arXiv subjects

Xuan Zhou

Publications and source records attributed to Xuan Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2025

Universal Scaling Functions of the Gr{ü}neisen Ratio near Quantum Critical Points

The Grüneisen ratio, defined as $Γ_g \equiv (1/T) (\partial T/\partial g)_S$, serves as a highly sensitive probe for detecting quantum critical points (QCPs) driven by an external feild $g$ and for characterizing the magnetocaloric effect (MCE). Near a QCP, the Grüneisen ratio displays a universal divergence which is governed by a universality-class-dependent scaling function stemming from the scale invariance. In this work, we systematically investigate the universal scaling functions of Grüneisen ratio in both one-dimensional (1D) and two-dimensional (2D) quantum spin systems, including the transverse-field Ising model, the spin-1/2 Heisenberg model, the quantum $q$-state Potts model ($q=3,4$) and the $J_1$-$J_2$ columnar dimer model. Our approach employs the thermal tensor-network method for infinite-size 1D systems and the stochastic series expansion quantum Monte Carlo (SSE QMC) simulations for 2D systems, enabling precise calculations of the Grüneisen ratio near QCPs. Through data collapse analysis, we extract the corresponding scaling functions, which establish quantitative frameworks to interpret magnetocaloric experiments and guide the development of ultralow-temperature refrigeration.

cond-mat.str-el↗

arXiv2025

Sedeve-Kit, a Specification-Driven Development Framework for Building Distributed Systems

Developing distributed systems presents significant challenges, primarily due to the complexity introduced by non-deterministic concurrency and faults. To address these, we propose a specification-driven development framework. Our method encompasses three key stages. The first stage defines system specifications and invariants using TLA${^+}$. It allows us to perform model checking on the algorithm's correctness and generate test cases for subsequent development phases. In the second stage, based on the established specifications, we write code to ensure consistency and accuracy in the implementation. Finally, after completing the coding process, we rigorously test the system using the test cases generated in the initial stage. This process ensures system quality by maintaining a strong connection between the abstract design and the concrete implementation through continuous verification.

cs.SE↗

arXiv2025

WideSearch: Benchmarking Agentic Broad Info-Seeking

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such "wide-context" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent reliability on these large-scale collection tasks. The benchmark features 200 manually curated questions (100 in English, 100 in Chinese) from over 15 diverse domains, grounded in real user queries. Each task requires agents to collect large-scale atomic information, which could be verified one by one objectively, and arrange it into a well-organized output. A rigorous five-stage quality control pipeline ensures the difficulty, completeness, and verifiability of the dataset. We benchmark over 10 state-of-the-art agentic search systems, including single-agent, multi-agent frameworks, and end-to-end commercial systems. Most systems achieve overall success rates near 0\%, with the best performer reaching just 5\%. However, given sufficient time, cross-validation by multiple human testers can achieve a near 100\% success rate. These results demonstrate that present search agents have critical deficiencies in large-scale information seeking, underscoring urgent areas for future research and development in agentic search. Our dataset, evaluation pipeline, and benchmark results have been publicly released at https://widesearch-seed.github.io/

cs.CL↗

arXiv2025

Thin accretion disk around a Kerr black hole immersed in swirling universes

We have studied the properties of thin accretion disks around swirling-Kerr black holes, which own an extra swirling parameter describing the rotation of the immersed universe. Our results show that the swirling parameter leaves distinct imprints on the energy flux, temperature distribution and emission spectra of the disk and gives rise to some new effects that differ from those induced by the black hole's spin. With the increasing of the swirling parameter, both the energy flux and radiated temperature in the disk increase in the inner region where circular orbital radii are smaller and decrease in the outer region where circular orbital radii are larger. In contrast, these quantities consistently increase with the black hole's spin. Although the swirling parameter and the black hole's spin parameter lead to higher cut-off frequencies, the background swirling reduces the observed luminosity of the disk at lower frequencies and enhances it only at higher frequencies, which is quite distinct from that of the black hole's spin. Furthermore, the conversion efficiency increases with the black hole's spin parameter, but decreases with the swirling parameters. Additionally, the effects of the swirling parameter are found to be suppressed by the black hole's spin parameter. These results could help us further understand the properties of thin accretion disks and the swirling of the universe background.

gr-qc↗

arXiv2025

Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective

We study a common challenge in reinforcement learning for large language models (LLMs): the Zero-Reward Assumption, where non-terminal actions (i.e., intermediate token generations) receive zero task-specific immediate reward, while only the final token receives a reward for the entire response. This assumption arises frequently in practice, as precise token-level rewards are often difficult or infeasible to obtain in LLM applications. In this work, we provide a unifying theoretical perspective. We introduce the Trajectory Policy Gradient Theorem, which shows that the policy gradient based on true, unknown token-level rewards can be unbiasedly estimated using only a response-level reward model, regardless of whether the Zero-Reward Assumption holds or not, for algorithms in the REINFORCE and Actor-Critic families. This result reveals that widely used methods such as PPO, GRPO, ReMax, and RLOO inherently possess the capacity to model token-level reward signals, offering a theoretical justification for response-level reward approaches. Our findings pave the way for more practical, efficient LLM fine-tuning, allowing developers to treat training algorithms as black boxes and focus on improving the response-level reward model with auxiliary sub-models. We also offer a detailed analysis of popular RL and non-RL methods, comparing their theoretical foundations and practical advantages across common LLM tasks. Finally, we propose a new algorithm: Token-Reinforced Policy Optimization (TRePO), a theoretically grounded method that is simpler than PPO, matches GRPO in memory efficiency, and holds promise for broad applicability.

cs.LG↗

arXiv2025

SynchroStore: A Cost-Based Fine-Grained Incremental Compaction for Hybrid Workloads

This study proposes a novel storage engine, SynchroStore, designed to address the inefficiency of update operations in columnar storage systems based on Log-Structured Merge Trees (LSM-Trees) under hybrid workload scenarios. While columnar storage formats demonstrate significant query performance advantages when handling large-scale datasets, traditional columnar storage systems face challenges such as high update complexity and poor real-time performance in data-intensive applications. SynchroStore introduces an incremental row storage mechanism and a fine-grained row-to-column transformation and compaction strategy, effectively balancing data update efficiency and query performance. The storage system employs an in-memory row storage structure to support efficient update operations, and the data is converted to a columnar format after freezing to support high-performance read operations. The core innovations of SynchroStore are reflected in the following aspects:(1) the organic combination of incremental row storage and columnar storage; (2) a fine-grained row-to-column transformation and compaction mechanism; (3) a cost-based scheduling strategy. These innovative features allow SynchroStore to leverage background computational resources for row-to-column transformation and compaction operations, while ensuring query performance is unaffected, thus effectively solving the update performance bottleneck of columnar storage under hybrid workloads. Experimental evaluation results show that, compared to existing columnar storage systems like DuckDB, SynchroStore exhibits significant advantages in update performance under hybrid workloads.

cs.DB↗

arXiv2025

Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models

Exploratory data analysis (EDA), coupled with SQL, is essential for data analysts involved in data exploration and analysis. However, data analysts often encounter two primary challenges: (1) the need to craft SQL queries skillfully, and (2) the requirement to generate suitable visualization types that enhance the interpretation of query results. Due to its significance, substantial research efforts have been made to explore different approaches to address these challenges, including leveraging large language models (LLMs). However, existing methods fail to meet real-world data exploration requirements primarily due to (1) complex database schema; (2) unclear user intent; (3) limited cross-domain generalization capability; and (4) insufficient end-to-end text-to-visualization capability. This paper presents TiInsight, an automated SQL-based cross-domain exploratory data analysis system. First, we propose hierarchical data context (i.e., HDC), which leverages LLMs to summarize the contexts related to the database schema, which is crucial for open-world EDA systems to generalize across data domains. Second, the EDA system is divided into four components (i.e., stages): HDC generation, question clarification and decomposition, text-to-SQL generation (i.e., TiSQL), and data visualization (i.e., TiChart). Finally, we implemented an end-to-end EDA system with a user-friendly GUI interface in the production environment at PingCAP. We have also open-sourced all APIs of TiInsight to facilitate research within the EDA community. Through extensive evaluations by a real-world user study, we demonstrate that TiInsight offers remarkable performance compared to human experts. Specifically, TiSQL achieves an execution accuracy of 86.3% on the Spider dataset using GPT-4. It also demonstrates state-of-the-art performance on the Bird dataset.

cs.DB↗

arXiv2024

Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system (RMFS). Existing research indicates that hierarchical reinforcement learning (HRL) is an effective method to reduce these challenges. Based on that, we construct an efficient multi-stage HRL-based multi-robot task planner for hyper scale MRTP in RMFS, and the planning process is represented with a special temporal graph topology. To ensure optimality, the planner is designed with a centralized architecture, but it also brings the challenges of scaling up and generalization that require policies to maintain performance for various unlearned scales and maps. To tackle these difficulties, we first construct a hierarchical temporal attention network (HTAN) to ensure basic ability of handling inputs with unfixed lengths, and then design multi-stage curricula for hierarchical policy learning to further improve the scaling up and generalization ability while avoiding catastrophic forgetting. Additionally, we notice that policies with hierarchical structure suffer from unfair credit assignment that is similar to that in multi-agent reinforcement learning, inspired of which, we propose a hierarchical reinforcement learning algorithm with counterfactual rollout baseline to improve learning performance. Experimental results demonstrate that our planner outperform other state-of-the-art methods on various MRTP instances in both simulated and real-world RMFS. Also, our planner can successfully scale up to hyper scale MRTP instances in RMFS with up to 200 robots and 1000 retrieval racks on unlearned maps while keeping superior performance over other methods.

cs.RO↗

arXiv2024

Large Language Models in the Clinic: A Comprehensive Benchmark

The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical decisions involve answering open-ended questions without pre-set options. To better understand LLMs in the clinic, we construct a benchmark ClinicBench. We first collect eleven existing datasets covering diverse clinical language generation, understanding, and reasoning tasks. Furthermore, we construct six novel datasets and clinical tasks that are complex but common in real-world practice, e.g., open-ended decision-making, long document processing, and emerging drug analysis. We conduct an extensive evaluation of twenty-two LLMs under both zero-shot and few-shot settings. Finally, we invite medical experts to evaluate the clinical usefulness of LLMs. The benchmark data is available at https://github.com/AI-in-Health/ClinicBench.

cs.CL↗

arXiv2024

The Cauchy problem for the Degasperis-Procesi Equation: Painlevé Asymptotics in Transition Zones

The Degasperis-Procesi (DP) equation \begin{align} &u_t-u_{txx}+3κu_x+4uu_x=3u_x u_{xx}+uu_{xxx}, \nonumber \end{align} serving as an asymptotic approximation for the unidirectional propagation of shallow water waves, is an integrable model of the Camassa-Holm type and admits a $3\times3$ matrix Lax pair. In our previous work, we obtained the long-time asymptotics of the solution $u(x,t)$ to the Cauchy problem for the DP equation in the solitonic region $\{(x,t): ξ>3 \} \cup \{(x,t): ξ<-\frac{3}{8} \}$ and the solitonless region $\{(x,t): -\frac{3}{8}<ξ< 0 \} \cup \{(x,t): 0\leq ξ<3 \}$ where $ξ:=\frac{x}{t}$. In this paper, we derive the leading order approximation to the solution $u(x,t)$ in terms of the solution for the Painlevé \uppercase\expandafter{\romannumeral2} equation in two transition zones $\left|ξ+\frac{3}{8}\right|t^{2/3} 0$ lying between the solitonic region and solitonless region. Our results are established by performing the $\bar \partial$-generalization of the Deift-Zhou nonlinear steepest descent method and applying a double scaling limit technique to an associated vector Riemann-Hilbert problem.

math.AP↗

arXiv2024

Soliton resolution and asymptotic stability of $N$-solitons to the Degasperis-Procesi equation on the line

The Degasperis-Procesi (DP) equation \begin{align} &u_t-u_{txx}+3κu_x+4uu_x=3u_x u_{xx}+uu_{xxx}, \nonumber \end{align} serving as a model delineating the propagation of shallow water waves, stands as a completely integrable system and admits a $3\times3$ matrix Lax pair. In this manuscript, we study the soliton resolution and large time behavior of solutions to the Cauchy problem of the DP equation with generic initial data in Schwarz space. Employing the $\bar \partial$-generalization of the Deift-Zhou nonlinear steepest descent method, we deduce different long time asymptotic expansions of the solution $u(x,t)$ in two distinct types of space-time regions. This result verifies the soliton resolution conjecture and asymptotic stability of $N$-soliton solutions for the DP equation.

math-ph↗

arXiv2024

Incremental SWAP Operator for Entanglement Entropy: Application for Exponential Observables in Quantum Monte Carlo Simulation

We propose a new method to efficiently compute the entanglement entropy (EE) of quantum many-body systems. Our approach, called the incremental SWAP operator method , combines the simplicity of the SWAP operator used in projector quantum Monte Carlo simulations with recent advances in precisely computing exponential observables using incremental algorithms. We apply this technique to obtain accurate EE data at reduced computational cost for 1d and 2d antiferromagnetic Heisenberg models with different bipartition schemes. Using the computed EE data, we extract the area law coefficient, universal logarithmic corrections from Goldstone modes, and the geometric constant, finding quantitative agreement with analytical predictions. Moreover, for the first time in an unbiased numerical simulation of 2d antiferromagnetic Heisenberg model, we successfully obtain reliable universal logarithmic corrections from sharp corners that match expected theoretical values. The consistency between our numerical results and theoretical calculations demonstrates the power of our approach for accessing challenging universal entanglement properties. The extensions of our method to other quantum spin/boson models and the interacting fermion models, are outlined.

cond-mat.str-el↗

arXiv2024

Geometrically thick equilibrium tori around a dyonic black hole with quasi-topological electromagnetism

We study geometrically thick and non-self gravitating equilibrium tori orbiting a static spherically symmetric dyonic black hole with quasi-topological electromagnetism. Our results show that the electric and magnetic charges together with the coupling parameter in the quasi-topological electromagnetism lead to a much richer class of equilibrium tori. There are a range of parameters which allow for the existence of double tori. The properties of double equilibrium tori become far richer. There exist transitions between single torus and double tori solutions as we change the specific angular momentum of the fluid. These properties of equilibrium tori could help to understand the dyonic black hole and its thick accretion disk.

gr-qc↗

arXiv2023

Fast Commitment for Geo-Distributed Transactions via Decentralized Co-coordinators

In a geo-distributed database, data shards and their respective replicas are deployed in distinct datacenters across multiple regions, enabling regional-level disaster recovery and the ability to serve global users locally. However, transaction processing in geo-distributed databases requires multiple cross-region communications, especially during the commit phase, which can significantly impact system performance. To optimize the performance of geo-distributed transactions, we propose Decentralized Two-phase Commit (D2PC), a new transaction commit protocol aiming to minimize the negative impact of cross-region communication. In D2PC, we employ multiple co-coordinators that perform commit coordination in parallel. Each co-coordinator is responsible for collecting 2PC votes and making a PreCommit decision in its local region. This approach allows for the concurrent invocation of multiple cross-region network round trips, and each region can conclude its concurrency control locally before replication is complete, thus significantly reducing the chances of blocking and enhancing system concurrency. Moreover, we propose the bypass leader replication reply method, leveraging decentralized co-coordinators to bypass the leader for message transmission, thereby reducing the commit latency. Experimental results have demonstrated that D2PC can reduce commit latency by 43% and improve throughput by up to 2.43 times compared to the existing alternative geo-distributed transaction processing methods.

cs.DB↗

arXiv2023

he Cauchy problem for the Novikov equation under a nonzero background: Painlevé asymptotics in a transition zone

In this paper, we investigate the Painlevé asymptotics in a transition zone for the solutions to the Cauchy problem of the Novikov equation under a nonzero background \begin{align} &u_{t}-u_{txx}+4 u_{x}=3uu_xu_{xx}+u^2u_{xxx}, \nonumber &u(x, 0)=u_{0}(x),\nonumber \end{align} where $u_0(x)\rightarrow κ>0, \ x\rightarrow \pm \infty$ and $u_0(x)-κ$ is assumed in the Schwarz space. This result is established by performing the $\overline\partial$-steepest descent analysis to a Riemann-Hilbert problem associated with the the Cauchy problem in a new spatial scale \begin{equation*} y = x - \int_{x}^{\infty} \left((u-u_{xx}+1)^{2/3}-1\right)ds, \end{equation*} for large times in the transition zone $y/t \approx -1/8 $. It is shown that the leading order term of the asymptotic approximation comes from the contribution of solitons, while the sub-leading term is related to the solution of the Painlevé \uppercase\expandafter{\romannumeral2} equation.n.

math.AP↗

arXiv2023

The Case of Transparent Cache Invalidation in Web Applications

Application-level caches are widely adopted by web applications to minimize the response time of user requests as well as to reduce the burden on the system backend, such as the database servers. In the state of practice, developers have to take care of the data freshness of application-level caches manually. Given the growing complexities of today's web applications, it becomes increasingly challenging for developers to understand, reason about, and implement cache invalidation methods. Furthermore, according to our survey of open-source web application projects and engineers, it is indeed challenging to map database updates with cache entries at the application level. Therefore, we propose a design to handle data validity in a transparent and precise manner, without requiring any intervention from developers. Its main idea is to modify the DBMS to provide necessary information for cache management and enhance the cache with an invalidation index to identify and invalidate outdated data automatically and efficiently. Based on the design, we further provide two specific solutions. Our preliminary experiments indicate that our solutions could effectively achieve transparent cache invalidation while maintaining cost-effectiveness.

cs.DB↗

arXiv2023

Sampling Algorithms for Butterfly Counting on Temporal Bipartite Graphs

Temporal bipartite graphs are widely used to denote time-evolving relationships between two disjoint sets of nodes, such as customer-product interactions in E-commerce and user-group memberships in social networks. Temporal butterflies, $(2,2)$-bicliques that occur within a short period and in a prescribed order, are essential in modeling the structural and sequential patterns of such graphs. Counting the number of temporal butterflies is thus a fundamental task in analyzing temporal bipartite graphs. However, existing algorithms for butterfly counting on static bipartite graphs and motif counting on temporal unipartite graphs are inefficient for this purpose. In this paper, we present a general framework with three sampling strategies for temporal butterfly counting. Since exact counting can be time-consuming on large graphs, our approach alternatively computes approximate estimates accurately and efficiently. We also provide analytical bounds on the number of samples each strategy requires to obtain estimates with small relative errors and high probability. We finally evaluate our framework on six real-world datasets and demonstrate its superior accuracy and efficiency compared to several baselines. Overall, our proposed framework and sampling strategies provide efficient and accurate approaches to approximating temporal butterfly counts on large-scale temporal bipartite graphs.

cs.SI↗

arXiv2023

FLDNet: A Foreground-Aware Network for Polyp Segmentation Leveraging Long-Distance Dependencies

Given the close association between colorectal cancer and polyps, the diagnosis and identification of colorectal polyps play a critical role in the detection and surgical intervention of colorectal cancer. In this context, the automatic detection and segmentation of polyps from various colonoscopy images has emerged as a significant problem that has attracted broad attention. Current polyp segmentation techniques face several challenges: firstly, polyps vary in size, texture, color, and pattern; secondly, the boundaries between polyps and mucosa are usually blurred, existing studies have focused on learning the local features of polyps while ignoring the long-range dependencies of the features, and also ignoring the local context and global contextual information of the combined features. To address these challenges, we propose FLDNet (Foreground-Long-Distance Network), a Transformer-based neural network that captures long-distance dependencies for accurate polyp segmentation. Specifically, the proposed model consists of three main modules: a pyramid-based Transformer encoder, a local context module, and a foreground-Aware module. Multilevel features with long-distance dependency information are first captured by the pyramid-based transformer encoder. On the high-level features, the local context module obtains the local characteristics related to the polyps by constructing different local context information. The coarse map obtained by decoding the reconstructed highest-level features guides the feature fusion process in the foreground-Aware module of the high-level features to achieve foreground enhancement of the polyps. Our proposed method, FLDNet, was evaluated using seven metrics on common datasets and demonstrated superiority over state-of-the-art methods on widely-used evaluation measures.

cs.CV↗