding method to segment the image into meaningful parts, such as off-ground objects, trees, and buildings, and extract the 2D scene layout. These segments and layouts are subsequently fed into a procedural content generation (PCG) engine, such as a 3D video game engine like Unity or Unreal, to create the 3D scene. The resulting 3D scene can be seamlessly integrated into a game development environment and is readily playable. Extensive tests demonstrate that our method can efficiently generate high-quality and interactive 3D game scenes with layouts that closely follow the user's intention.

cs.CV↗

arXiv2026

T$^3$-S2S: Training-free Triplet Tuning for Sketch to Scene Synthesis in Controllable Concept Art Generation

2D concept art generation for 3D scenes is a crucial yet challenging task in computer graphics, as creating natural intuitive environments still demands extensive manual effort in concept design. While generative AI has simplified 2D concept design via text-to-image synthesis, it struggles with complex multi-instance scenes and offers limited support for structured terrain layout. In this paper, we propose a Training-free Triplet Tuning for Sketch-to-Scene (T3-S2S) generation after reviewing the entire cross-attention mechanism. This scheme revitalizes the ControlNet model for detailed multi-instance generation via three key modules: Prompt Balance ensures keyword representation and minimizes the risk of missing critical instances; Characteristic Priority emphasizes sketch-based features by highlighting TopK indices in feature channels; and Dense Tuning refines contour details within instance-related regions of the attention map. Leveraging the controllability of T3-S2S, we also introduce a feature-sharing strategy with dual prompt sets to generate layer-aware isometric and terrain-view representations for the terrain layout. Experiments show that our sketch-to-scene workflow consistently produces multi-instance 2D scenes with details aligned with input prompts.

cs.CV↗

arXiv2026

Stabilization of arbitrary structures in a three-dimensional doubly degenerate nutrient taxis system

The doubly degenerate nutrient taxis system \begin{equation}\label {0.1} \left\{ \begin{aligned} &u_{t}=\nabla \cdot (uv\nabla u)-χ\nabla \cdot (u^αv\nabla v)+\ell uv,&x\in Ω,\, t>0,\\ & v_{t}=Δv-uv,&x\in Ω,\, t>0,\\ \end{aligned} \right. \end{equation} is considered under zero-flux boundary conditions in a smoothly bounded domain $Ω\subset\mathbb{R}^3$ where $α>0,χ>0$ and $\ell> 0$. By developing a novel class of functional inequalities to address the challenges posed by the doubly degenerate diffusion mechanism in \eqref{0.1}, it is shown that for $α\in(\frac{3}{2},\frac{19}{12})$, the associated initial-boundary value problem admits a global continuous weak solution for sufficiently regular initial data. Furthermore, in an appropriate topological setting, this solution converges to an equilibrium $(u_\infty, 0)$ as $t\rightarrow \infty$. Notably, the limiting profile $u_{\infty}$ is non-homogeneous when the initial signal concentration $v_0$ is sufficiently small, provided the initial data $u_0$ is not identically constant.

math.AP↗

arXiv2025

ColonAdapter: Geometry Estimation Through Foundation Model Adaptation for Colonoscopy

Estimating 3D geometry from monocular colonoscopy images is challenging due to non-Lambertian surfaces, moving light sources, and large textureless regions. While recent 3D geometric foundation models eliminate the need for multi-stage pipelines, their performance deteriorates in clinical scenes. These models are primarily trained on natural scene datasets and struggle with specularity and homogeneous textures typical in colonoscopy, leading to inaccurate geometry estimation. In this paper, we present ColonAdapter, a self-supervised fine-tuning framework that adapts geometric foundation models for colonoscopy geometry estimation. Our method leverages pretrained geometric priors while tailoring them to clinical data. To improve performance in low-texture regions and ensure scale consistency, we introduce a Detail Restoration Module (DRM) and a geometry consistency loss. Furthermore, a confidence-weighted photometric loss enhances training stability in clinical environments. Experiments on both synthetic and real datasets demonstrate that our approach achieves state-of-the-art performance in camera pose estimation, monocular depth prediction, and dense 3D point map reconstruction, without requiring ground-truth intrinsic parameters.

eess.IV↗

arXiv2025

BachVid: Training-Free Video Generation with Consistent Background and Character

Diffusion Transformers (DiTs) have recently driven significant progress in text-to-video (T2V) generation. However, generating multiple videos with consistent characters and backgrounds remains a significant challenge. Existing methods typically rely on reference images or extensive training, and often only address character consistency, leaving background consistency to image-to-video models. We introduce BachVid, the first training-free method that achieves consistent video generation without needing any reference images. Our approach is based on a systematic analysis of DiT's attention mechanism and intermediate features, revealing its ability to extract foreground masks and identify matching points during the denoising process. Our method leverages this finding by first generating an identity video and caching the intermediate variables, and then inject these cached variables into corresponding positions in newly generated videos, ensuring both foreground and background consistency across multiple videos. Experimental results demonstrate that BachVid achieves robust consistency in generated videos without requiring additional training, offering a novel and efficient solution for consistent video generation without relying on reference images or additional training.

cs.CV↗

arXiv2025

Global classical solutions to a two-dimensional chemotaxis-fluid system involving signal-dependent degenerate diffusion

This paper is concerned with the two-dimensional chemotaxis-fluid model \begin{equation*} \begin{cases} n_t+u\cdot\nabla n=Δ(nϕ(v))+μn(1-n),\\ v_t+u\cdot\nabla v=Δv-nv,\\ u_t+ κ(u\cdot\nabla) u=Δu+n\nablaΦ-\nabla P, \quad\nabla\cdot u=0, \end{cases} \end{equation*} accounting for signal-dependent motilities of microbial populations interacting with an incompressible liquid through transport and buoyancy, where the suitably smooth function $ϕ$ satisfies $ϕ>0$ on $(0,\infty)$ with $ϕ(0)=0$ and $ϕ'(0)>0$, and the parameter $μ\geq 0$. For all reasonably regular initial data, if $μ=0$, the corresponding initial boundary value problem possesses global classical solutions with a smallness condition on $\int_Ωn_0$; whereas if $μ>0$, this problem possesses global bounded classical solutions, which can converge toward (1,0,0) as time tends to infinity when a certain small mass is imposed on the initial data $v_0$. These results extend recent results for the fluid-free system to one in a Navier-Stokes fluid environment.

math.AP↗

arXiv2025

Numerical simulation of oscillatory magnetic reconnection modulated by solar convective motions

Oscillatory magnetic reconnection is a periodic magnetic reconnection process, during which the current sheet's orientation and the magnetic connections change periodically. This periodic variation is generally considered to originate from the magnetic reconnection itself rather than from external driving processes. We conduct 2.5-dimensional radiative magnetohydrodynamic simulations to investigate the emergence of a magnetic flux tube from the convection zone into the lower corona, where the emerging magnetic fields reconnect with background ones. During the reconnection process within 5771 s, the current sheet's orientation has been reversed 41 times, corresponding to 40 oscillation periods. Notably, the longest period is 30 minutes, which is consistent with the previous observational results. We find that the main factor leading to the reversal of the current sheet's orientation is the quasi-periodic external force provided by the emergence of plasma and magnetic fields from the convection zone. We also find the shifting of the upward outflows from the reconnection region along the horizontal direction due to the alternating changes of the reconnection inflow and outflow regions. In addition to the quasi-periodic change of the current sheet orientation, the reconnection rate at the main X-point also oscillates with a period between 100-400 s, which corresponds to the period of p-mode oscillations.

astro-ph.SR↗