arXiv subjects

Yi Wang

Publications and source records attributed to Yi Wang.

At least 163 records · Page 9Linked to original sources

arXiv2026

Operator Models via Compact Embedding

In this paper, we extend several function-theoretic and geometric constructions to the realm of multi-variable operator theory. A commuting tuple of bounded linear operators on a Hilbert space, equipped with a cyclic vector, is abbreviated as a cyclic commuting tuple. We encode the complete information of such a tuple into a single positive compact operator on the Fock space. Drawing parallels with spectral geometry, we investigate how the spectral data of this positive compact operator -- its eigenvalues and eigenfunction -- reflect fundamental properties of the operator tuple. Our main contributions are threefold. First, we establish a Weyl-type approximation formula for certain operator tuples, demonstrating that the asymptotic behavior of eigenvalues carries geometric information about the vanishing variety. Second, we construct two kernel functions derived from the eigenvalues and eigenfunctions: the first extends the Bergman kernel, while the second extends the Fourier-Laplace transformation. We prove that the Fourier-Laplace kernel defines a reproducing kernel Hilbert space (RKHS) on which the coordinate differential operators are unitarily equivalent to the adjoint tuple. Consequently, we show that the convergence points of the Bergman-type kernel characterize the joint eigenvalues of the adjoint tuple. Finally, we obtain a Paley-Wiener-Schwartz type theorem for cyclic commuting tuples, characterizing cyclic commuting tuples whose associated Agler's linear functional are distributions. For tuples consisting of matrices, we obtains a more explicit characterization.

math.FA↗

arXiv2026

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook

Temporal data, including time series and spatio-temporal data, are pervasive in real-world applications. Generated in massive volumes by physical and virtual sensors, they record dynamic system behaviors and enable a wide range of downstream tasks. Effectively analyzing such data is crucial to unlocking their rich information content. Recent advances in large language models and other foundation models have accelerated their use in time series and spatio-temporal data mining. These approaches not only improve pattern recognition and reasoning across diverse domains but also support progress toward artificial general intelligence that can understand and process temporal data. In this survey, we present a comprehensive, up-to-date review of large models tailored or adapted for time series and spatio-temporal data along four dimensions: data types, model categories, model scopes, and application areas/tasks. We organize existing work into two main groups: large models for time series analysis (LM4TS) and for spatio-temporal data mining (LM4STD), and further distinguish general-purpose from domain-specific models. We also curate related resources, including datasets, model implementations, and tools, organized by major application areas. Overall, this survey consolidates recent advances and highlights foundations, applications, resources, and open research opportunities in large model-centric temporal data analysis.

cs.LG↗

arXiv2026

A solution to Csikvári's conjecture and the largest matching root of $k$-graphs

In 2011, Csikvári [Electron. J. Combin. {\bf 18} (2011), $\#$P182] proved that among all graphs with a prescribed number of edges, the largest matching root is attained by a threshold graph, and conjectured that the extremal graph should be `as star-like as possible.' In this paper, we give a complete and affirmative answer to this problem and extend it to the setting of uniform hypergraphs. We prove that for every $k$-graph $\mathcal{H}$ with $m$ edges, its largest matching root satisfies $$λ(\mathcal{H})\le m^{1/k},$$ with equality if and only if $\mathcal{H}$ is intersecting. For $k=2$, after deleting all isolated vertices, the resulting graph must be the star $K_{1,m}$ or a triangle, thereby confirming Csikvári's conjecture. Moreover, if the matching number $ν(\mathcal{H})\ge 2$, then \[ λ(\mathcal{H})\le \left(\frac{m+\sqrt{m^2-4(ν(\mathcal{H})-1)}}{2}\right)^{1/k}, \] with equality if and only if $ν(\mathcal{H})=2$ and $\mathcal{H}$ has exactly one $2$-matching.

math.CO↗

arXiv2026

Retarded Correlators of Charge Transport in a Magnetic Field

We study charge transport in a magnetized relativistic plasma using kinetic theory within the relaxation-time approximation. By exactly solving the linearized Boltzmann equation in a uniform magnetic field, we obtain an analytic solution for the distribution function in terms of Bessel functions. Using this solution, we compute the full set of retarded current-current correlators and verify the Ward identities. In the hydrodynamic limit, we extract the charge diffusion modes, demonstrating that the transverse diffusion coefficient is strongly suppressed by the magnetic field, scaling as $1/B_0^2$ in the strong-field regime, while the longitudinal diffusion remains unaffected. Furthermore, we analyze the non-hydrodynamic branch cuts in the complex frequency plane, determining their kinematic thresholds and identifying the underlying wave-particle interactions as longitudinal Landau damping and transverse cyclotron damping.

hep-ph↗

arXiv2026

ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation

On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher. In multimodal reasoning, a common extension is to use a privileged teacher that observes training-time-only signals such as reference answers or rationales. However, such answer-side privilege creates a train-test mismatch: the teacher's supervision may depend on signals unavailable to the student, encouraging shortcut imitation rather than visually grounded reasoning. We propose ViCuR, a visually grounded privileged-teacher distillation framework that replaces answer-side privilege with visual cues (query-related evidence in the input). Because these cues are derived from the same visual input available at inference, their evidence is recoverable by the student. To support this, ViCuR introduces a lightweight cue recovery module that uses dedicated sink-token cross-attention during prefill to aggregate task-relevant visual evidence into an internal representation, without changing the inference interface or requiring auxiliary cue-generation losses. Across seven benchmarks with Qwen3-VL-2B and 8B students, ViCuR consistently improves over answer-based on-policy self-distillation by +1.19 and +1.24 on overall average performance. It also extends naturally to stronger-teacher OPD, surpassing OPD baselines by +0.64 and +1.08, with consistent out-of-domain gains at the 8B scale. These results show that, in multimodal on-policy distillation, the design of teacher privilege is as important as teacher strength.

cs.CV↗

arXiv2026

Tunable Mid-Infrared Chiral Selective Absorber Based on Asymmetric V-Shaped Metasurfaces Driven by Chiral quasi-Bound State in the Continum

Efficient discrimination of circularly polarized light (CPL) is of great significance in photonics. In this study, we propose a nanophotonic device based on asymmetric V-shaped metasurfaces that exhibits strong discrimination between left- and right-circularly polarized (LCP and RCP) light at the resonant wavelengths of the absorption spectra. The chiral-selective response originates from a quasi-bound state in the continuum (qBIC) mode enabled by controlled symmetry breaking in the V-shaped structure, which exhibits high absorption under LCP illumination while the resonance is strongly suppressed under RCP incidence, leading to a large absorption contrast between the two circular polarizations. This significant absorption difference enables highly efficient chiral discrimination. Furthermore, the resonant wavelength can be broadly tuned from 5200 to 6200 nm by scaling the structural dimensions without compromising the high absorption contrast between LCP and RCP. This work not only enables high-performance chiral detection and separation, but also offers valuable guidance for reconfigurable chiral nanodevices, with promising applications in areas such as enantiomer sensing, chiral imaging, and CPL spectroscopy.

physics.optics↗

arXiv2026

On Cosmological Correlators with Boundary Contributions

Cosmological correlators receive contributions from both field interactions in the bulk of quasi-de Sitter (dS) spacetime and boundary terms at the end of inflation. While most of the research efforts focus on the former, boundary contributions are normally believed to be negligible or related to field redefinitions that are associated with redundancies of the bulk Lagrangian. In this paper, we revisit this topic in the light of the cosmological bootstrap. We first establish the correspondence between boundary terms and field redefinitions for cosmological correlators. This result provides a set of criteria for determining when boundary terms lead to non-vanishing contributions to cosmological observables. Next, we apply this general understanding to concrete examples of correlators from massive-exchange diagrams, in both dS-invariant and boost-breaking scenarios. For theories with dS isometries, both IBP and field redefinitions are used to relate derivative and non-derivative exchange diagrams, from which the leading boundary contributions and IR-divergent pieces are extracted; we also derive recursion relations among higher-derivative exchange correlators. For theories with broken dS boosts, we use IBP and EoM to reduce exchange diagrams to a basis of independent templates, and then present a classification of the boundary contributions in the general effective field theory framework. These results pave the way for a more systematic investigation on the boundary physics of the inflationary spacetime.

gr-qc↗

arXiv2026

Almost sure convergence of differentially positive systems on a globally orderable manifold

Differentially positive systems are nonlinear systems whose linearization along trajectories preserves a cone field on a smooth Riemannian manifold. The structures of cone field come from general relativity and Lie theory. We prove that on a globally orderable manifold, the set of convergent points has full Riemann-Lebesgue measure, thus establishing almost sure convergence. This result thereby resolves a measure-theoretic form of the conjecture posed by Forni and Sepulchre in 2016 for such manifolds.

math.DS↗

arXiv2026

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction

Neural algorithmic reasoning has emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state represents the intermediate outcome after an execution step. The training objective is to generate state sequences that replicate the underlying algorithmic process. A common framework for this task adopts an encoder-processor-decoder architecture, where the encoder learns representations of states, the processor simulates algorithmic steps, and the decoder reconstructs output states. While prior work has focused on improving the processor, the role of the encoder in representation learning has received little attention. Most methods rely on simple MLP encoders, raising the question of whether such representations are sufficiently informative for supporting algorithmic reasoning. This paper investigates how to improve encoder representations for neural algorithmic reasoning. We propose a reconstruction module that aims to recover the input state from its encoded representation. This auxiliary reconstruction task encourages the encoder to retain critical information about the input. We demonstrate that incorporating this task during training improves the performance of existing neural architectures on standard benchmarks. Furthermore, we observe that current encoders often underutilize the correlations among features within a state. To address this, we draw inspiration from self-supervised learning and design an enhanced variant of the auxiliary task that encourages the encoder to capture intra-state feature dependencies. Experimental results show that our method enables the encoder to learn richer representations, thereby enhancing the performance of existing processors on algorithmic reasoning tasks.

cs.LG↗

arXiv2026

GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning

Existing agentic reinforcement learning methods for GUI grounding have limitations at two levels. At the data level, current approaches typically treat all training samples equally, although their training value to the baseline model varies with difficulty. Overlooking this can greatly reduce training efficiency or even cause collapse. At the strategy level, existing frameworks struggle to balance the trade-off between cropping larger regions for sufficient context and smaller ones for reduced redundancy, a tension inherent to tool-augmented grounding agents. In addition, overly complex decision-making is difficult for small-parameter models and significantly increases inference time. To address these issues, at the data level, we propose GUI-D, a data mining and difficulty scoring pipeline that identifies the training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights. At the strategy level, we propose GUI-C$^2$, which employs an area-gated coarse-to-fine refinement mechanism that progressively narrows the visual field via model-internal uncertainty signals, adaptively reserving context for large targets while amplifying precision for small ones, reinforced by improvement-aware stage rewards that ensure each refinement genuinely advances grounding. Meanwhile, we simplify the decision-making process to greatly reduce additional inference time. Finally, extensive experiments show that our method achieves state-of-the-art performance. The code and data will be publicly available.

cs.CV↗

arXiv2026

Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

LLMs have shown remarkable proficiency in general language understanding and reasoning. However, they consistently underperform in spatial reasoning that severely limits their application, particularly in embodied intelligence. Inspired by the success of hierarchical reinforcement learning, this paper introduces a novel method for hierarchical task decomposition in LLM spatial reasoning. Our approach guides LLMs to decompose complex tasks into manageable sub-tasks by identifying key intermediate states and generating simplified sub-environments. However, we identify that LLMs often fail to derive optimal intermediate states due to their insufficient spatial prior, leading to sub-optimal task decomposition. To address this limitation and enhance its planning capability, we propose the MCTS-Guided Group Relative Policy Optimization (M-GRPO), where we reformulate the UCT formula by incorporating the LLM's prior predictive probabilities alongside its epistemic uncertainty. Furthermore, we implement a more fine-grained advantage function, enabling the model to learn optimal path planning. Experimental results demonstrate that our method substantially improves LLM performance on spatial tasks, including navigation, planning, and strategic games, achieving state-of-the-art results. This work paves the way for LLMs in real-world applications.

cs.AI↗

arXiv2026

FreeRet: MLLMs as Training-Free Retrievers

Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into contrastive encoders for retrieval. This work asks: Can off-the-shelf MLLMs serve as powerful retrievers without additional training? We present FreeRet, a plug-and-play framework that turns any MLLM into a two-stage retriever. FreeRet first derives semantically grounded embeddings directly from the model for fast candidate search, and then exploits its reasoning ability for precise reranking. The framework contributes three advances: bypassing lexical alignment layers to obtain semantically faithful embeddings, conditioning representation generation with explicit priors, and mitigating framing effect in reranking via neutral choice framing. On the MMEB and MMEB-V2 benchmarks spanning 46 datasets, FreeRet substantially outperforms models trained on millions of pairs. Beyond benchmarks, FreeRet is model-agnostic and scales seamlessly across MLLM families and sizes, preserves their generative abilities, supports arbitrary modality combinations, and unifies retrieval, reranking, and generation into end-to-end RAG within a single model. Our findings demonstrate that pretrained MLLMs, when carefully harnessed, can serve as strong retrieval engines without training, closing a critical gap in their role as generalists.

cs.CV↗

arXiv2026

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse yet critical evidence amid extensive redundancy. We introduce Video-o3, a novel framework that supports iterative discovery of salient visual clues, fine-grained inspection of key segments, and adaptive termination once sufficient evidence is acquired. Technically, we address two core challenges in interleaved tool invocation. First, to mitigate attention dispersion induced by the heterogeneity of reasoning and tool-calling, we propose Task-Decoupled Attention Masking, which isolates per-step concentration while preserving shared global context. Second, to control context length growth in multi-turn interactions, we introduce a Verifiable Trajectory-Guided Reward that balances exploration coverage with reasoning efficiency. To support training at scale, we further develop a data synthesis pipeline and construct Seeker-173K, comprising 173K high-quality tool-interaction trajectories for effective supervised and reinforcement learning. Extensive experiments show that Video-o3 substantially outperforms state-of-the-art methods, achieving 72.1% accuracy on MLVU and 46.5% on Video-Holmes. These results demonstrate Video-o3's strong multi-hop evidence-seeking and reasoning capabilities, and validate the effectiveness of native tool invocation in long-video scenarios.

cs.CV↗

arXiv2026

GenTS: A Comprehensive Benchmark Library for Generative Time Series Models

Generative models have demonstrated remarkable potential in time series analysis tasks, like synthesis, forecasting, imputation, etc. However, offering limited coverage for generative models, existing time series libraries are mainly engineered for discriminative models, with standardized workflows for specific tasks, such as optimizing Mean Squared Errors for time series forecasting. This rigid structure is fundamentally incompatible with the distinct and often complex paradigms of generative models (e.g., adversarial training, diffusion processes), which learn the underlying data distribution rather than a direct input-output mapping. To this end, we proposed GenTS, a comprehensive and extensible benchmark library designed for systematic assessment on generative time series models. GenTS features a unified data preprocessing pipeline, a collection of versatile models, and panoramic evaluation metrics. Its modular design also enables the researchers to flexibly customize beyond our built-in datasets and models. Based on GenTS, we conducted benchmarking experiments under diverse tasks, accordingly offering suggestions for model selection and identifying potential directions for future research. Our codes are open-source at https://github.com/WillWang1113/GenTS. The official tutorials and document are available at https://willwang1113.github.io/GenTS/.

cs.LG↗

arXiv2026

Structure-BiEval: A Self-Supervised, Dual-Track Framework for Decoupling Structure and Content in LLM Evaluation for Web Information Systems

As Large Language Models (LLMs) evolve into the core of Web-based autonomous agents and complex Web Information Systems, their ability to faithfully translate natural language into rigorous structured formats has become paramount, as this capability is critical for Web API invocation and data exchange. However, evaluating this structural fidelity in Web-native payloads remains a challenge: traditional text metrics fail to capture topological consistency in semi-structured Web data, while manual evaluation is prohibitively costly. To address this, we propose Structure-BiEval, a novel self-supervised framework for quantitative, annotation-free assessment tailored for Web data engineering. By leveraging deterministic Intermediate Representations, our framework effectively decouples structure from content, utilizing Content Semantic Accuracy and Normalized Tree Edit Distance as precise metrics. We empirically benchmark 15 state-of-the-art LLMs across dual Web structural topologies, namely Hierarchical Data (Web backend payloads) and Tabular Data (Web frontend presentation). The results reveal substantial variability in structural performance, including cases where mid-sized models unexpectedly outperform larger counterparts in Web data formatting. Furthermore, our findings show that deep recursive nesting poses a consistent challenge for Web agents across varying parameter scales.

cs.CL↗

arXiv2026

Privacy-Preserving Federated Radio Map Learning for Wireless Digital Twins via Adaptive Noise Allocation

Radio maps provide a foundational data layer for wireless digital twins, and federated learning offers a natural framework for their distributed construction without centralizing raw radio environment data. However, the exchanged client model updates may still leak transmitter-location information, even when the underlying measurement data are never shared. Existing noise-based privacy defenses inject perturbation either uniformly across all uploaded coordinates or according to a fixed static rule, thereby ignoring the architecture-specific structure of this leakage. This paper proposes a budget-constrained adaptive noise allocation mechanism that redistributes a fixed perturbation budget across transmitter-sensitive upload groups identified from the two-stage RadioUNet architecture. The proposed method uses low-dimensional upload statistics to dynamically adjust group-wise noise scales and is integrated locally before client upload transmission. We evaluate the framework on a federated radio map learning task under a unified noise multiplier, comparing it against uniform and structure-aware baselines using reconstruction mean squared error and transmitter localization error as metrics. Results show that adaptive allocation achieves the strongest privacy protection while maintaining the best reconstruction quality among all noise-based defenses under a matched perturbation budget.

eess.SP↗

arXiv2026

EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding

Understanding human--environment interactions from egocentric vision is essential for assistive robotics and embodied intelligent agents, yet existing multimodal large language models (MLLMs) still struggle with accurate interaction reasoning and fine-grained pixel grounding. To this end, this paper introduces EARL, an Egocentric Analysis-guided Reinforcement Learning framework that explicitly transfers coarse interaction semantics to query-oriented answering and grounding. Specifically, EARL adopts a two-stage parsing framework including coarse-grained interpretation and fine-grained response. The first stage holistically interprets egocentric interactions and generates a structured textual description. The second stage produces the textual answer and pixel-level mask in response to the user query. To bridge the two stages, we extract a global interaction descriptor as a semantic prior, which is integrated via a novel Analysis-guided Feature Synthesizer (AFS) for query-oriented reasoning. To optimize heterogeneous outputs, including textual answers, bounding boxes, and grounding masks, we design a multi-faceted reward function and train the response stage with GRPO. Experiments on Ego-IRGBench show that EARL achieves 65.48% cIoU for pixel grounding, outperforming previous RL-based methods by 8.37%, while OOD grounding results on EgoHOS indicate strong transferability to unseen egocentric grounding scenarios.

cs.CV↗

arXiv2026

EVA: Editing for Versatile Alignment against Jailbreaks

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent defenses typically rely on safety fine-tuning or external filters to reduce the model's likelihood of producing harmful content. While effective to some extent, these methods often incur significant computational overheads and suffer from the safety utility trade-off, degrading the model's performance on benign tasks. To address these challenges, we propose EVA (Editing for Versatile Alignment against Jailbreaks), a novel framework that pioneers the application of direct model editing for safety alignment. EVA reframes safety alignment as a precise knowledge correction task. Instead of retraining massive parameters, EVA identifies and surgically edits specific neurons responsible for the model's susceptibility to harmful instructions, while leaving the vast majority of the model unchanged. By localizing the updates, EVA effectively neutralizes harmful behaviors without compromising the model's general reasoning capabilities. Extensive experiments demonstrate that EVA outperforms baselines in mitigating jailbreaks across both LLMs and VLMs, offering a precise and efficient solution for post-deployment safety alignment.

cs.CR↗