arXiv subjects

Yuhao Wang

Publications and source records attributed to Yuhao Wang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Beyond a Single Queue: Multi-Level-Multi-Queue as an Effective Design for SSSP problems on GPUs

As one of the most fundamental problems in graph processing, the Single-Source Shortest Path (SSSP) problem plays a critical role in numerous application scenarios. However, existing GPU-based solutions remain inefficient, as they typically rely on a single, fixed queue design that incurs severe synchronization overhead, high memory latency, and poor adaptivity to diverse inputs. To address these inefficiencies, we propose MultiLevelMultiQueue (MLMQ), a novel data structure that distributes multiple queues across the GPU's multi-level parallelism and memory hierarchy. To realize MLMQ, we introduce a cache-like collaboration mechanism for efficient inter-queue coordination, and develop a modular queue design based on unified Read and Write primitives. Within this framework, we expand the optimization space by designing a set of GPU-friendly queues, composing them across multiple levels, and further providing an input-adaptive MLMQ configuration scheme. Our MLMQ design achieves average speedups of 1.87x to 17.13x over state-of-the-art implementations. Our code is open-sourced at https://github.com/Leo9660/MLMQ.git.

cs.DS↗

arXiv2026

VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and introducing exposure bias. In this paper, we investigate Masked Diffusion Modeling~(MDM) as a non-autoregressive paradigm for speech LLMs and introduce VocalNet-MDM. To adapt MDM for streaming speech interaction, we address two critical challenges: training-inference mismatch and iterative overhead. We propose Hierarchical Block-wise Masking to align training objectives with the progressive masked states encountered during block diffusion decoding, and Iterative Self-Distillation to compress multi-step refinement into fewer steps for low-latency inference. Trained on a limited scale of only 6K hours of speech data, VocalNet-MDM achieves a 3.7$\times$--10$\times$ decoding speedup and reduces first-chunk latency by 34\% compared to AR baselines. It maintains competitive recognition accuracy while achieving state-of-the-art text quality and speech naturalness, demonstrating that MDM is a promising and scalable alternative for low-latency, efficient speech LLMs.

cs.CL↗

arXiv2026

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots

Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and effective defenses remain lacking. In this paper, we propose MemPot, the first theoretically verified defense framework against memory extraction attacks by injecting optimized honeypots into the memory. Through a two-stage optimization process, MemPot generates trap documents that maximize the retrieval probability for attackers while remaining inconspicuous to benign users. We model the detection process as Wald's Sequential Probability Ratio Test (SPRT) and theoretically prove that MemPot achieves a lower average number of sampling rounds compared to optimal static detectors. Empirically, MemPot significantly outperforms state-of-the-art baselines, achieving a 50% improvement in detection AUROC and an 80% increase in True Positive Rate under low False Positive Rate constraints. Furthermore, our experiments confirm that MemPot incurs zero additional online inference latency and preserves the agent's utility on standard tasks, verifying its superiority in safety, harmlessness, and efficiency.

cs.CR↗

arXiv2026

Engineering of Orbital Hybridization: An Exotic Strategy to Manipulate Orbital Current

Current-induced spin-orbit torque (SOT) plays a crucial role in the next-generation spin-orbitronics. Enhancing its efficiency is both fundamentally and practically interesting and remains a challenge to date. Recently, orbital counterparts of spin effects that do not rely on the spin-orbit coupling (SOC) have been found as an alternative mechanism to realize it. This work highlights the engineering of copper oxidation states for manipulating the orbital current and its torque in the CuO$_x$-based heterostructures. The orbital hybridization and thus the orbital-Rashba-Edelstein effect at the CuO$_x$/Cu interfaces are significantly enhanced by increasing the copper oxidation state, yielding a torque efficiency that is almost ten times larger than the conventional heavy metals. The Cu$_4$O$_3$/Cu interface, rather than the widely accepted CuO/Cu interface, is revealed to account for the enhanced SOT performance in the CuO$_x$-based heterostructures. In addition, the torque efficiency can be alternatively switched between high and low thresholds through the redox reaction. The current results establish an exotic and robust strategy for engineering the orbital current and SOT for spin-orbitronics, which applies to other weak-SOC materials.

cond-mat.mtrl-sci↗

arXiv2026

Rerandomization for quantile treatment effects

Although complete randomization is widely regarded as the gold standard for causal inference, covariate imbalance can still arise by chance in finite samples. Rerandomization has emerged as an effective tool to improve covariate balance across treatment groups and enhance the precision of causal effect estimation. While existing work focuses on average treatment effects, quantile treatment effects (QTEs) provide a richer characterization of treatment heterogeneity by capturing distributional shifts in outcomes, which is crucial for policy evaluation and equity-oriented research. In this article, we establish the asymptotic properties of the QTE estimator under rerandomization within a finite-population framework, without imposing any distributional or modeling assumptions on the covariates or outcomes.The estimator exhibits a non-Gaussian asymptotic distribution, represented as a linear combination of Gaussian and truncated Gaussian random variables. To facilitate inference, we propose a conservative variance estimator and construct corresponding confidence interval. Our theoretical analysis demonstrates that rerandomization improves efficiency over complete randomization under mild regularity conditions. Simulation studies further support the theoretical findings and illustrate the practical advantages of rerandomization for QTE estimation.

stat.ME↗

arXiv2026

VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models

Speech large language models (SpeechLLMs) have extended human-machine interactions from the text modality to the dynamic speech domain. Spoken dialogues convey diverse information, including semantic concepts, acoustic variations, paralanguage cues, and environmental context. However, existing evaluations of speech interaction models lack instances mimicking real scenarios and predominantly focus on the performance of distinct aspects, lacking a comprehensive comparison of critical capabilities between current routines. To address this gap, we propose VocalBench to assess the speech conversational abilities, comprising around 24k carefully curated instances of both English and Mandarin across four key dimensions - semantic quality, acoustic performance, conversational abilities, and robustness, covering 14 user-oriented characters. Experiments on 27 mainstream models reveal the common challenges for current routes, and highlight the need for new insights into next-generation speech interactive systems.

cs.CL↗

arXiv2026

SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances

Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint variation and inevitable appearance noise. To address these issues, we propose a Scale-Adaptive framework with Shape Priors for VPReID, named SAS-VPReID. The framework is built upon three complementary modules. First, we deploy a Memory-Enhanced Visual Backbone (MEVB) to extract discriminative feature representations, which leverages the CLIP vision encoder and multi-proxy memory. Second, we propose a Multi-Granularity Temporal Modeling (MGTM) to construct sequences at multiple temporal granularities and adaptively emphasize motion cues across scales. Third, we incorporate Prior-Regularized Shape Dynamics (PRSD) to capture body structure dynamics. With these modules, our framework can obtain more discriminative feature representations. Experiments on the VReID-XFD benchmark demonstrate the effectiveness of each module and our final framework ranks the first on the VReID-XFD challenge leaderboard. The source code is available at https://github.com/YangQiWei3/SAS-VPReID.

cs.CV↗

arXiv2026

VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results

Person re-identification (ReID) across aerial and ground views at extreme far distances introduces a distinct operating regime where severe resolution degradation, extreme viewpoint changes, unstable motion cues, and clothing variation jointly undermine the appearance-based assumptions of existing ReID systems. To study this regime, we introduce VReID-XFD, a video-based benchmark and community challenge for extreme far-distance (XFD) aerial-to-ground person re-identification. VReID-XFD is derived from the DetReIDX dataset and comprises 371 identities, 11,288 tracklets, and 11.75 million frames, captured across altitudes from 5.8 m to 120 m, viewing angles from oblique (30 degrees) to nadir (90 degrees), and horizontal distances up to 120 m. The benchmark supports aerial-to-aerial, aerial-to-ground, and ground-to-aerial evaluation under strict identity-disjoint splits, with rich physical metadata. The VReID-XFD-25 Challenge attracted 10 teams with hundreds of submissions. Systematic analysis reveals monotonic performance degradation with altitude and distance, a universal disadvantage of nadir views, and a trade-off between peak performance and robustness. Even the best-performing SAS-PReID method achieves only 43.93 percent mAP in the aerial-to-ground setting. The dataset, annotations, and official evaluation protocols are publicly available at https://www.it.ubi.pt/DetReIDX/ .

cs.CV↗

arXiv2026

A multivariate extension of Azadkia-Chatterjee's rank coefficient

The Azadkia-Chatterjee coefficient is a rank-based measure of dependence between a random variable $Y \in \mathbb{R}$ and a random vector ${\boldsymbol Z} \in \mathbb{R}^{d_Z}$. In this paper, we propose a multivariate extension that measures the dependence between random vectors ${\boldsymbol Y} \in \mathbb{R}^{d_Y}$ and ${\boldsymbol Z} \in \mathbb{R}^{d_Z}$, based on $n$ i.i.d. samples. The proposed coefficient converges almost surely to a limit with the following properties: i) it lies in $[0, 1]$; ii) it is equal to zero if and only if ${\boldsymbol Y}$ and ${\boldsymbol Z}$ are independent; and iii) it is equal to one if and only if ${\boldsymbol Y}$ is almost surely a function of ${\boldsymbol Z}$. Remarkably, the only assumption required by this convergence is that ${\boldsymbol Y}$ is not almost surely a constant vector. We further prove that under the same mild condition and after a proper scaling, this coefficient converges in distribution to a standard normal random variable when ${\boldsymbol Y}$ and ${\boldsymbol Z}$ are independent. This asymptotic normality result allows us to construct a Wald-type hypothesis test of independence based on this coefficient. To compute this coefficient, we propose a merge sort based algorithm that runs in $O(n (\log n)^{d_Y})$. Finally, we show that it can be used to measure the conditional dependence between ${\boldsymbol Y}$ and ${\boldsymbol Z}$ conditional on a third random vector ${\boldsymbol X}$, and prove that the measure is monotonic with respect to the deviation from an independence distribution under certain model restrictions.

math.ST↗

arXiv2026

W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search

Large Language Models (LLMs) demonstrate impressive capabilities, yet their outputs often suffer from misalignment with human preferences due to the inadequacy of weak supervision and a lack of fine-grained control. Training-time alignment methods like Reinforcement Learning from Human Feedback (RLHF) face prohibitive costs in expert supervision and inherent scalability limitations, offering limited dynamic control during inference. Consequently, there is an urgent need for scalable and adaptable alignment mechanisms. To address this, we propose W2S-AlignTree, a pioneering plug-and-play inference-time alignment framework that synergistically combines Monte Carlo Tree Search (MCTS) with the Weak-to-Strong Generalization paradigm for the first time. W2S-AlignTree formulates LLM alignment as an optimal heuristic search problem within a generative search tree. By leveraging weak model's real-time, step-level signals as alignment proxies and introducing an Entropy-Aware exploration mechanism, W2S-AlignTree enables fine-grained guidance during strong model's generation without modifying its parameters. The approach dynamically balances exploration and exploitation in high-dimensional generation search trees. Experiments across controlled sentiment generation, summarization, and instruction-following show that W2S-AlignTree consistently outperforms strong baselines. Notably, W2S-AlignTree raises the performance of Llama3-8B from 1.89 to 2.19, a relative improvement of 15.9 on the summarization task.

cs.CL↗

arXiv2025

On the physics of nested Markov models: a generalized probabilistic theory perspective

Determining potential probability distributions with a given causal graph is vital for causality studies. To bypass the difficulty in characterizing latent variables in a Bayesian network, the nested Markov model provides an elegant algebraic approach by listing exactly all the equality constraints on the observed variables. However, this algebraically motivated causal model comprises distributions outside Bayesian networks, and its physical interpretation remains vague. In this work, we inspect the nested Markov model through the lens of generalized probabilistic theory, an axiomatic framework to describe general physical theories. We prove that all the equality constraints defining the nested Markov model are valid theory-independently. At the same time, not every distribution within the nested Markov model is implementable, not even via exotic physical theories associated with generalized probability theories (GPTs). To interpret the origin of such a gap, we study three causal models standing between the nested Markov model and the set of all distributions admitting some GPT realization. Each of the successive three models gives a strictly tighter characterization of the physically implementable distribution set; that is, each successive model manifests new types of GPT-inviolable constraints. We further demonstrate each gap through a specially chosen illustrative causal structure. We anticipate our results will enlighten further explorations on the unification of algebraic and physical perspectives of causality.

quant-ph↗

arXiv2025

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation

The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating responses. However, due to differences in pre-training data and objectives, there is an inevitable gap between the documents ranked as relevant by the reranker and those required by the generator to support answering the query. To address this gap, we propose RADIO, a novel and practical preference alignment framework with RAtionale DIstillatiOn. Specifically, we first propose a rationale extraction method that leverages the reasoning capabilities of Large Language Models (LLMs) to extract the rationales necessary for answering the query. Subsequently, a rationale-based alignment process is designed to rerank the documents based on the extracted rationales, and fine-tune the reranker to align the preferences. We conduct extensive experiments on two tasks across three datasets to demonstrate the effectiveness of our approach compared to baseline methods. Our code is released online to ease reproduction.

cs.CL↗

arXiv2025

Infrared and Visible Image Fusion with Language-Driven Loss in CLIP Embedding Space

Infrared-visible image fusion (IVIF) has attracted much attention owing to the highly-complementary properties of the two image modalities. Due to the lack of ground-truth fused images, the fusion output of current deep-learning based methods heavily depends on the loss functions defined mathematically. As it is hard to well mathematically define the fused image without ground truth, the performance of existing fusion methods is limited. In this paper, we propose to use natural language to express the objective of IVIF, which can avoid the explicit mathematical modeling of fusion output in current losses, and make full use of the advantage of language expression to improve the fusion performance. For this purpose, we present a comprehensive language-expressed fusion objective, and encode relevant texts into the multi-modal embedding space using CLIP. A language-driven fusion model is then constructed in the embedding space, by establishing the relationship among the embedded vectors representing the fusion objective and input image modalities. Finally, a language-driven loss is derived to make the actual IVIF aligned with the embedded language-driven fusion model via supervised training. Experiments show that our method can obtain much better fusion results than existing techniques. The code is available at https://github.com/wyhlaowang/LDFusion.

cs.CV↗

arXiv2025

Histomorphology-Guided Prototypical Multi-Instance Learning for Breast Cancer WSI Classification

Histomorphology is crucial in cancer diagnosis. However, existing whole slide image (WSI) classification methods struggle to effectively incorporate histomorphology information, limiting their ability to capture key pathological features. Particularly when the number of instances within a bag is large and their features are complex, it becomes challenging to accurately identify instances decisive for the bag label, making these methods prone to interference from ambiguous instances. To address this limitation, we propose a novel Histomorphology-Guided Prototypical Multi-Instance Learning (HGPMIL) framework that explicitly learns histomorphology-guided prototypical representations by incorporating tumor cellularity, cellular morphology, and tissue architecture. Specifically, our approach consists of three key components: (1) estimating the importance of tumor-related histomorphology information at patch-level based on medical prior knowledge; (2) generating representative prototypes through histomorphology-prototypical clustering; and (3) enabling WSI classification through histomorphology-guided prototypical aggregation. HGPMIL adjusts the decision boundary by incorporating histomorphological importance to reduce instance label uncertainty, thereby reversely optimizing the bag-level boundary. Experimental results demonstrate its effectiveness, achieving high diagnostic accuracy for molecular subtyping, cancer subtyping and survival analysis. The code will be made available at https://github.com/Badgewho/HMDMIL.

cs.CV↗

arXiv2025

Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification

Multi-modal object Re-IDentification (ReID) is devoted to retrieving specific objects through the exploitation of complementary multi-modal image information. Existing methods mainly concentrate on the fusion of multi-modal features, yet neglecting the background interference. Besides, current multi-modal fusion methods often focus on aligning modality pairs but suffer from multi-modal consistency alignment. To address these issues, we propose a novel selective interaction and global-local alignment framework called Signal for multi-modal object ReID. Specifically, we first propose a Selective Interaction Module (SIM) to select important patch tokens with intra-modal and inter-modal information. These important patch tokens engage in the interaction with class tokens, thereby yielding more discriminative features. Then, we propose a Global Alignment Module (GAM) to simultaneously align multi-modal features by minimizing the volume of 3D polyhedra in the gramian space. Meanwhile, we propose a Local Alignment Module (LAM) to align local features in a shift-aware manner. With these modules, our proposed framework could extract more discriminative features for object ReID. Extensive experiments on three multi-modal object ReID benchmarks (i.e., RGBNT201, RGBNT100, MSVR310) validate the effectiveness of our method. The source code is available at https://github.com/010129/Signal.

cs.CV↗

arXiv2025

CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking

RGB-Thermal (RGBT) tracking aims to exploit visible and thermal infrared modalities for robust all-weather object tracking. However, existing RGBT trackers struggle to resolve modality discrepancies, which poses great challenges for robust feature representation. This limitation hinders effective cross-modal information propagation and fusion, which significantly reduces the tracking accuracy. To address this limitation, we propose a novel Contextual Aggregation with Deformable Alignment framework called CADTrack for RGBT Tracking. To be specific, we first deploy the Mamba-based Feature Interaction (MFI) that establishes efficient feature interaction via state space models. This interaction module can operate with linear complexity, reducing computational cost and improving feature discrimination. Then, we propose the Contextual Aggregation Module (CAM) that dynamically activates backbone layers through sparse gating based on the Mixture-of-Experts (MoE). This module can encode complementary contextual information from cross-layer features. Finally, we propose the Deformable Alignment Module (DAM) to integrate deformable sampling and temporal propagation, mitigating spatial misalignment and localization drift. With the above components, our CADTrack achieves robust and accurate tracking in complex scenarios. Extensive experiments on five RGBT tracking benchmarks verify the effectiveness of our proposed method. The source code is released at https://github.com/IdolLab/CADTrack.

cs.CV↗

arXiv2025

A Respiratory Motion Analysis for Guiding Stereotactic Arrhythmia Radiotherapy Motion Management

Stereotactic Arrhythmia Radiotherapy (STAR) treats ventricular tachycardia (VT) but requires internal target volume (ITV) expansions to compensate for cardiorespiratory motion. Current clinical r4DCT imaging methods are limited, and the reconstructed r4DCTs suffer from unmanaged cardiac motion artifacts that affect the quantitative assessment of respiratory motion. A groupwise surface-to-surface deformable image registration (DIR) algorithm, named gCGF, was developed. A novel principal component filtering (PCF) mechanism and a spatial smoothing mechanism were developed and incorporated into gCGF to iteratively register heart contours from an average respiratory-phase CT to ten r4DCT phases while removing random cardiac motion from the cyclic respiratory motion. The performance of the groupwise DIR was quantitatively validated using 8 digital phantoms with simulated cardiac artifacts. An ablation study was conducted to compare gCGF to another comparable state-of-the-art groupwise DIR method. gCGF was applied to r4DCTs of 20 STAR patients to analyze the respiratory motion of the heart. Validation on digital phantoms showed that gCGF achieved a mean target registration error of 0.63+-0.51 mm while successfully achieving phase smoothness and reducing cardiac motion artifacts. Among all STAR patients, the heart's maximum and mean respiratory motion magnitudes ranged from 3.6 to 7.9 mm and 1.0 mm to 2.6 mm. The peak-to-peak motion range was from 6.2 to 14.7 mm. For VT targets, the max and mean motion magnitude ranges were 3.0 to 6.7 mm and 0.8 to 2.9 mm, respectively. The peak-to-peak range was from 4.7 to 11.8 mm. Significant dominance of the first principal component of the motion direction was observed (p = 0).

physics.med-ph↗

arXiv2025

VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context

The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Mandarin is supported by most models to enhance their applicability and reach. However, the scarcity of comprehensive speech-to-speech (S2S) benchmarks in Mandarin contexts impedes systematic evaluation for developers and hinders fair model comparison for users. In this work, we propose VocalBench-zh, an ability-level divided evaluation suite adapted to Mandarin context consisting of 10 well-crafted subsets and over 10K high-quality instances, covering 12 user-oriented characters. The evaluation experiment on 14 mainstream models reveals the common challenges for current routes, and highlights the need for new insights into next-generation speech interactive systems. The evaluation codes and datasets will be available at https://github.com/SJTU-OmniAgent/VocalBench-zh.

cs.CL↗