arXiv subjects

Ying Zhang

Publications and source records attributed to Ying Zhang.

At least 19 recordsLinked to original sources

arXiv2026

VeriNC: Finding Design Risks of In-Network Computing Systems

The emergence of programmable switches has brought in-network computing (INC) into the spotlight in recent years. By offloading computation directly onto the data transmission process, INC improves network utilization, reduces latency to sub-RTT levels, saves link bandwidth, and maintains throughput. However, INC disrupts the transparency of traditional networks, forcing developers to consider network exceptions like packet loss and out-of-order. If not properly handled, these exceptions can lead to violations of application properties, such as cache consistency and lock exclusion. Usual testing cannot exhaustively cover these exceptions, raising doubts about the correctness of INC systems and hindering their deployment in the industry. This paper presents VeriNC, the first general-purpose tool for verifying INC systems. VeriNC provides a high-level specification language and saves developers 67.2% lines of code on average. To help better understand the behavior of the system, VeriNC offers configurable network environments. VeriNC enables developers to express INC-specific correctness properties. VeriNC translates developer-specified systems into state transition representations, performs model checking to detect potential design risks, and reports violation traces to developers. We propose optimizations for INC-specific scenarios to address the challenge of state space explosion. We modeled INC systems across four application domains and identified design risks with VeriNC in seconds. VeriNC has also been adopted to guide the design of a new INC protocol. Based on our verification experience, we summarize lessons that help develop a correct INC protocol. We further reproduce them in real systems to confirm the validity of our verification result.

cs.DC↗

arXiv2026

A research world model of power engineering learns its dynamics and reveals what-ifs

Decisions about the direction of research in power engineering determine which technologies mature and, through them, shape infrastructure that lasts decades, yet their consequences cannot be observed before they are taken, and existing forecasts of research fields extrapolate a single trajectory. Here we introduce research world models, which treat a research field as a dynamical system that can be acted upon, and establish one for power engineering from 1.1 million papers. A distilled language model reads each paper into role-typed concepts, two sophisticated, high-fidelity graph-temporal neural network cores learn how the resulting concept network evolves, and operators learned from natural experiments in the publication record estimate the effects of interventions. In temporally held-out tests, the model forecast years ahead which concepts would grow and which method-target pairs would be joined for the first time, outperforming tuned machine-learning baselines in most settings, and its estimated intervention effects tracked those realized in natural experiments it had not seen. Its training scheme and three of its operators replicated in two fields withheld from development. Questions posed in natural language are compiled by a domain-specialized 27-billion-parameter language model into executable actions and answered as paired simulations with and without the intervention. The answers were rated 4.1 of 5 for faithfulness by an independent language-model judge. By revealing the latent dynamics of a research field and its response to interventions, research world models offer a new way to simulate and test research decisions before they are made.

cs.AI↗

arXiv2026

LatentTriad: Pre-Action Risk Representations for Malicious Agent Skill Detection

Large language model agents are increasingly extended with reusable skills, but untrusted skill content can induce operations outside the user's task. Detecting this contextual risk requires more than suspicious-pattern matching, while dynamic analysis incurs the cost of skill execution. We find that hidden states formed during prefill contain readable information about task-operation consistency, including across held-out expression forms in controlled evaluations. Matched Operation-state interventions also affect later Boundary states and shift fixed risk readouts toward the donor label. Based on these findings, we introduce LatentTriad, which combines contextual Boundary features, group-adjusted Operation directions, and departures from benign state relationships. All branches share one prefill: detection generates no output tokens, invokes no tools, and executes no skill code. Across 5,830 skill packages from five sources and seven backbones, LatentTriad achieves 99.0-99.2% pooled F1 and 93.0-94.6% source-macro F1. A separately measured compact implementation completes prefill and detection in a median of 259-284 ms. These results connect pre-action risk readability and functional influence to execution-free skill screening.

cs.AI↗

arXiv2026

Non-asymptotic analysis of SGLD with discontinuous stochastic gradients: a new route to portfolio CVaR minimization

Conditional-Value-at-Risk (CVaR) optimization is a fundamental tool in portfolio selection, yet its nonsmooth loss structure poses a challenge for the existing theory of stochastic gradient methods including associated Langevin algorithms. In particular, the positive-part loss and the softmax portfolio parametrization lead to stochastic gradients that need not be globally Lipschitz continuous, but rather discontinuous, where available non-convex stochastic gradient Langevin dynamics (SGLD) guarantees often exhibit an unfavorable exponential dependence on the problem dimension. In this article, we develop a non-asymptotic analysis of SGLD for a regularized CVaR portfolio optimization problem. We exploit the geometric structure of the CVaR objective to establish linear growth, convexity-at-infinity, and one-sided Lipschitz properties of the stochastic gradient without imposing density assumptions on the asset losses that are typical in previous works. Crucially, the constants appearing in the aforementioned structural conditions are shown to be independent of the number of assets. Moreover, we establish a convergence bound in Wasserstein-2 distance with rate $\mathcal{O}(λ^{1/4})$ and a finite-time guarantee for the expected excess risk. Our analysis, together with the dimension-independent constants in the structural conditions, leads to an excess risk bound that depends linearly on the number of assets. Numerical experiments with simulated Gaussian portfolios exhibit the predicted dimension dependence. Computational comparisons with alternative stochastic optimization methods further illustrate the practical efficiency of SGLD for the optimization problem under consideration. Finally, we extend the framework to a broader class of non-convex stochastic optimization problems with discontinuous stochastic gradients.

q-fin.PM↗

arXiv2026

A Computational Verification of the Markov Uniqueness Conjecture for $z\leq 10^{500000}$

We describe a finite computational verification of Markov Uniqueness Conjecture for normalized positive integer solutions of $x^2+y^2+z^2=3xyz$ with $z \leq 10^{500000}$. The archived run reports $239\,536\,376\,556$ triples with distinct maximal coordinates.The method combines a disjoint tree decomposition, certified fixed-point range bounds, a deterministic 48-bit candidate screen,and replay modulo $2^{128}$. We give the mathematical justification and a reproducibility procedure covering package checks,retained-data auditing, and a full rerun. The conclusion depends on correct execution of the exhaustive screen and replay; the retained audit does not regenerate the deleted screening buckets.

math.GM↗

arXiv2026

Uniform cubic bounds for irrational values of the dilogarithm

We study explicit denominator conditions ensuring the irrationality of the dilogarithm at positive and negative rational points. We prove that $\operatorname{Li}_2(p/q)$ is irrational whenever $q>(4e^4/27)p^3$, and obtain an explicit, slightly smaller threshold for $\operatorname{Li}_2(-p/q)$. The positive argument specializes the Rhin--Viola integral family and uses a uniform estimate for a restricted prime divisor. The negative argument combines the same arithmetic construction with three adjacent integral moments and an explicit maximization. We also give finite-numerator refinements by interpolating certified partition bounds and by introducing a comparison measure with a quadratic tail. In particular, $\operatorname{Li}_2(5/q)$ is irrational for every integer $q\ge418$. The proof separates the established integral and determinant constructions from the parameter estimates and finite certificates used here.

math.NT↗

arXiv2026

From Evaluation to Evolution: Benchmarking Image Editing and Evolving Image Models

Real-world image editing requires coordinating multiple visual transformations with content preservation and reference constraints, yet aggregate scores can readily obscure unmet local requirements. Effective evaluation must therefore identify local failures and translate them into priorities for subsequent model improvement. We introduce WeGenEditBench, comprising 2,740 evaluation instances and 148 task types across single-image, text-intensive, and multi-reference editing. Pre-generated checklists shared across models decompose each request into atomic requirements; item-level deductions and visual evidence are established first and then summarized into scores for edit execution, preservation, visual quality, and task-specific correctness. To support the experience-acquisition component of recursive self-improvement (RSI), we develop WeGenEvoStudio, a unified multi-agent harness for RSI-oriented learning that integrates model-conditioned failure diagnosis, retrieval-grounded data construction, supervised adaptation, and re-evaluation. Among 15 evaluated configurations, GPT-Image-2 leads single-image editing with an Overall score of 4.076, while Seedream-5.0-Pro leads text-intensive editing at 4.291. Evolution experiments across four generation and editing benchmarks demonstrate substantial targeted gains: on their report-selected Top-5 single-image targets, FLUX.2 [dev] improves Overall from 1.083 to 3.517, while Qwen-Image-Edit-2511 gains 13.2%. Together, our benchmark and harness provide a foundation for developing more reliable image models through interpretable evaluation and feedback-driven learning.

cs.CV↗

arXiv2026

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research.

cs.CL↗

arXiv2026

Competition and cancellation in a tilted Rice--Mele chain: exact Wannier--Stark offset and spectral readout

In a tilted Rice--Mele chain, the Wannier--Stark (WS) ladder becomes staggered, $E_n=n\Fo+(-1)^{n+1}A$. The offset $A$ reflects the competition between the staggered onsite energy $Δ$ and the dimerized hopping $\dt$, and its cancellation restores spectral equidistance. We determine $A$ through a systematic strong-field series in the WS basis and a nonperturbative two-band Floquet expression. An exact matrix element reduces the strong-field expansion to Bessel algebra; at the representative working point, truncation at seventh order locates the cancellation point with a theory-internal truncation error of $0.010$~Hz, against $27.3$~Hz at first order. The Floquet propagator gives the closed form $A=(\Fo/π)\arcsin(-i\,\mathrm{Tr}\,U/2)$, exact within the two-band model, implying the kinematic bound $|A|\le\Fo/2$ and identifying cancellation with maximum spectral uniformity. The same analytic structure yields a family of real zeros and complex exceptional points that set the convergence radius of the strong-field series without touching the real axis. On odd-length chains, the hidden-symmetry defect produces a pairing plateau of height $2|A|$ that persists numerically beyond first order in the modulations, allowing the offset to be read from the static spectrum without Floquet propagation or time evolution. In the bulk, cancellation appears as the merging of two sidebands into a single line at $\Fo$, a null measurement that requires no calibrated sideband amplitudes, although the tilt and line frequency still need calibration. These signatures provide complementary spectral tests of the staggered WS ladder and a calibration-aware route to precision force sensing.

quant-ph↗

arXiv2026

Silent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents

Large language model (LLM) services process massive volumes of user requests, resulting in substantial inference costs. To reduce both cost and latency, providers have introduced prompt caching. However, correctly integrating prompt caching is non-trivial due to heterogeneous provider-specific APIs and continuously evolving caching semantics. To understand prompt-caching mis-integration in downstream applications, we conduct the first empirical study of 120 prompt-caching-related pull requests from 10 popular open-source agent systems. Our findings show that prompt-caching mis-integrations arise in both request-side misconfiguration and read-side usage miscount. More importantly, most mis-integrations fail silently without causing observable runtime failures. Motivated by these findings, we design CACHELINT, which models a prompt-caching mis-integration as an invocation site together with the preconditions required for correct cache integration. CACHELINT locates caching invocation sites with CodeQL and discharges each precondition either against a dated provider capability oracle or with an LLM guard check. CACHELINT achieves 0.71 precision and 0.78 recall in identifying the 120 labeled mis-integrations across the 10 studied agent systems. Our evaluation further demonstrates the effectiveness of CACHELINT in real-world settings, identifying 32 mis-integrations across 571 agent projects with 0.86 precision. These findings have received 21 developer confirmations and led to 18 upstream fixes, including one in Anthropic's official SDK.

cs.SE↗

arXiv2026

ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents

Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entanglement, where heterogeneous information is mixed within coarse-grained memory units; and (2) Organizational Mismatch, where memory structures based primarily on semantic similarity may overlook other associations. To address these challenges, we propose ETAMem, a multi-view memory framework that decouples heterogeneous conversational information and aligns memory representations and organization with its distinct characteristics. Specifically, heterogeneous information parsing extracts atomic memory units and identifies affective information. View-specific memory structuring then organizes these units into three complementary hierarchical views: Event, Affect, and Time. ETAMem incrementally maintains memory structures with adaptively calibrated thresholds. For retrieval, entropy-based retrieval allocates query-specific budgets across views and performs hierarchical search within each view. Experiments on LoCoMo and LongMemEval-S demonstrate that ETAMem outperforms state-of-the-art baselines, achieving relative accuracy improvements of 12.46% and 7.96%, respectively, while maintaining competitive token efficiency. Further analyses demonstrate the complementary benefits of different memory views.

cs.CL↗

arXiv2026

Photoinduced Odd- and Mixed-Parity Magnetism in Collinear Antiferromagnets

Altermagnetism, characterized by compensated collinear magnetic moments and even-parity momentum-dependent spin splitting, has emerged as a distinct form of magnetic order. However, realizing odd- and mixed-parity magnetism in fully compensated collinear magnets remains challenging. Here, we demonstrate light-induced odd- and mixed-parity magnetism in conventional collinear antiferromagnets. Combining Floquet theory with first-principles calculations, we show that circularly polarized light (CPL) induces odd-parity $f$-wave spin splitting in monolayer CoS and CoSe, whereas elliptically polarized light (EPL) induces $p$-wave spin splitting. Uniaxial strain combined with CPL offers an alternative route to the $p$-wave state. Furthermore, combining an electric field with CPL or EPL generates mixed-parity spin splitting. Light-induced breaking of $\mathcal{PT}$ symmetry, together with spin-orbit coupling, gives rise to a finite anomalous Hall response. Our findings establish a versatile approach to engineering spin splitting and controlling electronic and magnetic properties in compensated antiferromagnets.

cond-mat.mtrl-sci↗

arXiv2026

DeltaTrace: Efficient Signed Attribution for Reasoning Language Models

We study how words in the context support or oppose a language model's response and present DeltaTrace, a novel attribution framework that explains the effect of input tokens on a fixed model response. DeltaTrace measures how the response's log-probability changes when the context tokens being explained are masked. To distribute this difference among source tokens, it constructs operator-specific local rules for finite changes and composes them backward through the computational graph using effective secant slopes. Each token is assigned a signed attribution as the inner product of its embedding displacement and the corresponding backward-propagated slope. Local conservation makes these contributions sum to the measured score difference and preserves their meaning when aggregated over sentences or passages. DeltaTrace supports both attention and linear-attention models, with auxiliary memory growing linearly with sequence length at fixed model dimensions and chunk size. On the evaluated attention model, DeltaTrace achieves the lowest deletion-faithfulness scores (RISE and MAS) on most retrieval and reasoning tasks and the highest needle-in-a-haystack Recall, exceeding FlashTrace by 5.67-24.33 percentage points. On the evaluated hybrid attention and linear-attention model, DeltaTrace lowers RISE on 9 tasks and MAS on 12 relative to FlashTrace.

cs.LG↗

arXiv2026

Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking

Multimodal Entity Linking (MEL) is a fundamental task in data management that maps ambiguous mentions with diverse modalities to the multimodal entities in a knowledge base. However, most existing MEL approaches primarily focus on optimizing instance-centric features and evidence, leaving broader forms of evidence and their intricate interdependencies insufficiently explored. Motivated by the observation that human expert decision-making process relies on multi-perspective judgment, in this work, we propose MSR-MEL, a Multi-perspective Evidence Synthesis and Reasoning framework with Large Language Models (LLMs) for unsupervised MEL. Specifically, we adopt a two-stage framework: (1) Offline Multi-Perspective Evidence Synthesis constructs a comprehensive set of evidence. This includes instance-centric evidence capturing the instance-centric multimodal information of mentions and entities, group-level evidence that aggregates neighborhood information, lexical evidence based on string overlap ratio, and statistical evidence based on simple summary statistics. A core contribution of our framework is the synthesis of group-level evidence, which effectively aggregates vital neighborhood information by graph. We first construct LLM-enhanced contextualized graphs. Subsequently, different modalities are jointly aligned through an asymmetric teacher-student graph neural network. (2) Online Multi-Perspective Evidence Reasoning leverages the power of LLM as a reasoning module to analyze the correlation and semantics of the multi-perspective evidence to induce an effective ranking strategy for accurate entity linking without supervision. Extensive experiments on widely used MEL benchmarks demonstrate that MSR-MEL consistently outperforms state-of-the-art unsupervised methods. The source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.

cs.CL↗

arXiv2026

Ensemble-based Deep Multilayer Community Search

Multilayer graphs, consisting of multiple interconnected layers, are widely used to model diverse relationships in the real world. A community is a cohesive subgraph that offers valuable insights for analyzing (multilayer) graphs. Recently, there has been an emerging trend focused on searching query-driven communities within the multilayer graphs. However, existing methods for multilayer community search are either 1) rule-based, which suffer from structure inflexibility; or 2) learning-based, which rely on labeled data or fail to capture layer-specific characteristics. To address these, we propose EnMCS, an Ensemble-based unsupervised (i.e., label-free) Multilayer Community Search framework. EnMCS contains two key components, i.e., HoloSearch which identifies potential communities in each layer while integrating both layer-shared and layer-specific information, and EMerge which is an Expectation-Maximization (EM)-based method that synthesizes the potential communities from each layer into a consensus community. Specifically, HoloSearch first employs a graph-diffusion-based model that integrates three label-free loss functions to learn layer-specific and layer-shared representations for each node. Communities in each layer are then identified based on nodes that exhibit high similarity in layer-shared representations while demonstrating low similarity in layer-specific representations w.r.t. the query nodes. To account for the varying layer-specific characteristics of each layer when merging communities, EMerge models the error rates of layers and true community as latent variables. It then employs the EM algorithm to simultaneously minimize the error rates of layers and predict the final consensus community through iterative maximum likelihood estimation. Experiments over 10 real-world datasets highlight the superiority of EnMCS in terms of both efficiency and effectiveness.

cs.SI↗

arXiv2026

Label-Centric Knowledge Retrieval for Zero-Shot Text Classification

Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit their use for large-scale data labeling. We study zero-shot text classification with semantically meaningful labels and task descriptions, without task-specific labeled examples or classifier feedback. We propose \textbf{SLKR} (Semantic Label Knowledge Retrieval), a label-centric retrieval-augmented generation framework that separates offline knowledge construction from lightweight online inference. Offline, a flagship LLM independently generates label definitions, retrieval keywords, and boundary rules for potentially confusable label pairs, forming a reusable label-knowledge store. Because this construction operates over the label space rather than the input corpus, its one-time flagship cost can be amortized across large-scale inference. Online, hybrid semantic and lexical retrieval first identifies the top-$K$ candidate labels and then selects up to $M$ input-relevant boundary rules connecting candidate-label pairs. A lightweight LLM performs the final classification in a single call using the retrieved definitions and rules. Across three public benchmarks and a real-world multilingual book-classification dataset, SLKR achieves the best results on all four datasets with Qwen3.5-4B and on three of four with Ministral-3-3B, while using compact input contexts and no task-specific labeled examples. Boundary ablations further show that retrieving a small set of input-relevant rules preserves performance close to using all boundaries with substantially less context, supporting efficient reuse of flagship-generated label knowledge for lightweight classification.

cs.AI↗

arXiv2026

Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching

Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagrees and the fused margin is small. The evaluation covers 561 cases from six benchmark families. JevNexus obtains dataset-macro MRR and Hits@1 of 0.930 and 0.909, compared with 0.926 and 0.903 for Magneto, while reducing mean latency from 123.452 to 15.929 seconds (7.750). Paired analysis finds no statistically significant difference in either MRR or Hits@1. The gate invokes listwise refinement for only 5.665% of source columns and avoids the degradation caused by unconditional refinement. Code and experimental artifacts are available at https://github.com/RazeenLI/JevNexus.

cs.DB↗

arXiv2026

Anomalous Hall enhancement in fully compensated non-collinear antiferromagnetic Cr-doped Mn3Sn

The non-collinear antiferromagnet (AFM), Mn3Sn, exhibits ultrafast spin dynamics and negligible stray fields, making it a promising candidate for fast and energy-efficient spintronic devices. However, its practical applications remain limited by the relatively small Hall response compared with ferromagnets. Here, we demonstrate through both first-principles calculations and experiments that Cr-doping is a promising strategy to enhance the anomalous Hall transport in Mn3Sn without breaking the antiferromagnetic order. Our first-principles calculations reveal an effective Cr-doping window that enhances the anomalous Hall conductivity while largely preserving the host coplanar inverse triangular AFM order. Berry curvature and Wannier Hamiltonian analyses further reveal that Cr substitution amplifies the pre-existing Berry curvature hotspots through coordinated changes in the energy alignment, local interband gap, and Mn-derived orbital weight of the relevant bands. Experimentally, we have found that Cr doping not only supports our computational predictions (enhancement of the anomalous Hall conductivity), but also suppresses the transition to helical or spin-glass phases at low temperatures. These findings demonstrate that Cr-doping is an effective strategy for stabilizing the AFM order while simultaneously improving the anomalous Hall transport properties over a wide temperature range in Mn3Sn.

cond-mat.mtrl-sci↗