arXiv subjects

Yuhao Wang

Publications and source records attributed to Yuhao Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Incentive Noise and Structural Prior Infusion for Multi-modal Object Re-Identification

Multi-modal object Re-Identification (ReID) benefits from complementary information across heterogeneous imaging modalities. To further enrich semantic representation, text descriptions have recently been incorporated as an additional modality. However, recent vision-language approaches often treat text descriptions as clean, deterministic signals and overlook their inherent noise, including modality-mismatched phrases and semantically ambiguous expressions. Moreover, prevailing methods lack explicit mechanisms to reconcile fine-grained structural discrepancies between modalities, even after high-level semantic alignment. To address these challenges, we propose a novel framework centered on Positive-Incentive Noise (π-noise) and structured prompt modulation. First, the Semantic Cross-Modal Modulator harnesses task-aware π-noise, sampled from a distribution conditioned on both visual and text inputs, to perturb global tokens and enable semantics-guided cross-modal compensation. Second, the Structure-Aware Prompt Adapter injects learnable geometric priors via prompts to enhance spatial consistency. Third, the Context-Aware Sparse Fusion module distills structural context to guide adaptive fusion while shielding identity features from noisy local details. Experiments on three multi-modal ReID benchmarks demonstrate the effectiveness and robustness of our approach. The code is available at https://github.com/zw-absin/INSPI.

cs.CV↗

arXiv2026

EviRCA: Decoupling Evidence Extraction from Reasoning for Microservice Root-Cause Analysis

Root-cause analysis (RCA) is a critical yet labor-intensive task for maintaining modern microservice systems, making it an attractive target for large language models (LLMs). Recent agentic approaches allow an LLM to iteratively explore raw telemetry by generating and executing code, asking a single model to simultaneously retrieve evidence, localize faults, and infer root causes over large volumes of heterogeneous telemetry, which leads to high computational cost, unstable behavior, and limited diagnostic accuracy. However, raw telemetry consists of numeric metrics, structured traces, and machine-generated logs that are not directly suitable for LLM processing. We present EviRCA, a framework for LLM-based RCA that decouples deterministic evidence extraction from LLM reasoning. A system-agnostic extraction stage converts raw metrics, traces, and logs into a compact set of faithful multimodal evidence cards, while the LLM reasons only over these structured observations through a small set of predefined read-only tools, without accessing raw telemetry or executing code. We evaluate EviRCA on OpenRCA, a benchmark built from real, heterogeneous telemetry across three enterprise systems. EviRCA achieves a correct rate of 40.6%-43.9% across two different LLMs, substantially outperforming prior OpenRCA baselines that achieve up to 15.2%, while reducing token consumption by 15-26x and execution time by 3-20x. Moreover, EviRCA solves hard cases requiring simultaneous reasoning over time, components, and root causes, a setting where previous approaches reported near-zero performance. Our process-level failure analysis further shows that the bottleneck lies in judging the evidence that the extraction stage has already surfaced, rather than searching for it, suggesting that the effectiveness of LLM-based RCA depends heavily on the quality of evidence extraction.

cs.SE↗

arXiv2026

TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents

GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory usage. Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint. Once tokens are discarded, the corresponding visual evidence cannot be recovered without re-encoding. Pruning therefore becomes an \textit{irreversible admission decision} that must remain useful for unknown future targets while preserving coverage of operable regions under tight budgets. To address these challenges, we propose \textbf{\method{}}, a training-free framework for \emph{\textbf{T}rajectory-\textbf{r}obust \textbf{A}dmission and \textbf{C}overage-aware \textbf{E}vidence ordering}. Specifically, we combine a query-independent layout-derived interaction prior with instruction relevance and feature novelty to rank visual evidence according to both potential future utility and diversity. Then, we reserve part of the budget for native visual tokens distributed across the screen, repairing missing spatial coverage without breaking the ordering. Together, these mechanisms produce a nested token order, allowing retained visual evidence to shrink monotonically across budgets while remaining reusable throughout the trajectory. Finally, our monotone KV contraction incrementally contracts retired frames into compact session state, avoiding repeated visual encoding or pruning. Extensive experiments across six GUI benchmarks and diverse models verify the effectiveness of our proposed \method{} under tight budgets. The source code will be released.

cs.CV↗

arXiv2026

Develop and Optimize 5DCT Imaging Simulation and Reconstruction Methods

Purpose: To develop and optimize a 5DCT (3D + cardiac phase + respiratory phase) imaging simulation and reconstruction pipeline, and to compare two sinogram-space interpolation methods for reconstructing images at arbitrary combinations of cardiac and respiratory phase. Methods: Helical CT projections were simulated from the 4D XCAT phantom across a range of cardiac and respiratory motion states, with Poisson and electronic noise added. Ground-truth-matched volumes were generated at 5 cardiac phases and 10 respiratory amplitudes (50 total phase combinations). Because acquired projections are sparsely and unevenly distributed across this joint phase space, each target slice was reconstructed by interpolating rebinned sinogram rows to the target cardiac phase and respiratory amplitude, using either 2D scattered barycentric interpolation or 2D scattered local linear interpolation with a circular kernel for cardiac phase. Reconstructed volumes were compared to phantom ground truth using mean absolute error (MAE), and to conventional respiratory-gated 4DCT (r4DCT) reconstructed from the same simulated data. Results: Both interpolation methods eliminated the severe axial misalignment artifacts present when helical projections were reconstructed without phase-space interpolation. Local linear interpolation achieved lower MAE than barycentric interpolation across most tested conditions, with the largest improvement at low pitch. The 5DCT pipeline also produced respiratory-only volumes with fewer residual cardiac-motion artifacts than conventional r4DCT reconstructed from the same projection data, including at standard clinical pitch (0.1). Conclusions: 5DCT reconstruction using sinogram-space interpolation is feasible and can jointly resolve cardiac and respiratory motion with better accuracy than conventional 4DCT reconstruction.

physics.med-ph↗

arXiv2026

Lightweight Dynamic Modeling of Cable-Driven Continuum Robots Based on Actuation-Space Energy Formulation

Cable-driven continuum robots (CDCRs) require accurate, real-time dynamic models for high-speed dynamics prediction or model-based control, making such capability an urgent need. In this paper, we propose the Lightweight Actuation-Space Energy Modeling (LASEM) framework for CDCRs, which formulates actuation potential energy directly in actuation space to enable lightweight yet accurate dynamic modeling. Through a unified variational derivation, the governing dynamics reduce to a single partial differential equation (PDE), requiring only the Euler moment balance while implicitly incorporating the Newton force balance. By also avoiding explicit computation of cable-backbone contact forces, the formulation simplifies the model structure and improves computational efficiency while preserving geometric accuracy and physical consistency. Importantly, the proposed framework for dynamic modeling natively supports both force-input and displacement-input actuation modes, a capability seldom achieved in existing dynamic formulations. Leveraging this lightweight structure, a Galerkin space-time modal discretization with analytical time-domain derivatives of the reduced state further enables an average 62.3% computational speedup over state-of-the-art real-time dynamic modeling approaches.

cs.RO↗

arXiv2026

Multi-Task Deep Recommender Systems: A Survey

Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.

cs.IR↗

arXiv2026

Learning a Single Token to Replace Long System Prompts in LLMs

Long system prompts are widely used to steer Large Language Models (LLMs), but repeatedly processing them at inference time is inefficient and consumes valuable context budget. This motivates a central question: can the behavioral effect of a long system prompt be retained using only a minimal learned representation? To enable this, we propose a lightweight training framework that learns a single Behavior-Equivalent Token ([BE]). The framework first trains [BE] to encode the semantic content of the original system prompt via reconstruction, and then distills the prompt's downstream behavior into this single token. Importantly, our method requires no update to the pretrained LLM weights, no auxiliary compression models, and no labeled responses. Empirical evaluations on three datasets show that replacing long prompts with a single [BE] token yields up to a $3000\times$ prompt compression ratio, while retaining about 98% of the downstream performance of the original system prompts. This substantially reduces inference cost and frees nearly the entire context window for user inputs and model outputs.

cs.CL↗

arXiv2026

GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory

Organizing long-term memory for multimodal agents remains challenging because existing methods either suffer from expensive question-agnostic offline summaries or naive embedding similarity matching that introduces incomplete and redundant context. To address these issues, we propose GraphMemix, a combinatorial-optimization graph memory framework that models memory organization as query-aware evidence-forest construction. Specifically, our method consists of three key components:(1) candidate graph construction, which expands multi-view seed memories through schema and semantic relations to acquire query-aware original context; (2) evidence utility and activation costs, which decouples direct memory support from anchor-conditioned relation verification to suppress redundant or conflicting information; and (3) forest optimization, which jointly selects a forest-format memory context under a maximum evidence budget and its reliable relational structure. By organizing memory into a query-relevant subgraph, the method avoids substantial lifecycle cost and recovers low-similarity complementary evidence. Experimental results across four long-term multimodal memory benchmarks demonstrate significant improvements with different foundation models and establish a new Pareto frontier between accuracy and lifecycle cost.

cs.AI↗

arXiv2026

Minimax estimation of functionals in sparse vector model with correlated observations

We consider the observations of an unknown $s$-sparse vector ${\boldsymbol θ}$ corrupted by Gaussian noise with zero mean and unknown covariance matrix ${\boldsymbol Σ}$. We propose minimax optimal methods of estimating the $\ell_2$ norm of ${\boldsymbol θ}$ and testing the hypothesis $H_0: {\boldsymbol θ}=0$ against sparse alternatives when only partial information about ${\boldsymbol Σ}$ is available, such as an upper bound on its Frobenius norm and the values of its diagonal entries to within an unknown scaling factor. We show that the minimax rates of the estimation and testing are leveraged not by the dimension of the problem but by the value of the Frobenius norm of ${\boldsymbol Σ}$.

math.ST↗

arXiv2026

Parallel single-pixel imaging based on modulation region expansion and overlapping reconstruction

Parallel single-pixel imaging (PSPI) enhances the data acquisition efficiency of single-pixel imaging, but its reconstruction quality depends on a cumbersome and noise-sensitive calibration process. To address this challenge, a PSPI strategy was introduced that leverages modulation region expansion and overlapping reconstruction. This method results in the calibration of modulation of the subregion for each detector, enabling robust operations with undersampled data. It compensates for misalignment via modulation region expansion and overlapping reconstruction, achieving seamless and high-quality imaging that surpasses conventional PSPI in simulations and experiments. Furthermore, this strategy exhibits remarkable robustness, maintaining high imaging quality under extremely nonideal conditions, such as large deflection angles between the array detector and the modulator. This work provides a simple, efficient, and robust framework that simplifies the PSPI workflow and offers broad applicability in high-resolution, high-speed computational imaging.

physics.optics↗

arXiv2026

MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualization

Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization, by simplifying complex datasets while retaining essential information. However, achieving both high DR accuracy and strong explainability remains a fundamental challenge, especially for users dealing with high-dimensional data. Traditional DR methods often face a trade-off between precision and transparency, where optimizing for performance can lead to reduced explainability, and vice versa. This limitation is especially prominent in real-world applications such as image, tabular, and text data analysis, where both accuracy and explainability are critical. To address these challenges, this work introduces the MoE-based Explainable Deep Manifold Transformation (DMT-ME). The proposed approach combines a geometry-aware hyperbolic mapper with Mixture of Experts (MoE) models, where sparse expert specialization provides the main representational gain and the hyperbolic component offers an additional refinement for structurally complex data. DMT-ME enhances DR accuracy primarily through MoE-based sparse routing and structure-aware matching, while also improving explainability by explicitly linking input data, embedding outcomes, and key features through the MoE structure. Extensive experiments demonstrate that DMT-ME consistently achieves superior performance in both DR accuracy and model explainability, making it a robust solution for complex data analysis. The code is available at https://github.com/zangzelin/code_dmtme.

cs.LG↗

arXiv2026

Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation

Multi-modal object Re-Identification (ReID) aims to retrieve target instances by leveraging complementary information across modalities. However, existing methods suffer from two challenges. First, they often fail to exploit well-aligned and reliable semantic priors, making them vulnerable to background clutter and cross-modal misalignment. On the other hand, they typically rely on holistic feature modeling, overlooking the synergy between global and local representations. To overcome these limitations, we propose a robust multi-modal ReID framework with dual semantic guidance and global-local mutual modulation, which mainly consists of three key components, namely the Text-Semantic Injector (TSI), the Masked Global-Local Modulator (MGLM), and the Hierarchical MoE Fusion (HMF). The TSI enhances semantic awareness by integrating clean and coherent textual features into visual tokens. The MGLM enables part-aware cross-modal interaction through joint guidance from soft masks and global context, improving fine-grained feature alignment. Finally, the HMF adaptively aggregates multi-spectral features under local semantic supervision, yielding discriminative and robust representations. Extensive experiments on three multi-modal ReID benchmarks demonstrate the effectiveness of the proposed method. The code will be made publicly available at https://github.com/zw-absin/DSGM upon acceptance.

cs.CV↗

arXiv2026

Intrinsic Tangential Hadamard Differentiability of Rough-BSDE Solution Maps

We study first-order sensitivity of a scalar backward stochastic differential equation with a deterministic rough driver. The driver belongs to the nonlinear space of step-two weakly geometric $p$-rough paths, $2<p<3$, so an ordinary Banach-space difference quotient is not available. At a fixed rough path $x$, we use a weakly geometric, finite-$(p,p/2)$-variation tensor realization of the Qian-Tudor tangent structure, represented intrinsically by a first-level direction $h$ and a compatible second-level direction $κ$. Admissible rough-path secants are required to converge in a strong levelwise variation topology. Under bounded smooth rough vector fields, a bounded terminal condition, and a globally Lipschitz generator, we construct a continuous linear map $A_x:T_x^p\to S^\infty\times H^2_{\mathrm{BMO}}$. The proof first establishes a uniform four-jet expansion for reset rough flows along bounded realizations of full rough tangents. A Doss-Sussmann transformation transfers this expansion to quadratic generators. Uniform BMO and reverse-Holder estimates then yield a local difference-quotient theorem, which is propagated over a fixed deterministic partition and reconstructed in the original coordinates. The resulting derivative is independent of the joint lift, central decomposition, and radial realization. Consequently, solution difference quotients converge to $A_x(h,κ)$ for varying directions and arbitrary admissible secants with strong levelwise variation contact. This is intrinsic tangential Hadamard differentiability on that tensor-coordinate tangent class. Locally bounded ray-homogeneous selections give Frechet-differentiable chart pullbacks at the parameter origin. The latter statement is chartwise; it is not Frechet differentiability of the solution map in the homogeneous rough-path metric.

math.PR↗

arXiv2026

Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance

Multi-modal object Re-Identification (ReID) aims to retrieve specific objects by integrating complementary information from multiple modalities. However, existing multi-modal ReID methods do not effectively address background interference suppression or achieve tri-modal alignment, instead focusing on pairwise feature fusion. Moreover, many current aggregation approaches suffer from high computational complexity. To address these limitations, we propose PRISM, a novel multi-modal ReID framework built upon Prompt-S6 (PS6) and semantic-aware knowledge guidance. PS6 maintains the linear complexity and strong sequence modeling capability of Mamba while enabling efficient cross-modal interaction. Leveraging these advantages, we design two key components: Semantic-Driven Token Pruning (SDTP) and Progressive Fusion Network (PFN). Parsing semantic priors from the segmentation foundation models, the SDTP then leverages these priors and applies dynamic token pruning to suppress background noise and refine feature representations. The PFN progressively aggregates multi-modal features to achieve tri-modal alignment and fully exploit modality complementarity. With the proposed modules, PRISM generates more robust multi-modal representations under complex scenarios. Extensive experiments on four multi-modal object ReID benchmarks demonstrate the effectiveness and efficiency of our approach. The source code is available at https://github.com/zw-absin/PRISM.

cs.CV↗

arXiv2026

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework

Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning processes. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, TeaRAG improves the average Exact Match by 4% and 2% while reducing output tokens by 61% and 59% on Llama3-8B-Instruct and Qwen2.5-14B-Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG.

cs.IR↗

arXiv2026

VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also frequently appears as visualized text embedded in images, raising the question of whether current VLMs handle such input requests comparably. We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and visualized-text questions under controlled rendering conditions. Extensive evaluation of over 30 representative VLMs reveals a pronounced modality gap: models that perform well on pure-text queries often degrade substantially when equivalent semantic content is presented as visualized text. This gap is further amplified by increased perceptual difficulty, highlighting sensitivity to rendering variations despite unchanged semantics. Overall, VISTA-Bench provides a principled evaluation framework to diagnose this limitation and to guide progress toward more unified language representations across tokenized text and pixels. The source dataset and code are publicly available at https://github.com/QingAnLiu/VISTA-Bench.

cs.CV↗

arXiv2026

Wavenumber-explicit stability and preasymptotic error analysis of UPML finite element method for obstacle scattering problems

This paper develops a wavenumber-explicit stability and preasymptotic error analysis for finite element approximation of the two-dimensional Helmholtz scattering problem with a uniaxial perfectly matched layer (UPML) truncation. The analysis is based on direct estimates of the stretched Green kernel associated with the Cartesian complex coordinate transformation. We establish explicit stability for the truncated UPML problem. In particular, we prove that the inf-sup constant of the truncated UPML formulation is $μ_L = O(k^{-1})$ in a natural $k$-weighted $H^1$ norm. As a consequence, we also obtain an exponential decay estimate for the PML truncation error. Based on this stability estimate, we formulate a linear continuous interior penalty finite element method (CIP-FEM) on the truncated UPML domain. A key ingredient of the analysis is to establish a piecewise $H^{1+s}$-regularity result (for any $0<s<1$), which accounts for coefficient jumps across PML interfaces and singularities induced by Cartesian corner geometries. This fractional regularity is sufficient to derive wavenumber-explicit preasymptotic error estimates. Numerical experiments confirm the theoretical predictions and illustrate the effectiveness of the UPML CIP-FEM in the high-frequency regime.

math.NA↗

arXiv2026

Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding

Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains. Recently, generative recommendation (GR) has emerged. It first learns semantic identifiers (SIDs) from item semantics and formulates recommendation as autoregressive generation. However, existing methods face two critical issues: (1) they ignore collaborative correlations across domains during tokenization, and (2) they adopt inefficient decoding strategies, such as beam search, during generation, which hinders real-time deployment. To address these limitations, we propose GenCDSR, an effective and efficient generative framework for CDSR. Specifically, we design a cross-domain hybrid tokenization mechanism with a multi-tower architecture to jointly capture cross-domain commonalities and domain-specific distinctions through hierarchical shared-specific and fine-grained codebooks. Furthermore, we develop a cross-domain serial-parallel decoding strategy that leverages the hierarchical SID structure to partially parallelize generation, significantly reducing inference latency while preserving generation consistency. Experiments on three public datasets show that GenCDSR achieves an average accuracy improvement of 1.5 percent and an average inference latency reduction of 85.1 percent compared with state-of-the-art baselines. The implementation code and datasets are available online: https://github.com/Applied-Machine-Learning-Lab/RecSys2026_GenCDSR.

cs.AI↗