arXiv subjects

Xinyu Wu

Publications and source records attributed to Xinyu Wu.

At least 19 recordsLinked to original sources

arXiv2026

Geometry-dependent rank defect in $C^1$ cubic spline space

Determining the dimension of the $C^1$ cubic spline space $S_3^1(\mathcal{T})$ on an arbitrary nondegenerate planar triangulation has remained unresolved since the 1970s. Schumaker's lower bound includes a local correction $\sigma$ for singular interior four-stars, and it was conjectured that this bound is always attained. We disprove this conjecture by constructing a one-parameter family of nondegenerate realizations of a fixed 18-triangle complex, with only the central vertex moving as $v_6(t)=(t,0)$ on the admissible interval $I=(-3/4,24/55)$. The family exhibits three distinct cases. For $t\in I\setminus\{1/5,3/83\}$, the lower bound is attained and $\dim S_3^1(\mathcal{T}(t))=33$. At $t=3/83$, the central four-star is singular, $\sigma=1$, and the resulting dimension 34 is exactly accounted for by the classical local correction. At $t=1/5$, however, all interior vertices are nonsingular and $\sigma=0$, yet $\dim S_3^1(\mathcal{T}(1/5))=34>P_{\mathcal{T}(1/5)}(1,3)=33$. The smoothing-cofactor calculation shows that the dependence at $t=3/83$ is confined to the central vertex block, whereas the dependence at $t=1/5$ couples all seven interior vertex cycles even though every individual block has full row rank. A complementary Bernstein--B\'ezier calculation gives the same dimension profile. Thus the singular-four-star correction does not capture every geometry-dependent contribution to $\dim S_3^1(\mathcal{T})$; genuinely global compatibility must also be taken into account.

math.NA↗

arXiv2026

SkiP: When to Skip and When to Refine for Efficient Robot Manipulation

Previous imitation learning policies predict future actions at every control step, whether in smooth motion phases or precise, contact-rich operation phases. This uniform treatment is wasteful: most steps in a manipulation trajectory traverse free space and carry little task-relevant information, while a small fraction of \emph{key} steps around contacts, grasps, and alignment demand dense, high-resolution prediction. We propose a novel \emph{action relabeling} mechanism: at each timestep in a skip segment, we replace the behavior cloning target with the action at the entrance of the next key segment, enabling the policy to leap over redundant steps in a single decision. The resulting \textbf{Skip Policy (SkiP)} dynamically leaps over skip segments and intensively refines actions in key segments, within a single unified network requiring no learned skip planner or hierarchical structure. To automatically partition demonstrations into key and skip segments without manual annotation, we introduce \emph{Motion Spectrum Keying} (MSK), a fast, task-agnostic procedure that detects local motion complexity from action signals. Extensive experiments across 72 simulated manipulation tasks and three real-robot tasks show that SkiP reduces executed steps by $15$--$40\%$ while matching or improving success rates across various policy backbones. Project page: \texttt{https://pgq18.github.io/SkiP-page/}.

cs.RO↗

arXiv2026

Spectral Sensitivity of Directed Weighted Networks: Why Weakening Edges May Trigger Synchronization

Synchronization in dynamical systems on directed weighted networks is often associated with stronger coupling and denser interactions. This paper shows that the opposite can also occur: weakening selected edges may increase the generalized algebraic connectivity, denoted by $\kappa$, and in some nonlinear systems this spectral improvement is accompanied by a transition from nonsynchronization to synchronization. To explain this effect, we develop a perturbation-based spectral sensitivity framework for directed weighted networks. We derive an explicit first-order formula for the response of $\kappa$ to edge-weight perturbations and show that it decomposes into a directed cut-energy term and a stationary redistribution term. This decomposition clarifies how asymmetric flow structure and invariant-mass redistribution jointly determine the synchronization role of each edge. Based on this theory, we design sensitivity-guided algorithms for edge weakening, edge deletion, negative-edge insertion, and edge strengthening. Experiments on synthetic and real networks show that these methods identify critical edges whose modification yields substantial gains in $\kappa$. Simulations of first- and second-order nonlinear consensus dynamics further show markedly faster convergence and, in some cases, a transition from incoherence to synchronization. The results provide a local spectral mechanism by which reducing or reallocating coupling can enhance synchronization-related performance.

math.DS↗

arXiv2026

Multi-Perspective Transformers in ARC-AGI-2 Challenge

ARC-AGI-2 is a benchmark of human-intuitive visual puzzles that measures a machine's ability to generalize from limited examples, interpret symbolic meaning, and flexibly apply rules in varying contexts. In this paper, we discuss our approach to solving the ARC-AGI-2 puzzles with TinyLM, with additional fine-tuning at test time, including Test-Time-Training (TTT) and Products of Experts (POE). Our model achieves 96.1% accuracy on the training set and 21.7% accuracy on the evaluation set.

cs.LG↗

arXiv2026

ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response

While passive agents merely follow instructions, proactive agents align with higher-level objectives, such as assistance and safety by continuously monitoring the environment to determine when and how to act. However, developing proactive agents is hindered by the lack of specialized resources. To address this, we introduce ProAct-75, a benchmark designed to train and evaluate proactive agents across diverse domains, including assistance, maintenance, and safety monitoring. Spanning 75 tasks, our dataset features 91,581 step-level annotations enriched with explicit task graphs. These graphs encode step dependencies and parallel execution possibilities, providing the structural grounding necessary for complex decision-making. Building on this benchmark, we propose ProAct-Helper, a reference baseline powered by a Multimodal Large Language Model (MLLM) that grounds decision-making in state detection, and leveraging task graphs to enable entropy-driven heuristic search for action selection, allowing agents to execute parallel threads independently rather than mirroring the human's next step. Extensive experiments demonstrate that ProAct-Helper outperforms strong closed-source models, improving trigger detection mF1 by 6.21%, saving 0.25 more steps in online one-step decision, and increasing the rate of parallel actions by 15.58%.

cs.RO↗

arXiv2025

ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning

Multimodal Large Language Models (MLLMs) have empowered embodied agents with remarkable capabilities in planning and reasoning. However, when facing ambiguous natural language instructions (e.g., "fetch the tool" in a cluttered room), current agents often fail to balance the high cost of physical exploration against the cognitive cost of human interaction. They typically treat disambiguation as a passive perception problem, lacking the strategic reasoning to minimize total task execution costs. To bridge this gap, we propose ESearch-R1, a cost-aware embodied reasoning framework that unifies interactive dialogue (Ask), episodic memory retrieval (GetMemory), and physical navigation (Navigate) into a single decision process. We introduce HC-GRPO (Heterogeneous Cost-Aware Group Relative Policy Optimization). Unlike traditional PPO which relies on a separate value critic, HC-GRPO optimizes the MLLM by sampling groups of reasoning trajectories and reinforcing those that achieve the optimal trade-off between information gain and heterogeneous costs (e.g., navigate time, and human attention). Extensive experiments in AI2-THOR demonstrate that ESearch-R1 significantly outperforms standard ReAct-based agents. It improves task success rates while reducing total operational costs by approximately 50\%, validating the effectiveness of GRPO in aligning MLLM agents with physical world constraints.

cs.AI↗

arXiv2025

GraspView: Active Perception Scoring and Best-View Optimization for Robotic Grasping in Cluttered Environments

Robotic grasping is a fundamental capability for autonomous manipulation, yet remains highly challenging in cluttered environments where occlusion, poor perception quality, and inconsistent 3D reconstructions often lead to unstable or failed grasps. Conventional pipelines have widely relied on RGB-D cameras to provide geometric information, which fail on transparent or glossy objects and degrade at close range. We present GraspView, an RGB-only robotic grasping pipeline that achieves accurate manipulation in cluttered environments without depth sensors. Our framework integrates three key components: (i) global perception scene reconstruction, which provides locally consistent, up-to-scale geometry from a single RGB view and fuses multi-view projections into a coherent global 3D scene; (ii) a render-and-score active perception strategy, which dynamically selects next-best-views to reveal occluded regions; and (iii) an online metric alignment module that calibrates VGGT predictions against robot kinematics to ensure physical scale consistency. Building on these tailor-designed modules, GraspView performs best-view global grasping, fusing multi-view reconstructions and leveraging GraspNet for robust execution. Experiments on diverse tabletop objects demonstrate that GraspView significantly outperforms both RGB-D and single-view RGB baselines, especially under heavy occlusion, near-field sensing, and with transparent objects. These results highlight GraspView as a practical and versatile alternative to RGB-D pipelines, enabling reliable grasping in unstructured real-world environments.

cs.RO↗

arXiv2025

RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

Vision-Language-Action (VLA) models have become a prominent paradigm for embodied intelligence, yet further performance improvements typically rely on scaling up training data and model size -- an approach that is prohibitively expensive for robotics and fundamentally limited by data collection costs. We address this limitation with $\mathbf{RoVer}$, an embodied test-time scaling framework that uses a $\mathbf{Ro}$bot Process Reward Model (PRM) as a Test-Time $\mathbf{Ver}$ifier to enhance the capabilities of existing VLA models without modifying their architectures or weights. Specifically, RoVer (i) assigns scalar-based process rewards to evaluate the reliability of candidate actions, and (ii) predicts an action-space direction for candidate expansion/refinement. During inference, RoVer generates multiple candidate actions concurrently from the base policy, expands them along PRM-predicted directions, and then scores all candidates with PRM to select the optimal action for execution. Notably, by caching shared perception features, it can amortize perception cost and evaluate more candidates under the same test-time computational budget. Essentially, our approach effectively transforms available computing resources into better action decision-making, realizing the benefits of test-time scaling without extra training overhead. Our contributions are threefold: (1) a general, plug-and-play test-time scaling framework for VLAs; (2) a PRM that jointly provides scalar process rewards and an action-space direction to guide exploration; and (3) an efficient direction-guided sampling strategy that leverages a shared perception cache to enable scalable candidate generation and selection during inference.

cs.RO↗

arXiv2025

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT introduces new safety challenges that extend beyond conventional language model alignment. We identify a failure mode in current safety CoT tuning methods: the \textit{snowball effect}, where minor reasoning deviations progressively amplify throughout the thought process, leading to either harmful compliance or excessive refusal. This effect stems from models being trained to imitate perfect reasoning scripts without learning to self-correct. To address this limitation, we propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning. Our method involves constructing a dataset containing Temptation-Correction and Hesitation-Correction samples, where models learn to recover from harmful reasoning drifts and unnecessary cautions. Extensive experiments show that AdvChain significantly enhances robustness against jailbreak attacks and CoT hijacking while substantially reducing over-refusal on benign prompts, achieving a superior safety-utility balance without compromising reasoning capabilities. Our work establishes a new direction for building more robust and reliable reasoning models.

cs.AI↗

arXiv2025

Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation

We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a) acceptance of only one style image, thus prohibiting hybrid aesthetics and scalability to more styles, and (b) lack of a principled mechanism to balance several stylistic influences. AMSF mitigates these challenges by encoding all style images and textual hints with a semantic token decomposition module that is adaptively injected into every cross-attention layer of an frozen diffusion model. A similarity-aware re-weighting module then recalibrates, at each denoising step, the attention allocated to every style component, yielding balanced and user-controllable blends without any fine-tuning or external adapters. Both qualitative and quantitative evaluations show that AMSF produces multi-style fusion results that consistently outperform the state-of-the-art approaches, while its fusion design scales seamlessly to two or more styles. These capabilities position AMSF as a practical step toward expressive multi-style generation in diffusion models.

cs.CV↗

arXiv2025

Prompt-Guided Dual Latent Steering for Inversion Problems

Inverting corrupted images into the latent space of diffusion models is challenging. Current methods, which encode an image into a single latent vector, struggle to balance structural fidelity with semantic accuracy, leading to reconstructions with semantic drift, such as blurred details or incorrect attributes. To overcome this, we introduce Prompt-Guided Dual Latent Steering (PDLS), a novel, training-free framework built upon Rectified Flow models for their stable inversion paths. PDLS decomposes the inversion process into two complementary streams: a structural path to preserve source integrity and a semantic path guided by a prompt. We formulate this dual guidance as an optimal control problem and derive a closed-form solution via a Linear Quadratic Regulator (LQR). This controller dynamically steers the generative trajectory at each step, preventing semantic drift while ensuring the preservation of fine detail without costly, per-image optimization. Extensive experiments on FFHQ-1K and ImageNet-1K under various inversion tasks, including Gaussian deblurring, motion deblurring, super-resolution and freeform inpainting, demonstrate that PDLS produces reconstructions that are both more faithful to the original image and better aligned with the semantic information than single-latent baselines.

cs.CV↗

arXiv2025

Check Field Detection Agent (CFD-Agent) using Multimodal Large Language and Vision Language Models

Checks remain a foundational instrument in the financial ecosystem, facilitating substantial transaction volumes across institutions. However, their continued use also renders them a persistent target for fraud, underscoring the importance of robust check fraud detection mechanisms. At the core of such systems lies the accurate identification and localization of critical fields, such as the signature, magnetic ink character recognition (MICR) line, courtesy amount, legal amount, payee, and payer, which are essential for subsequent verification against reference checks belonging to the same customer. This field-level detection is traditionally dependent on object detection models trained on large, diverse, and meticulously labeled datasets, a resource that is scarce due to proprietary and privacy concerns. In this paper, we introduce a novel, training-free framework for automated check field detection, leveraging the power of a vision language model (VLM) in conjunction with a multimodal large language model (MLLM). Our approach enables zero-shot detection of check components, significantly lowering the barrier to deployment in real-world financial settings. Quantitative evaluation of our model on a hand-curated dataset of 110 checks spanning multiple formats and layouts demonstrates strong performance and generalization capability. Furthermore, this framework can serve as a bootstrap mechanism for generating high-quality labeled datasets, enabling the development of specialized real-time object detection models tailored to institutional needs.

cs.CV↗

arXiv2025

Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges

Content generation modeling has emerged as a promising direction in computational pathology, offering capabilities such as data-efficient learning, synthetic data augmentation, and task-oriented generation across diverse diagnostic tasks. This review provides a comprehensive synthesis of recent progress in the field, organized into four key domains: image generation, text generation, molecular profile-morphology generation, and other specialized generation applications. By analyzing over 150 representative studies, we trace the evolution of content generation architectures -- from early generative adversarial networks to recent advances in diffusion models and generative vision-language models. We further examine the datasets and evaluation protocols commonly used in this domain and highlight ongoing limitations, including challenges in generating high-fidelity whole slide images, clinical interpretability, and concerns related to the ethical and legal implications of synthetic data. The review concludes with a discussion of open challenges and prospective research directions, with an emphasis on developing integrated and clinically deployable generation systems. This work aims to provide a foundational reference for researchers and practitioners developing content generation models in computational pathology.

eess.IV↗

arXiv2025

VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents

Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create immersive user experiences through consistent persona adoption. However, current RPCA research faces dual limitations. First, existing work predominantly focuses on the textual modality, entirely overlooking critical paralinguistic features including intonation, prosody, and rhythm in speech, which are essential for conveying character emotions and shaping vivid identities. Second, the speech-based role-playing domain suffers from a long-standing lack of standardized evaluation benchmarks. Most current spoken dialogue datasets target only fundamental capability assessments, featuring thinly sketched or ill-defined character profiles. Consequently, they fail to effectively quantify model performance on core competencies like long-term persona consistency. To address this critical gap, we introduce VoxRole, the first comprehensive benchmark specifically designed for the evaluation of speech-based RPCAs. The benchmark comprises 13335 multi-turn dialogues, totaling 65.6 hours of speech from 1228 unique characters across 261 movies. To construct this resource, we propose a novel two-stage automated pipeline that first aligns movie audio with scripts and subsequently employs an LLM to systematically build multi-dimensional profiles for each character. Leveraging VoxRole, we conduct a multi-dimensional evaluation of contemporary spoken dialogue models, revealing crucial insights into their respective strengths and limitations in maintaining persona consistency.

cs.CL↗

arXiv2025

Growing Trees with an Agent: Accelerating RRTs with Learned, Multi-Step Episodic Exploration

Classical sampling-based motion planners like the RRTs suffer from inefficiencies, particularly in cluttered or high-dimensional spaces, due to their reliance on undirected, random sampling. This paper introduces the Episodic RRT, a novel hybrid planning framework that replaces the primitive of a random point with a learned, multi-step "exploratory episode" generated by a Deep Reinforcement Learning agent. By making the DRL agent the engine of exploration, ERRT transforms the search process from a diffuse, volumetric expansion into a directed, branch-like growth. This paradigm shift yields key advantages: it counters the curse of dimensionality with focused exploration, minimizes expensive collision checks by proactively proposing locally valid paths, and improves connectivity by generating inherently connected path segments. We demonstrate through extensive empirical evaluation across 2D, 3D, and 6D environments that ERRT and its variants consistently and significantly outperform their classical counterparts without any GPU acceleration. In a challenging 6D robotic arm scenario, ERRT achieves a 98% success rate compared to 19% for RRT, is up to 107x faster, reduces collision checks by over 99.6%, and finds initial paths that are nearly 50% shorter. Furthermore, its asymptotically optimal variant, ERRT*, demonstrates vastly superior anytime performance, refining solutions to near-optimality up to 29x faster than standard RRT* in 3D environments. Code: https://xinyuwuu.github.io/Episodic_RRT/.

cs.RO↗

arXiv2025

Subpixel Edge Localization Based on Converted Intensity Summation under Stable Edge Region

To satisfy the rigorous requirements of precise edge detection in critical high-accuracy measurements, this article proposes a series of efficient approaches for localizing subpixel edge. In contrast to the fitting based methods, which consider pixel intensity as a sample value derived from a specific model. We take an innovative perspective by assuming that the intensity at the pixel level can be interpreted as a local integral mapping in the intensity model for subpixel localization. Consequently, we propose a straightforward subpixel edge localization method called Converted Intensity Summation (CIS). To address the limited robustness associated with focusing solely on the localization of individual edge points, a Stable Edge Region (SER) based algorithm is presented to alleviate local interference near edges. Given the observation that the consistency of edge statistics exists in the local region, the algorithm seeks correlated stable regions in the vicinity of edges to facilitate the acquisition of robust parameters and achieve higher precision positioning. In addition, an edge complement method based on extension-adjustment is also introduced to rectify the irregular edges through the efficient migration of SERs. A large number of experiments are conducted on both synthetic and real image datasets which cover common edge patterns as well as various real scenarios such as industrial PCB images, remote sensing and medical images. It is verified that CIS can achieve higher accuracy than the state-of-the-art method, while requiring less execution time. Moreover, by integrating SER into CIS, the proposed algorithm demonstrates excellent performance in further improving the anti-interference capability and positioning accuracy.

cs.CV↗

arXiv2025

Conversations With The Stressed Body: Facilitating Stress Self-Disclosure Among Adolescent Girls Through An Embodied Approach

Adolescent girls face significant mental health challenges during their transition to adulthood, often experiencing heightened stress from various sources. While various interactive technologies for self-disclosure had been explored to support stress relief, little is known about how to encourage stress-related self-disclosure through an embodied approach. This study presents a co-design workshop centred on Embodied Probes, a series of artefacts and activities incorporating embodied methods and technologies. During the workshop, nine participants aged 15 to 18 engaged with their bodies, expressed bodily sensations through tangible means, and designed embodied prototypes tailored to their personal needs for stress perception and relief. The workshop revealed insights into somatic symptoms, sources, and coping strategies for stress among adolescent girls, as well as how embodied methods can support their stress self-disclosure. This paper contributes to the HCI community by offering design implications on leveraging embodied technologies to support self-disclosure for young women's mental well-being.

cs.HC↗

arXiv2025

Multi-Modal Foundation Models for Computational Pathology: A Survey

Foundation models have emerged as a powerful paradigm in computational pathology (CPath), enabling scalable and generalizable analysis of histopathological images. While early developments centered on uni-modal models trained solely on visual data, recent advances have highlighted the promise of multi-modal foundation models that integrate heterogeneous data sources such as textual reports, structured domain knowledge, and molecular profiles. In this survey, we provide a comprehensive and up-to-date review of multi-modal foundation models in CPath, with a particular focus on models built upon hematoxylin and eosin (H&E) stained whole slide images (WSIs) and tile-level representations. We categorize 32 state-of-the-art multi-modal foundation models into three major paradigms: vision-language, vision-knowledge graph, and vision-gene expression. We further divide vision-language models into non-LLM-based and LLM-based approaches. Additionally, we analyze 28 available multi-modal datasets tailored for pathology, grouped into image-text pairs, instruction datasets, and image-other modality pairs. Our survey also presents a taxonomy of downstream tasks, highlights training and evaluation strategies, and identifies key challenges and future directions. We aim for this survey to serve as a valuable resource for researchers and practitioners working at the intersection of pathology and AI.

cs.CV↗