Searcharxiv⌕ Search

arXiv subjects

Jie Wu

Publications and source records attributed to Jie Wu.

At least 55 records · Page 3Linked to original sources
arXiv2026

Effects of Solar Wind Plasma Noise on Stochastic Gravitational Wave Background Searches with the LISA-Taiji Network

The LISA-Taiji dual detector network improves millihertz SGWB sensitivity through cross correlation measurements. Solar wind plasma, however, can generate plasma noise correlated between detectors and bias SGWB cross correlation estimates. We use high time resolution electron density data from Wind/SWE, estimate the solar wind electron density fluctuation spectrum with the Lomb-Scargle method, and propagate the resulting plasma noise to the TDI A/E channels of the LISA-Taiji network. By including finite arm propagation, Taylor frozen flow spatial correlations, and the network overlap reduction response, we compute the SGWB parameter bias induced by interdetector plasma noise. Although the single detector plasma residual is below the reference noise, the component correlated between detectors can enter the SGWB cross correlation estimator directly. Under dual detector scale coverage, the plasma induced parameter bias for a power law SGWB can reach 12.73% of the corresponding Fisher parameter uncertainty. For M2/M3 cosmic string spectra, the bias in ln Gmu can reach 19.26% of the corresponding Fisher parameter uncertainty for the network configurations, observing times, and frequency bands considered here. These results show that the impact of solar wind plasma noise cannot be assessed from the single detector residual noise level alone. In LISA-Taiji SGWB searches, the interdetector correlated component of this noise can directly affect parameter estimation.

astro-ph.CO↗
arXiv2026

Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution

Light Field Super-Resolution (LFSR) necessitates accurate modeling of spatial-angular correlations while preserving intrinsic 4D ray coherence. However, maintaining such high-dimensional consistency remains challenging, primarily due to two inherent limitations in prevailing modeling paradigms. First, spatial and angular dimensions are often modeled in a decoupled manner, restricting early cross-dimensional interaction and leading to geometric inconsistencies. Moreover, although continuous sequence modeling paradigms show promise in representing epipolar structures, their rigid scanning mechanisms fundamentally conflict with epipolar geometry, limiting geometry-aware feature aggregation. To address these challenges, we propose a hybrid light field super-resolution network, termed SMART, which integrates a Slope-Guided Mamba and an Angular-Refined Transformer to effectively overcome these limitations. Specifically, we introduce an angular-modulated spatial module to bridge the decoupling gap, incorporating angular priors to strengthen spatial-angular correlation modeling. To mitigate the scan-geometry mismatch, we propose a manifold-aligned trajectory module that enables geometry-consistent sequence modeling along epipolar structures. Experiments on five benchmarks demonstrate that SMART achieves state-of-the-art performance, surpassing previous methods by 0.42 dB (PSNR) with significantly reduced artifacts.

cs.CV↗
arXiv2026

Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems

Large Vision-Language Models (LVLMs) have been increasingly integrated into robotic systems. However, these models may exhibit overthinking behaviors, where they generate excessively long reasoning traces, incurring an excessive inference time. This overthinking behavior poses a serious risk to robotic systems, as the adversary can deliberately trigger overthinking to slow down the decision making of a victim robotic system, causing a variety of safety issues (i.e., an overthinking-induced slowdown attack). To initiate this attack, an adversary can embed carefully crafted, human-readable scene text into the visual scene observed by a victim robotic agent, causing significant inference delays even under a strict black-box setting. Therefore, the embedded scene text serves as a significant "trigger" for the attack. This work systematically identifies and validates transferable triggers of overthinking in robotic systems by introducing a three-stage framework. First, we construct a diverse corpus of reasoning-intensive scene text and extract overthinking-correlated lexical features from short response prefixes. Second, we perform an efficient black-box search guided by a prefix-based proxy score while selectively confirming a small set of top candidates with full latency measurements. Third, we evaluate black-box transfer using a fixed pool of triggers on unseen images and multiple LVLMs, reporting latency amplification and attack success rates under standard thresholds. Across three representative LVLMs, all triggers yield slowdown ratios greater than 1.0x, with the strongest single-trigger case reaching 6.96x. The physical printing of the text trigger still causes up to 4.74x latency amplification. These results demonstrate that our discovered triggers are transferred between multiple LVLM models and consistently cause significant slowdowns in robotic systems.

cs.CR↗
arXiv2026

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reliable. Yet existing data pipelines scale supervision while trusting the labeller, and policy-side methods assume the underlying answers are already correct. We instead treat scaling as a verifiable data-construction problem and decouple two axes before any policy update: prompt difficulty, expanded by route-specific evolution operators, and answer reliability, enforced by offline hypothesis-test falsification. We instantiate this as VeriEvol, an iterative framework with two extensible components: a type-aware evolution module that rewrites low-difficulty image-question seeds into harder, image-grounded prompts; and HTV-Agent, a verifier that accepts an answer only after multi-source counter-evidence has failed to refute it. The resulting verified data scales in volume, extends by adding evolution routes or verifier channels, and plugs directly into existing GRPO-style RL recipes. On a five-benchmark visual-math suite, scaling evolved SFT data from 10K to 250K samples raises the mean accuracy from 35.42 to 54.73; then, with backbone, SFT initialization, and GRPO recipe held fixed, VeriEvol adds a cumulative +3.88 over an un-evolved RL baseline, of which +1.82 comes from evolved prompts and +2.06 from the HTV-Agent verifier. We release the prompts, data, models, code, and the full verifier trace of every sample, so that downstream work can scale and audit the pipeline rather than only inspect its outputs.

cs.AI↗
arXiv2026

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR

Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a mainstream paradigm in recent years. Although existing LLM-based ASR models demonstrate impressive performance on public benchmarks, their training remains predominantly data-driven, leaving key practical challenges insufficiently addressed -- particularly limited downward scalability in resource-constrained deployments and hallucinations under acoustically challenging conditions. To address these issues, we present NIM4-ASR, a production-oriented LLM-based ASR framework optimized for both efficiency and robustness. Grounded in a principled delineation of functional roles between the encoder and the LLM, we redesign the multi-stage training paradigm to align each module with its intended capability boundary. Specifically, we reformulate the pre-training architecture and objective to mitigate the modality gap and improve parameter efficiency; introduce an iterative asynchronous SFT stage to preserve acoustic fidelity and constrain representation drift; and design an ASR-specialized reinforcement learning stage to further enhance recognition quality and robustness. We additionally incorporate a suite of production-oriented optimizations, including robustness under noisy and silent conditions, real-time streaming inference, and hotword customization via retrieval-augmented generation (RAG). Experiments show that NIM4-ASR achieves state-of-the-art performance on multiple public benchmarks with merely 2.3B parameters, while substantially outperforming larger-scale competitors on internal benchmarks -- particularly in entity-intensive real-world scenarios. NIM4-ASR further supports million-scale hotword customization via RAG with sub-millisecond retrieval latency, enabling efficient adaptation to emerging entities and personalized user requirements.

eess.AS↗
arXiv2026

Distance spectral radius and $H_b$-factors in graphs

Let $G$ be a connected graph, and let $b\geq2$ be an even integer. The distance spectral radius of $G$ is denoted by $μ(G)$. An $H_b$-factor of $G$ is a spanning subgraph $F$ of $G$ with $d_F(v)\in\{1,3,5,\ldots,b-1,b\}$ for any $v\in V(G)$, where $d_F(v)$ is the degree of $v$ in $F$. Lu and Wang provided a sufficient condition with respect to the number of odd components in $G-S$ for a connected graph $G$ of even order to contain an $H_b$-factor, where $S$ is a vertex subset of $G$ [H. Lu, D. Wang, On Cui-Kano's characterization problem on graph factors, J. Graph Theory 74 (2013) 335--343]. In this paper, motivated by Lu and Wang's above result, we establish an upper bound on the distance spectral radius $μ(G)$ of a connected graph $G$ to guarantee that $G$ contains an $H_b$-factor.

math.CO↗
arXiv2026

Constraining Kerr supermassive black hole properties using gravitational waves from inspiraling stellar-mass binary black holes

We study the capability of future space-based gravitational-wave (GW) detectors to constrain supermassive black hole (SMBH) properties through observations of inspiraling stellar-mass binary black holes (BBHs) orbiting them. Focusing on stable hierarchical triple systems, we model the BBH motion in Kerr spacetime and compute the modulated GW signals using the post Newtonian waveform combined with moving-source transformation. Based on the LISA configuration and second-generation time delay interferometry technology, we estimate parameter uncertainties with the Fisher information matrix. Our results show that the outer semimajor axis has the strongest influence on parameter precision, while the SMBH spin and eccentricity mainly affect their own uncertainties. For high-SNR signals, the SMBH mass and orbital parameters can be measured with relative uncertainties on the order of $10^{-5}$, while the spin magnitude and its orientation can be constrained to within a few percentages. Applying the method to an M87*-like system, GW observations provide more precise measurements of the SMBH mass and spin compared with current electromagnetic observations, highlighting the potential of space-based GW astronomy to probe SMBH properties with high accuracy.

gr-qc↗
arXiv2026

Identifiability of $g$ mode Resonances in Eccentric Binary Neutron Stars with Multidetector Observations

$g$ mode resonances in eccentric binary neutron star systems are potential probes of internal stratification, superfluidity, composition gradients, and the equation of state. Although such weak dynamical tidal signatures are unlikely to be resolved with current detector sensitivities, third generation observations may make them accessible, in which case identifying the weak resonant phase shift would provide information beyond the bulk adiabatic tidal deformability. We build a four class dataset in an eccentric harmonic framework, containing point particle, adiabatic tide, resonant $g$ mode, and pure noise samples, and use Einstein Telescope (ET) and Cosmic Explorer (CE) detector data to test whether this weak resonant phase signature can be identified from noisy time domain strain. The ET, CE, and ET+CE deep learning models reach accuracies of $0.655$, $0.815$, and $0.897$, respectively. On the same simulated samples, the matched filtering method reaches lower accuracies of $0.514$, $0.677$, and $0.689$. This result arises from the fact that the resonant correction manifests as a weak phase morphology difference superimposed on the adiabatic tidal background, whereas matched filtering is sensitive only to the overall similarity. Hence, in the presence of weak phase differences, the neural classifier employed in deep learning is better able to learn these local phase and morphology features from the complete time domain strain segment. The results indicate that joint third generation observations improve the identifiability of weak internal mode phase information.

astro-ph.HE↗
arXiv2026

Detection of Multiband Lensed Gravitational Waves from Dark Matter Halos with Deep Learning

Lensed gravitational waves acquire amplitude and phase modulations when propagating through the gravitational potential of dark matter halos, producing interference structures in the observed waveform. However, these features are often difficult to identify in detector noise. In this work, we develop a deep learning framework for the automatic classification of lensed gravitational wave signals under multiband observations. We simulate binary neutron star signals observed by the space based detector DECIGO and the ground based Einstein Telescope, and construct five classes of data including pure noise, unlensed signals, and three lensed cases generated by the SIS, CIS, and NFW dark matter halo models. By comparing single detector and joint detector configurations, we evaluate the classification performance under different observational settings. The results show that multiband observations significantly improve the identification of lensed signals and reduce confusion among different lens models. This approach provides an efficient method for automated recognition of lensed gravitational waves in future multiband gravitational wave observations.

astro-ph.IM↗
arXiv2026

On the Communication Complexity of Decentralized Stochastic Bilevel Optimization

Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural architecture search. To extend stochastic bilevel optimization to distributed data, several decentralized stochastic bilevel optimization algorithms have been developed. However, existing methods often suffer from slow convergence rates and high communication costs in heterogeneous settings, limiting their applicability to real-world tasks. To address these issues, we propose two novel decentralized stochastic bilevel gradient descent algorithms based on \textit{simultaneous} and \textit{alternating} update strategies. Our algorithms can achieve faster convergence rates and lower communication costs than existing methods. Importantly, our convergence analyses do not rely on strong assumptions regarding heterogeneity. More importantly, our theoretical analyses clearly disclose how the computation and communication regarding the Hessian-inverse-vector product under the heterogeneous setting affects the convergence rate. To the best of our knowledge, this is the first time such favorable theoretical results have been achieved with mild assumptions in the heterogeneous setting. Furthermore, we demonstrate how to establish the convergence rate for the alternating update strategy when combined with the variance-reduced gradient. Finally, experimental results confirm the efficacy of our algorithms.

cs.LG↗
arXiv2026

An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG

Retrieval-Augmented Generation (RAG) empowers LLMs with external knowledge, making cross-institutional domain-specific knowledge base integration a highly promising deployment paradigm. Despite this potential, strict privacy regulations create severe "data silos" that obstruct such collaboration. Building federated RAG systems requires distributed inference, but the Transformer's self-attention mechanism fundamentally conflicts with this by mandating cross-node access to distributed Key-Value caches. To address this challenge, we present FedRAG, a high-throughput, privacy-preserving federated RAG framework. At its core is a novel Scrambled Distributed Attention protocol that utilizes numerically stable feature scrambling and token permutation. By dynamically delegating scrambled computations to collaborating nodes, our system successfully decouples attention execution from data localization without exposing plaintext. Crucially, our approach requires no specialized hardware or model retraining, circumventing the prohibitive latency and communication overheads of cryptographic solutions while robustly defending against intermediate state inversion attacks. Extensive evaluations demonstrate our framework preserves negligible (<0.1\%) model utility degradation and achieves up to a 62$\times$ latency reduction over existing secure baselines, sustaining practical, human-reading throughput for cross-institutional knowledge synergy.

cs.CR↗
arXiv2026

Leveraging Verifier-Based Reinforcement Learning in Image Editing

While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually give overall scores without detailed checks, ignoring different instruction requirements and causing biased rewards. To address this, we argue that the key is to move from a simple scorer to a reasoning verifier. We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) and then leverages it for downstream image editing. The Edit-RRM breaks instructions into distinct principles, evaluates the edited image against each principle, and aggregates these checks into an interpretable, fine-grained reward. To build such an RRM, we first apply supervised fine-tuning (SFT) as a ``cold-start'' to generate CoT reward trajectories. Then, we introduce Group Contrastive Preference Optimization (GCPO), a reinforcement learning algorithm that leverages human pairwise preference data to reinforce our pointwise RRM. After building the RRM, we use GRPO to train editing models with this non-differentiable yet powerful reward model. Extensive experiments demonstrate that our Edit-RRM surpasses powerful VLMs such as Seed-1.5-VL and Seed-1.6-VL as an editing-specific reward model, and we observe a clear scaling trend, with performance consistently improving from 3B to 7B parameters. Moreover, Edit-R1 delivers gains to editing models like FLUX.1-kontext, highlighting its effectiveness in enhancing image editing.

cs.CV↗
arXiv2026

Solving Vlasov-Poisson system with an adaptive Hermite spectral method

We propose an adaptive Hermite spectral method for the Vlasov-Poisson system based on a recently developed frequency indicator that measures the contribution of the high-order expansion coefficients. Precisely, the symmetrically weighted Hermite basis with a scaling factor is utilized to approximate the distribution function to satisfy the increasing resolution requirement, which, for example, is induced by filamentation. To implement the scaling adjustment, a fast conservative projection operator is constructed in two steps. The first step is to formulate the projection as a constrained optimization problem to preserve key invariants, including mass, momentum, energy, and the $L^2$ norm of the distribution function. The second step is an ODE-based approximation developed to compute the updated expansion coefficients with linear complexity. Numerical experiments with 1D1V and 2D2V settings validate the feasibility and efficiency of this proposed adaptive Hermite method.

math.NA↗
arXiv2026

Stable Cohomotopy in Codimensions Two and Three: From Algebraic Characterizations to Bordism-Theoretic Interpretations

This paper investigates stable cohomotopy groups in codimensions two and three from complementary algebraic and geometric viewpoints. For general CW complexes, we give a complete characterization of stable cohomotopy in codimension two and a characterization in codimension three up to a $3$-primary parameter. Geometrically, we provide bordism-theoretic interpretations of these stable cohomotopy groups for oriented manifolds in codimension two and string manifolds in codimension three. As an application, we derive necessary and sufficient conditions for the existence of nowhere-vanishing sections of vector bundles, extending the foundational codimension-one results of Konstantis.

math.AT↗
arXiv2026

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without an additional cold-start stage. Our approach unlocks the model's intrinsic potential to perform advanced reasoning tasks: Reasoning Text-to-Image Generation, where the model actively infers implicit user intents, and Self-Reflective Refinement, where it autonomously diagnoses and corrects misalignments in generated outputs. To address the challenge of providing stable supervision for real-world multimodal generation, we introduce the Decompositional Verifiable Reward (DVReward). Unlike holistic scalar rewards, DVReward utilizes an LLM to decompose complex user requests into atomic, verifiable semantic and quality questions, which are then evaluated by a general MLLM to provide reliable and interpretable feedback. Extensive experiments demonstrate that AlphaGRPO yields robust improvements across multimodal generation benchmarks, including GenEval, TIIF-Bench, DPG-Bench and WISE, while also achieving significant gains in editing tasks on GEdit without training on editing tasks. These results validate that our self-reflective reinforcement approach effectively leverages inherent understanding to guide high-fidelity generation. Project page: https://huangrh99.github.io/AlphaGRPO/

cs.CV↗
arXiv2026

ViPO: Visual Preference Optimization at Scale

While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naively optimizing on such noisy datasets fails to learn preferences, hindering effective scaling. To enhance robustness against noise, we propose Poly-DPO, which extends the DPO objective with an additional polynomial term that dynamically adjusts model confidence based on dataset characteristics, enabling effective learning across diverse data distributions. Beyond biased patterns, existing datasets suffer from low resolution, limited prompt diversity, and imbalanced distributions. To facilitate large-scale visual preference optimization by tackling data bottlenecks, we construct ViPO, a massive-scale preference dataset with 1M image pairs at 1024px across five categories and 300K video pairs at 720p+ across three categories. State-of-the-art generative models and diverse prompts ensure reliable preference signals with balanced distributions. Remarkably, when applying Poly-DPO to our high-quality dataset, the optimal configuration converges to standard DPO. This convergence validates dataset quality and Poly-DPO's adaptive nature: sophisticated optimization becomes unnecessary with sufficient data quality, yet remains valuable for imperfect datasets. We validate our approach across visual generation models. On noisy datasets like Pick-a-Pic V2, Poly-DPO achieves 6.87 and 2.32 gains over Diffusion-DPO on GenEval for SD1.5 and SDXL, respectively. For ViPO, models achieve performance far exceeding those trained on existing open-source preference datasets. These results confirm that addressing both algorithmic adaptability and data quality is essential for scaling visual preference optimization.

cs.CV↗
arXiv2026

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data

Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustness to explicit noise (e.g., document semantics) but overlooks implicit noise (spurious features). Moreover, previous studies on spurious features in LLMs are limited to specific types (e.g., formats) and narrow scenarios (e.g., ICL). In this work, we identify and study spurious features in the RAG paradigm, a robustness issue caused by the sensitivity of LLMs to semantic-agnostic features. We then propose a novel framework, SURE, to empirically quantify the robustness of RALMs against spurious features. Beyond providing a comprehensive taxonomy and metrics for evaluation, the framework's data synthesis pipeline facilitates training-based strategies to improve robustness. Further analysis suggests that spurious features are a widespread and challenging problem in the field of RAG. Our code is available at https://github.com/maybenotime/RAG-SpuriousFeatures .

cs.CL↗
arXiv2026

Towards Long-horizon Agentic Multimodal Search

Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous information and high token costs associated with multimodal inputs over long horizons remains a critical challenge, as existing methods often suffer from context explosion or the loss of crucial visual signals. To address this, we propose a novel Long-horizon MultiModal deep search framework, named LMM-Searcher, centered on a file-based visual representation mechanism. By offloading visual assets to an external file system and mapping them to lightweight textual identifiers (UIDs), our approach mitigates context overhead while preserving multimodal information for future access. We equip the agent with a tailored fetch-image tool, enabling a progressive, on-demand visual loading strategy for active perception. Furthermore, we introduce a data synthesis pipeline designed to generate queries requiring complex cross-modal multi-hop reasoning. Using this pipeline, we distill 12K high-quality trajectories to fine-tune Qwen3-VL-Thinking-30A3B into a specialized multimodal deep search agent. Extensive experiments across four benchmarks demonstrate that our method successfully scales to 100-turn search horizons, achieving state-of-the-art performance among open-source models on challenging long-horizon benchmarks like MM-BrowseComp and MMSearch-Plus, while also exhibiting strong generalizability across different base models. Our code will be released in https://github.com/RUCAIBox/LMM-Searcher.

cs.CV↗