arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 127 records · Page 7Linked to original sources

arXiv2026

Constructing a gravitational wave analysis pipeline for extremely large mass ratio inspirals

Extremely large mass-ratio inspirals (XMRIs), consisting of a brown dwarf orbiting a supermassive black hole, emit long-lived and nearly monochromatic gravitational waves in the millihertz band and constitute a promising probe of strong-field gravity and black-hole properties. However, dedicated data-analysis pipelines for XMRI signals have not yet been established. In this work, we develop, for the first time, a hierarchical semi-coherent search pipeline for XMRIs tailored to space-based gravitational-wave detectors, with a particular focus on the TianQin mission. The pipeline combines a semi-coherent multi-harmonic $\mathcal{F}$-statistic with particle swarm optimization, and incorporates a novel eccentricity estimation method based on the relative power distribution among harmonics. We validate the performance of the pipeline using simulated TianQin data for a Galactic Center XMRI composed of a brown dwarf and Sgr A*. For a three-month observation, the pipeline successfully recovers the signal and achieves high-precision parameter estimation, including fractional uncertainties of $2.0\times10^{-6}$ in the orbital frequency, $2.9\times10^{-4}$ in the eccentricity, $2.5\times10^{-5}$ in the black-hole mass, and $5.6\times10^{-4}$ in the black-hole spin. Our framework establishes a practical foundation for future XMRI searches with space-based detectors and highlights the potential of XMRIs as precision probes of stellar dynamics and strong-field gravity in the vicinity of supermassive black holes.

astro-ph.HE↗

arXiv2026

MoE-Based Learned Inertial Odometry for Bicycle Localization

GNSS suffers from multipath errors in urban canyons, making reliable bicycle localization difficult. Hand-crafted inertial alternatives, such as cycling dead reckoning and nonholonomic constraints, fail to generalize across riders, postures, and road surfaces. This work implements learned inertial odometry for bicycle localization: a neural velocity predictor, trained on multirider, multi-bicycle, and multi-surface IMU data, is tightly coupled with an extended Kalman filter for three-dimensional pose estimation, replacing hand-crafted cycling models with a data-driven representation. To reduce computational overhead, the predictor is realized as a sparsely-gated Mixture of Experts (MoE) network with top-K routing, trained under an alternating parameter-freezing scheme with a per-expert capacity constraint to encourage diverse and balanced specialization.The proposed model attains 0.333 m/s inference error, 9.49 m ATE, and 2.58 m RTE at only 28.76 M FLOPs. This corresponds to approximately 7 times and 9 times fewer FLOPs than the ResMLP and ResNet backbones used in LLIO and TLIO, while maintaining comparable or superior accuracy. The proposed MoE variants further rank first on both ATE and RTE across all evaluation splits, demonstrating strong generalization.

cs.RO↗

arXiv2026

DINS-IO: Learned Inertial Odometry via Differentiable INS Consistency

The training of learned inertial odometry depends on dense, high-precision position ground truth from motion capture, visual-inertial odometry or SLAM, which is costly and hard to acquire at scale. We propose DINS-IO, which learns inertial odometry directly from raw IMU streams without position labels. Our key insight is that the strapdown INS velocity recursion is a strong, fully differentiable consistency prior: the predicted velocity, rotated into the navigation frame, must agree with the integrated specific force up to an unknown initial velocity and a constant accelerometer bias. We cast this constraint as a sliding-window least-squares problem with a globally shared bias, solve it in closed form, and use the solver residual as a self-supervised loss whose gradient flows back to the network through the analytic solution. To supply this per-sample constraint, we design a high-frequency network that emits dense body-frame velocity at the IMU rate. Since the self-supervised network learns consistent motion but its velocity is not yet metrically calibrated, we calibrate it to true metric velocity from a few labeled trajectories by directly supervising the predicted body-frame velocity and adapting only low-rank (LoRA) patches. On standard benchmarks, DINS-IO pretrained self-supervised and fine-tuned with a small fraction of labels matches or surpasses fully supervised baselines.

cs.RO↗

arXiv2026

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead Sparse Attention (LSA)}, a novel inference paradigm powered by a Neural Memory Indexer built upon the DeepSeek-V4 architecture. Rather than passively attending to all historical tokens, LSA proactively predicts future context demands and preserves only the query-critical KV chunks in the GPU memory. Crucially, we instantiate this architecture via a \textbf{backbone-free decoupled training} strategy. By formulating the indexer as a standard dual-encoder architecture, we train it independently using standard retrieval training frameworks without ever loading the massive backbone model into GPU memory. We demonstrate that this ``less is more'' paradigm significantly maximizes serving efficiency while acting as an effective attention denoiser in tasks that rely on long-term global memory. Across primary long-context evaluation suites (e.g., LongBench-v2, LongMemEval, and RULER), \texttt{FM-DS-V4} compresses the average physical KV cache footprint down to merely 13.5\% of the full-context baseline, while consistently preserving or slightly elevating downstream accuracy (+0.6\% absolute margin on average). At 1M context, per-decode-token compute drops to 0.30$\times$ of the baseline and GPU KV cache shrinks by 90\% (3.73$\to$0.37 GB), translating into \textbf{2.8$\times$ aggregate throughput and 2.7$\times$ concurrency gains} in PD-disaggregated serving on 8$\times$H20 GPUs.

cs.LG↗

arXiv2026

Frequency-Corrupt Based Graph Self-Supervised Learning

Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and other web applications. However, existing methods often underuse high-frequency signals and may overfit to specific local patterns, which limits representation quality and generalization. We propose Frequency-Corrupt Based Graph Self-Supervised Learning (FC-GSSL), a method that builds corrupted graphs biased toward high-frequency information by corrupting nodes and edges according to their low-frequency contributions. These corrupted graphs are used as inputs to an autoencoder, while low-frequency and general features are reconstructed as supervision targets, forcing the model to fuse information from multiple frequency bands. We further design multiple sampling strategies and generate diverse corrupted graphs from the intersections and unions of the sampling results. By aligning node representations from these views, the model can discover useful frequency combinations, reduce reliance on specific high-frequency components, and improve robustness. Experiments on 14 datasets across node classification, graph prediction, and transfer learning show that FC-GSSL consistently improves performance and generalization.

cs.LG↗

arXiv2026

Solutions to Two Problems of Sárközy and Sós on Additive Representation Functions

For a set $A\subseteq\mathbb{N}_0$, let $r_1(A,n)$ denote the number of solutions of the equation $a+a^{\prime}=n$ with $a,a^{\prime}\in A$, and let $r_2(A,n)$ denote the number of such solutions subject to $a\le a^{\prime}$. These functions are called additive representation functions (as first considered by Erdős, Sárközy and Sós). In this paper, we resolve two problems posed by Sárközy and Sós in 1997. First, if $A$ is infinite and $r_2(A,2m+1)\ge r_2(A,2m)$ for every sufficiently large $m$, then the complement of $A$ is finite. This gives a negative answer to Problem 3.1 in~\cite{SarkozySos1997}. Secondly, there exist an arithmetic function $f$ satisfying $f(n) \to \infty$, $f(n+1) \ge f(n)$ for $n > n_0$, and $f(n) = o\left(\frac{n}{(\log n)^2}\right)$, and a set $A$ such that $ |r_1(A,n) - f(n)| = o((f(n))^{1/2}) $ holds on a sequence of integers $n$ whose density is $1$. This gives a positive answer to Problem 3.3 in~\cite{SarkozySos1997}.

math.NT↗

arXiv2026

Perfect matching in 4-partite 4-uniform hypergraphs

A balanced $k$-partite $k$-graph is a $k$-uniform hypergraph such that every edge intersects each partition class in exactly one vertex, where each partition class has size $n$. Lo and Markström (2014) determined the minimum vertex-degree threshold for perfect matchings in balanced $3$-partite $3$-graphs. In this paper, we determine the minimum vertex-degree threshold for balanced $4$-partite $4$-graphs. The proof relies on a reduction framework for $k$-partite $k$-graphs, through which the existence of a perfect fractional matching is converted into a finite-dimensional optimization problem.

math.CO↗

arXiv2026

GlobalForge: Towards Robust AI-Generated Image Detection

AI-generated image (AIGI) detectors achieve strong accuracy on clean benchmarks, but their performance drops sharply after images are propagated through real-world channels. We trace this fragility to what these detectors actually learn: they overfit to local artifacts left by generators in small spatial neighborhoods, which are easily destroyed by common propagation degradations such as JPEG compression and blur. Instead, we shift the discriminative cue from fragile local artifacts to more robust global structure. Building on this, we propose GlobalForge, a framework with two complementary modules. The Local Information Bottleneck (LIB) suppresses local components to block shortcut learning, while the Global Structural Reasoning (GSR) module forces every token to gather evidence from distant regions. Both modules are trained jointly under a contrastive structural loss based on degradation that keeps the resulting features stable under degradation. To support fine-grained robustness evaluation, we further introduce RealDeg-Bench, covering 7 common degradation operators and multi-step compound chains. GlobalForge improves average BAcc on 8 in-the-wild benchmark groups by $\mathbf{5.89\%}$ over the previous state-of-the-art, and is clearly ahead of representative baselines on RealDeg-Bench under both single and compound degradations. Code is available at https://anonymous.4open.science/r/GlobalForge-BE0F/.

cs.CV↗

arXiv2026

Gravitational Wave Astronomy With TianQin

The opening of the gravitational wave window has significantly enhanced our capacity to explore the universe's most extreme and dynamic sector. In the mHz frequency range, a diverse range of compact objects, from the most massive black holes at the farthest reaches of the Universe to the lightest white dwarfs in our cosmic backyard, generate a complex and dynamic symphony of gravitational wave signals. Once recorded by gravitational wave detectors, these unique fingerprints have the potential to decipher the birth and growth of cosmic structures over a wide range of scales, from stellar binaries and stellar clusters to galaxies and large-scale structures. The TianQin space-borne gravitational wave mission is scheduled for launch in the 2030s, with an operational lifespan of five years. It will facilitate pivotal insights into the history of our universe. This document presents a concise overview of the detectable sources of TianQin, outlining their characteristics, the challenges they present, and the expected impact of the TianQin observatory on our understanding of them.

astro-ph.GA↗

arXiv2026

Deep Simulation-Based Inference for Inhomogeneous Bivariate Log-Gaussian Cox Processes

We propose a computationally efficient simulation-based estimation method with a two-step procedure for inhomogeneous bivariate Log-Gaussian Cox Processes. It combines classical Poisson estimation for the first-order parameters with simulation-based inference using neural networks for the latent field parameters. By separating the estimations, it reduces the complexity of high dimensional parameter estimation and the need for the simulation-based method to specify broad parameter ranges in the presence of covariates. In addition, we introduce two dimensional image inputs that enable the model to learn spatial information directly. Simulation results demonstrate that the proposed approach provides accurate estimates of the latent field parameters. We further illustrate the method's practical applicability using the gorilla dataset.

stat.ME↗

arXiv2026

Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing

The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and tool-using computational actors. As these agents move from isolated cognitive prototypes into complex distributed workflows, they confront challenges that the Service-Oriented Computing community has studied for more than two decades: composition, interoperability, quality of service, lifecycle management, governance, security, and trust. Yet much of today's agentic AI ecosystem is developing these foundations ad hoc, without the engineering rigour required for dependable enterprise and societal deployment. This paper introduces Agentic Service-Oriented Computing (ASOC) as a new research and practice area concerned with engineering agents as services, orchestrating services through autonomous and semi-autonomous agents, and governing ecosystems of agents and services under constraints of trust, cybersecurity, compliance, performance, and accountability. We articulate six foundational principles of ASOC (harness-ability, composability, lifecycle engineering, trustworthiness by design, goal-driven orchestration, and observability/accountability) and organise a five-dimensional research agenda spanning: (i) agentic services foundations and lifecycle engineering; (ii) composition, orchestration, and interoperability; (iii) governance, observability, and accountability; (iv) security, trust, and risk management; and (v) evaluation, certification, and Agentic QoS. We argue that the Services Computing community is especially well positioned to provide the conceptual and engineering spine for this emerging field, transforming agentic AI from fragmented demonstrations into dependable, service-based systems worthy of human and organisational trust.

cs.AI↗

arXiv2026

A Single-Exponential Erdős--Hajnal Bound for Graphs of Bounded VC-Dimension

A homogeneous set in a graph is a clique or a stable set. The Erdős--Hajnal conjecture states that, for every graph $H$, there exists $c>0$ such that every $H$-free graph on $n$ vertices has a homogeneous set of size at least $n^c$. Nguyen, Scott and Seymour proved that for every $d>0$, graphs of VC-dimension at most $d$ have the Erdős--Hajnal property, confirming a conjecture of Fox, Pach and Suk. In particular, they showed that every such $n$-vertex graph contains a homogeneous set of size at least $n^{η_d}$ for some $η_d\ge 2^{-2^{O(d)}}$. In this paper, we give a sharper quantitative bound on the homogeneous sets in graphs of VC-dimension at most $d$, showing that one may take $ η_d\ge (Cd)^{-d}, $ where $C$ is an absolute constant. Equivalently, every graph $G$ of VC-dimension at most $d$ satisfies \[ \max\{ω(G),α(G)\}\ge |G|^{(Cd)^{-d}}. \] Our proof refines the iterative sparsification method of Nguyen, Scott and Seymour. The main enhancement is to apply the VC-dimension assumption directly, which gives a more efficient induction and thus improves the dependence on $d$. We also derive quantitative consequences for polynomial Rödl subgraphs, hypergraph Ramsey bounds under bounded VC-dimension, induced-free and viral formulations, tournaments, NIP and semi-algebraic graphs, Boolean combinations of relations of bounded VC-dimension, graphs whose adjacency matrices have bounded rank, graphs of bounded sign-rank, and graphs defined by dot-product threshold representations.

math.CO↗

arXiv2026

OpenLongTail: Generative Scaling of Long-Tail Driving Data

Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, such long-tail events remain underutilized when collected from heterogeneous sources. Specifically, diverse but valuable in-the-wild long-tail videos lack the full view coverage required for training policy models, often missing multi-view poses or originating solely from monocular dash cameras. This modality gap prevents these ubiquitous observations from being converted into scalable training data for long-tail generalization. We introduce OpenLongTail, an open-source generative data engine for scaling autonomous driving policies under long-tail events. To transform heterogeneous data sources into view-aligned and temporally coherent multi-view assets that are useful for policy learning, we develop a pose-informed extrapolative view synthesis pipeline that generates the missing views. We further enhance cross-view consistency and the temporal alignment for the newly generated views by injecting Plücker ray geometry into the scalable generation engine. By synthesizing heterogeneous long-tail data, we observe a significant improvement in closed-loop driving robustness in handling long-tail events. By measuring the extrapolative view synthesis and pose metrics, we validate the effectiveness of OpenLongTail in visual fidelity, cross-view consistency, and ego-trajectory recovery.

cs.CV↗

arXiv2026

Experimental demonstration of entanglement sudden death induced by natural dissipation

Any quantum system inevitably interacts with its natural environment, which can be modeled as a Markovian reservoir consisting of a continuum of electromagnetic field modes. The quantum coherence of qubits in a zero-temperature natural reservoir decays asymptotically, whereas the quantum entanglement of two qubits coupled to such reservoirs may disappear in a finite time. This phenomenon, referred to as entanglement sudden death (ESD), has been simulated with artificially engineered dissipative channels, but ESD induced by natural dissipative channels has not been confirmed. We here present the first demonstration of natural-dissipation-induced ESD for two photonic qubits, each stored in a leaky resonator of a superconducting circuit. The disentanglement dynamics of the two photonic qubits is monitored with two ancilla superconducting qubits, which can be controllably coupled to the corresponding leaky resonators. The techniques developed in our experiment pave the way for experimental exploration of entanglement dynamics in natural environments.

quant-ph↗

arXiv2026

A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

Generative world models hold immense promise as scalable simulators for autonomous systems, particularly for synthesizing rare but safety-critical multi-agent interactions, such as vehicle collisions. However, current evaluation paradigms index heavily on visual fidelity and semantic alignment, leaving a critical blind spot: they cannot reliably quantify whether generated dynamics actually obey the fundamental physical laws required for reliable simulation. Assessing this physical plausibility is inherently difficult due to a lack of physical metrics and the challenge of extracting metric-scale kinematics from uncalibrated video rollouts. To bridge this gap, we introduce CrashTwin, a physics-grounded evaluation framework designed to stress-test the physical trustworthiness of world models. CrashTwin couples a diverse dataset of multi-agent collision scenarios, comprising 25K controllable synthetic and 12K in-the-wild real-world collision sequences with a novel calibration-free reconstruction pipeline, enabling the recovery of 3D physical attributes directly from world model rollouts. We propose a diagnostic suite that systematically evaluates three dimensions: spatio-temporal consistency, momentum and kinetic energy conservation, and world-dynamics integrity. Extensive benchmarking of state-of-the-art models reveals a crucial insight: high perceptual quality frequently masks severe physical violations during complex interactions. By quantitatively exposing these failure modes, CrashTwin provides a vital diagnostic tool for developing physically grounded world models capable of reliable real-world simulation.

cs.CV↗

arXiv2026

Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns

Information Operations on social media networks have been identified as a significant threat to democracy and modern society, but they are challenging and expensive to detect by humans. Existing supervised IO detection methods fail to capture the dynamic nature of evolving IO user behavior, while existing unsupervised approaches rely on oversimplified assumptions of coordination among IO users that may not exist in practice. To overcome the limitations of existing methods, we formulate IO user detection as an anomaly detection problem and propose a novel unsupervised IO user detection approach called Temporal-bEhavior-laNguage Signals for information Operation Recognition (TENSOR), which leverages multimodal data, including temporal online user behavior, such as message posting activities, and the textual content of the messages. The motivation is that IO users are typically a very small fraction of all online users and have unique temporal behavioral and language patterns. Specifically, we train a Temporal Point Process (TPP) to capture abnormal temporal behavioral patterns of IO users because they are known to behave in a coordinated manner for IO campaigns. We further introduce a novel evidence function that converts LLM responses, which are generated from user post timelines, into quantitative scores to adjust the TPP outputs for better IO user detection. Experimental results show that TENSOR outperforms the baselines on five real-world IO datasets. Code is available at https://github.com/xiuzhenzhang/TENSOR.

cs.LG↗

arXiv2026

KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learning

Non-invasive prediction of Gleason Grade Group (GGG) in prostate cancer using multiparametric MRI (mpMRI) is clinically vital for reducing unnecessary biopsies. Existing GGG prediction methods face two major limitations. First, they often overlook non-image information critical for GGG prediction, including age, prostate-specific antigen (PSA), and expert priors embedded in radiology reports. Second, they tend to oversimplify GGG as flat categorical labels, failing to account for its intrinsic hierarchy of primary and secondary Gleason patterns. To this end, we propose a novel Knowledge-Driven Ordinal-Aware Learning (KOAL) framework with three synergistic modules. Specifically, the Clinical-Context Modulation (CCM) module uses clinical variables (e.g., age and PSA) to dynamically modulate discriminative image representations. The Knowledge-Guided Prototype Alignment (KGPA) module leverages an LLM to extract group-specific expert knowledge from training radiology reports and clinical guidelines, producing offline semantic anchors describing grade-specific radiological findings without requiring patient-specific reports at inference. Through prototype contrastive alignment, patient-specific mpMRI representations are matched with these anchors to promote pathology-aligned representation learning. The Hierarchical Ordinal-aware Constraints (HOC) module decouples primary and secondary Gleason pattern prediction and maps their probabilistic outputs to GGG via a Differentiable Bio-logic Mapping Layer (DBML), ensuring pathological grading consistency. Experiments on public PI-CAI and in-house datasets demonstrate that KOAL outperforms state-of-the-art methods. Code is available at: https://github.com/Gother-GZ/KOAL.

cs.CV↗

arXiv2026

Enhancing Optomechanical Entanglement and Mechanical Squeezing by the Synergistic Effect of Quadratic Optomechanical Coupling and Coherent Feedback

In this paper, we investigate how to achieve strong optomechanical entanglement and mechanical squeezing in a membrane-embedded cavity optomechanical system incorporating a coherent feedback loop, where the membrane interacts with the cavity mode through both linear and quadratic optomechanical couplings. This hybrid optomechanical architecture offers a flexible tunability of intrinsic system parameters, thereby enabling controlled stiffening or softening of the mechanical mode through adjusting quadratic optomechanical coupling, as well as effective modulation of the cavity decay rate via feedback control. More importantly, the synergistic interplay effect allows for a strategic reconfiguration of the system's stability regime, which in turn permits the presence of significantly enhanced effective optomechanical coupling strengths before entering the unstable regime. Exploiting these unique features, we showcase that optomechanical entanglement can be substantially enhanced with positive coupling sign and suitable feedback parameters, while strong mechanical squeezing beyond the $3$dB limit is simultaneously achieved over a broad parameter range with negative coupling sign, reaching squeezing degree above $10$dB under optimized conditions. Our proposal, establishing an all-optical method for generating highly entangled or squeezed states in cavity optomechanical systems, opens up a new route to explore macroscopic quantum effects and to advance quantum information processing.

quant-ph↗