arXiv subjects

Ruoyu Wu

Publications and source records attributed to Ruoyu Wu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scenarios by compressing high-resolution meshes into compact, editable representations. Towards this end, effective shape abstraction must therefore be structure-aware, characterized by low overlap between primitives, part-aware alignment, and primitive compactness. We present Light-SQ, a novel superquadric-based optimization framework that explicitly emphasizes structure-awareness from three aspects. (a) We introduce SDF carving to iteratively udpate the target signed distance field, discouraging overlap between primitives. (b) We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition, enabling structural partitioning to drive primitive placement. (c) We implement adaptive residual pruning based on SDF update history to surpress over-segmentation and ensure compact results. In addition, Light-SQ supports multiscale fitting, enabling localized refinement to preserve fine geometric details. To evaluate our method, we introduce 3DGen-Prim, a benchmark extending 3DGen-Bench with new metrics for both reconstruction quality and primitive-level editability. Extensive experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics for complex generated geometry, advancing the feasibility of 3D UGC creation.

cs.GR↗

arXiv2025

From "What to Eat?" to Perfect Recipe: ChefMind's Chain-of-Exploration for Ambiguous User Intent in Recipe Recommendation

Personalized recipe recommendation faces challenges in handling fuzzy user intent, ensuring semantic accuracy, and providing sufficient detail coverage. We propose ChefMind, a hybrid architecture combining Chain of Exploration (CoE), Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM). CoE refines ambiguous queries into structured conditions, KG offers semantic reasoning and interpretability, RAG supplements contextual culinary details, and LLM integrates outputs into coherent recommendations. We evaluate ChefMind on the Xiachufang dataset and manually annotated queries, comparing it with LLM-only, KG-only, and RAG-only baselines. Results show that ChefMind achieves superior performance in accuracy, relevance, completeness, and clarity, with an average score of 8.7 versus 6.4-6.7 for ablation models. Moreover, it reduces unprocessed queries to 1.6%, demonstrating robustness in handling fuzzy demands.

cs.AI↗

arXiv2025

Large Deviation Asymptotics for the Supermarket Model with Growing Choices

We consider the Markovian supermarket model with growing choices, where jobs arrive at rate $nλ_n$ and each of $n$ parallel servers processes jobs in its queue at rate $1$. Each incoming job joins the shortest among $d_n \in \{1,\dotsc,n\}$ randomly selected queues. Under the assumption $d_n \to \infty$ and $λ_n \to λ\in (0,\infty)$ as $n\to \infty$, a large deviation principle (LDP) for the occupancy process is established in a suitable infinite-dimensional path space, and it is shown that the rate function is invariant with respect to the manner in which $d_n \to \infty$. The LDP gives information on the rate of decay of probabilities of various types of rare events associated with the system. We illustrate this by establishing explicit exponential decay rates for probabilities of large total number of jobs in the system. As a corollary, we also show that probabilities of certain rare events can indeed depend on the rate of $d_n \to \infty$.

math.PR↗

arXiv2025

Many-Server Asymptotics for Join-the-Shortest-Queue: Large Deviations and Rare Events

The Join-the-Shortest-Queue routing policy is studied in an asymptotic regime where the number of processors $n$ scales with the arrival rate. A large deviation principle (LDP) for the occupancy process is established, as $n\to \infty$, in a suitable infinite-dimensional path space. Model features that present technical challenges include, Markovian dynamics with discontinuous statistics, a diminishing rate property of the transition probability rates, and an infinite-dimensional state space. The difficulty is in the proof of the Laplace lower bound which requires establishing the uniqueness of solutions of certain infinite-dimensional systems of controlled ordinary differential equations. The LDP gives information on the rate of decay of probabilities of various types of rare events associated with the system. We illustrate this by establishing explicit exponential decay rates for probabilities of long queues. In particular, denoting by $E_j^n(T)$ the event that there is at least one queue with $j$ or more jobs at some time instant over $[0,T]$, we show that, in the critical case, for large $n$ and $T$, $\mathbb{P}(E^n_j(T)) \approx \exp\left [-\frac{n (j-2)^2}{4T}\right].$

math.PR↗

arXiv2025

Probabilistic cellular automata with local transition matrices: synchronization, ergodicity, and inference

We introduce a new class of probabilistic cellular automata that are capable of exhibiting rich dynamics such as synchronization and ergodicity and can be easily inferred from data. The system is a finite-state locally interacting Markov chain on a circular graph. Each site's subsequent state is random, with a distribution determined by its neighborhood's empirical distribution multiplied by a local transition matrix. We establish sufficient and necessary conditions on the local transition matrix for synchronization and ergodicity. Also, we introduce novel least squares estimators for inferring the local transition matrix from various types of data, which may consist of either multiple trajectories, a long trajectory, or ensemble sequences without trajectory information. Under suitable identifiability conditions, we show the asymptotic normality of these estimators and provide non-asymptotic bounds for their accuracy.

math.PR↗

arXiv2025

Moderate Deviation Principle for Join-The-Shortest-Queue-d Systems

The Join-the-Shortest-Queue-d routing policy is considered for a large system with $n$ servers. Moderate deviation principles (MDP) for the occupancy process and the empirical queue length process are established as $n\to \infty$. Each MDP is formulated in terms of a large deviation principle with an appropriate speed function in a suitable infinite-dimensional path space. Proofs rely on certain variational representations for exponential functionals of Poisson random measures. As a case study, the convergence of rate functions for systems with finite buffer size $K$ to the rate function without buffer is analyzed, as $K \to \infty$.

math.PR↗

arXiv2024

Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

Building on the foundations of language modeling in natural language processing, Next Token Prediction (NTP) has evolved into a versatile training objective for machine learning tasks across various modalities, achieving considerable success. As Large Language Models (LLMs) have advanced to unify understanding and generation tasks within the textual modality, recent research has shown that tasks from different modalities can also be effectively encapsulated within the NTP framework, transforming the multimodal information into tokens and predict the next one given the context. This survey introduces a comprehensive taxonomy that unifies both understanding and generation within multimodal learning through the lens of NTP. The proposed taxonomy covers five key aspects: Multimodal tokenization, MMNTP model architectures, unified task representation, datasets \& evaluation, and open challenges. This new taxonomy aims to aid researchers in their exploration of multimodal intelligence. An associated GitHub repository collecting the latest papers and repos is available at https://github.com/LMM101/Awesome-Multimodal-Next-Token-Prediction

cs.CL↗

arXiv2024

ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12

As Computational Thinking (CT) continues to permeate younger age groups in K-12 education, established CT platforms such as Scratch face challenges in catering to these younger learners, particularly those in the elementary school (ages 6-12). Through formative investigation with Scratch experts, we uncover three key obstacles to children's autonomous Scratch learning: artist's block in project planning, bounded creativity in asset creation, and inadequate coding guidance during implementation. To address these barriers, we introduce ChatScratch, an AI-augmented system to facilitate autonomous programming learning for young children. ChatScratch employs structured interactive storyboards and visual cues to overcome artist's block, integrates digital drawing and advanced image generation technologies to elevate creativity, and leverages Scratch-specialized Large Language Models (LLMs) for professional coding guidance. Our study shows that, compared to Scratch, ChatScratch efficiently fosters autonomous programming learning, and contributes to the creation of high-quality, personally meaningful Scratch projects for children.

cs.HC↗

arXiv2023

Online Task Assignment with Controllable Processing Time

We study a new online assignment problem, called the Online Task Assignment with Controllable Processing Time. In a bipartite graph, a set of online vertices (tasks) should be assigned to a set of offline vertices (machines) under the known adversarial distribution (KAD) assumption. We are the first to study controllable processing time in this scenario: There are multiple processing levels for each task and higher level brings larger utility but also larger processing delay. A machine can reject an assignment at the cost of a rejection penalty, taken from a pre-determined rejection budget. Different processing levels cause different penalties. We propose the Online Machine and Level Assignment (OMLA) Algorithm to simultaneously assign an offline machine and a processing level to each online task. We prove that OMLA achieves $1/2$-competitive ratio if each machine has unlimited rejection budget and $Δ/(3Δ-1)$-competitive ratio if each machine has an initial rejection budget up to $Δ$. Interestingly, the competitive ratios do not change under different settings on the controllable processing time and we can conclude that OMLA is "insensitive" to the controllable processing time.

cs.DS↗

arXiv2022

Exploiting Data Locality to Improve Performance of Heterogeneous Server Clusters

We consider load balancing in large-scale heterogeneous server systems in the presence of data locality that imposes constraints on which tasks can be assigned to which servers. The constraints are naturally captured by a bipartite graph between the servers and the dispatchers handling assignments of various arrival flows. When a task arrives, the corresponding dispatcher assigns it to a server with the shortest queue among $d\geq 2$ randomly selected servers obeying the above constraints. Server processing speeds are heterogeneous and they depend on the server-type. For a broad class of bipartite graphs, we characterize the limit of the appropriately scaled occupancy process, both on the process-level and in steady state, as the system size becomes large. Using such a characterization, we show that data locality constraints can be used to significantly improve the performance of heterogeneous systems. This is in stark contrast to either heterogeneous servers in a full flexible system or data locality constraints in systems with homogeneous servers, both of which have been observed to degrade the system performance. Extensive numerical experiments corroborate the theoretical results.

math.PR↗

arXiv2022

Graphon particle system: Uniform-in-time concentration bounds

In this paper, we consider graphon particle systems with heterogeneous mean-field type interactions and the associated finite particle approximations. Under suitable growth (resp. convexity) assumptions, we obtain uniform-in-time concentration estimates, over finite (resp. infinite) time horizon, for the Wasserstein distance between the empirical measure and its limit, extending the work of Bolley--Guillin--Villani.

math.PR↗

arXiv2022

Graphon mean field systems

We consider heterogeneously interacting diffusive particle systems and their large population limit. The interaction is of mean field type with weights characterized by an underlying graphon. A law of large numbers result is established as the system size increases and the underlying graphons converge. The limit is given by a graphon mean field system consisting of independent but heterogeneous nonlinear diffusions whose probability distributions are fully coupled. Well-posedness, continuity and stability of such systems are provided. We also consider a not-so-dense analogue of the finite particle system, obtained by percolation with vanishing rates and suitable scaling of interactions. A law of large numbers result is proved for the convergence of such systems to the corresponding graphon mean field system.

math.PR↗

arXiv2022

Local weak convergence for sparse networks of interacting processes

We study the limiting behavior of interacting particle systems indexed by large sparse graphs, which evolve either according to a discrete time Markov chain or a diffusion, in which particles interact directly only with their nearest neighbors in the graph. To encode sparsity we work in the framework of local weak convergence of marked (random) graphs. We show that the joint law of the particle system varies continuously with respect to local weak convergence of the underlying graph marked with the initial conditions. In addition, we show that the global empirical measure converges to a non-random limit for a large class of graph sequences including sparse Erdös-Rényi graphs and configuration models, whereas the empirical measure of the connected component of a uniformly random vertex converges to a random limit. Along the way, we develop some related results on the time-propagation of ergodicity and empirical field convergence, as well as some general results on local weak convergence of Gibbs measures in the uniqueness regime which appear to be new. The results obtained here are also useful for obtaining autonomous descriptions of marginal dynamics of interacting diffusions and Markov chains on sparse graphs. While limits of interacting particle systems on dense graphs have been extensively studied, there are relatively few works that have studied the sparse regime in generality.

math.PR↗

arXiv2022

Propagation of Chaos of Forward-Backward Stochastic Differential Equations with Graphon Interactions

In this paper, we study graphon mean field games using a system of forward-backward stochastic differential equations. We establish the existence and uniqueness of solutions under two different assumptions and prove the stability with respect to the interacting graphons which are necessary to show propagation of chaos results. As an application of propagation of chaos, we prove the convergence of n-player game Nash equilibrium for a general model, which is new in the theory of graphon mean field games.

math.PR↗

arXiv2021

Mean field interaction on random graphs with dynamically changing multi-color edges

We consider weakly interacting jump processes on time-varying random graphs with dynamically changing multi-color edges. The system consists of a large number of nodes in which the node dynamics depends on the joint empirical distribution of all the other nodes and the edges connected to it, while the edge dynamics depends only on the corresponding nodes it connects. Asymptotic results, including law of large numbers, propagation of chaos, and central limit theorems, are established. In contrast to the classic McKean-Vlasov limit, the limiting system exhibits a path-dependent feature in that the evolution of a given particle depends on its own conditional distribution given its past trajectory. We also analyze the asymptotic behavior of the system when the edge dynamics is accelerated. A law of large number and a propagation of chaos result is established, and the limiting system is given as independent McKean-Vlasov processes. Error between the two limiting systems, with and without acceleration in edge dynamics, is also analyzed.

math.PR↗

arXiv2021

Marginal dynamics of interacting diffusions on unimodular Galton-Watson trees

Consider a system of homogeneous interacting diffusive particles labeled by the nodes of a unimodular Galton-Watson (UGW) tree, where the state of each node evolves like a d-dimensional diffusion whose drift coefficient depends on (the histories of) its own state and the states of neighboring nodes, and whose diffusion coefficient depends only on (the history of) its own state. Under suitable regularity assumptions on the coefficients, an autonomous characterization is obtained for the marginal distribution of the dynamics of the neighborhood of a typical node in terms of a certain local equation, which is a new kind of SDE that is nonlinear in the sense of McKean. This equation describes a finite-dimensional non-Markovian stochastic process whose evolution at any time depends not only on the structure and current state of the neighborhood, but also on the conditional law of the current state given the past of the states of neighborhing nodes. Such marginal distributions are of interest because they arise as weak limits of both marginal distributions and empirical measures of interacting diffusions on many sequences of sparse random graphs, including the configuration model and Erdos-Renyi graphs whose average degrees converge to a finite non-zero limit. The results obtained complement classical results in the mean-field regime, which characterize the limiting dynamics of homogeneous interacting diffusions on complete graphs, as the number of nodes goes to infinity, in terms of a corresponding nonlinear Markov process. However, in the sparse graph setting, the topology of the graph strongly influences the dynamics, and the analysis requires a completely different approach. The proofs of existence and uniqueness of the local equation rely on delicate new conditional independence and symmetry properties of particle trajectories on UGW trees, as well as judicious use of changes of measure.

math.PR↗

arXiv2021

Stationarity and uniform in time convergence for the graphon particle system

We consider the long time behavior of heterogeneously interacting diffusive particle systems and their large population limit. The interaction is of mean field type with weights characterized by an underlying graphon. The limit is given by a graphon particle system consisting of independent but heterogeneous nonlinear diffusions whose probability distributions are fully coupled. Under suitable assumptions, including a certain convexity condition, we show the exponential ergodicity for both systems, establish the uniform-in-time law of large numbers for marginal distributions as the number of particles increases, and introduce the uniform-in-time Euler approximation. The precise rate of convergence of the Euler approximation is provided.

math.PR↗

arXiv2020

Locally interacting diffusions as space-time Markov random fields

We consider a countable system of interacting (possibly non-Markovian) stochastic differential equations driven by independent Brownian motions and indexed by the vertices of a locally finite graph $G = (V,E)$. The drift of the process at each vertex is influenced by the states of that vertex and its neighbors, and the diffusion coefficient depends on the state of only that vertex. Such processes arise in a variety of applications including statistical physics, neuroscience, engineering and math finance. Under general conditions on the coefficients, we show that if the initial conditions form a second-order Markov random field on $d$-dimensional Euclidean space, then at any positive time, the collection of histories of the processes at different vertices forms a second-order Markov random field on path space. We also establish a bijection between (second-order) Gibbs measures on $(\R^d)^V$ (with finite second moments) and a set of space-time (second-order) Gibbs measures on path space, corresponding respectively to the initial law and the law of the solution to the stochastic differential equation. As a corollary, we establish a Gibbs uniqueness property that shows that for infinite graphs the joint distribution of the paths is completely determined by the initial condition and the specifications, namely the family of conditional distributions on finite vertex sets given the configuration on the complement. Along the way, we establish various approximation and projection results for Markov random fields on locally finite graphs that may be of independent interest.

math.PR↗