Searcharxiv⌕ Search

arXiv subjects

Yang Zhou

Publications and source records attributed to Yang Zhou.

At least 145 records · Page 8Linked to original sources
arXiv2026

Experimental Side-Channel-Secure Quantum Key Distribution over 200 km

Quantum key distribution (QKD) enables two remote parties to share encryption keys with information-theoretic security guaranteed by physical laws. Side-channel-secure QKD (SCS-QKD) has attracted considerable attention because it simultaneously removes source and detector side-channel vulnerabilities. Although a recent experiment demonstrated SCS-QKD over 50 km, practical implementation remains challenging due to imperfect vacuum preparation and finite-key constraints under coherent attacks. Here, following the theoretical framework of Jiang et al. [Phys. Rev. Res. 6, 013266 (2024)], we experimentally implement a practical SCS-QKD protocol using an imperfect whole-space source and rigorous finite-key analysis. Benefiting from a stable GHz-level system operating at 1.25 GHz, we extend the transmission distance to 200 km and achieve high secure key rates of 18.31 kbps, 2.55 kbps, and 196.03 bps at 100 km, 150 km, and 200 km, respectively. Our results establish a new distance record for SCS-QKD and demonstrate the feasibility of high-speed, long-distance, and practically secure quantum key distribution.

quant-ph↗
arXiv2026

A Directly Modulated Laser Platform for High-Dimensional Quantum Key Distribution

High-dimensional quantum key distribution (HD-QKD) offers a promising approach to enhance secret key rates beyond conventional binary-encoded QKD, addressing the growing demand for secure data transmission. However, the practical application of most HD-QKD systems has been hindered by their complexity, as they require the preparation and detection of quantum states in large Hilbert spaces. Here, we design and experimentally realize a directly modulated laser platform for HD-QKD. It operates at a repetition rate of 312.5 MHz, yielding a remarkably simple and scalable architecture. Through which, we achieve a record transmission distance of 250 km for HD-QKD, demonstrating its feasibility for long-distance quantum communication. Furthermore, we witness that the four-dimensional states outperform their two-dimensional counterpart in secret key rate, highlighting the practical advantage of high-dimensional encoding. This simple and scalable approach shows strong potential for chip-scale integration.

quant-ph↗
arXiv2026

Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition

Deep learning methods for Visual Place Recognition (VPR) have advanced significantly, largely driven by large-scale datasets. However, most existing approaches are trained on a single dataset, which can introduce dataset-specific inductive biases and limit model generalization. While multi-dataset joint training offers a promising solution for developing universal VPR models, divergences among training datasets can saturate the limited information capacity in feature aggregation layers, leading to suboptimal performance. To address these challenges, we propose Query-based Adaptive Aggregation (QAA), a novel feature aggregation technique that leverages learned queries as reference codebooks to effectively enhance information capacity without significant computational or parameter complexity. We show that computing the Cross-query Similarity (CS) between query-level image features and reference codebooks provides a simple yet effective way to generate robust descriptors. Our results demonstrate that QAA outperforms state-of-the-art models, achieving balanced generalization across diverse datasets while maintaining peak performance comparable to dataset-specific models. Ablation studies further explore QAA's mechanisms and scalability. Visualizations reveal that the learned queries exhibit diverse attention patterns across datasets. Project page: http://xjh19971.github.io/QAA.

cs.CV↗
arXiv2026

Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss

Linear autoencoders (LAEs) have gained increasing popularity in recommender systems due to their simplicity and strong empirical performance. Most LAE models, including the Emphasized Denoising Linear Autoencoder (EDLAE) introduced by (Steck, 2020), use quadratic loss during training. However, the original EDLAE only provides closed-form solutions for the hyperparameter choice $b = 0$, which limits its capacity. In this work, we generalize EDLAE objective into a Decoupled Expected Quadratic Loss (DEQL). We show that DEQL simplifies the process of deriving EDLAE solutions and reveals solutions in a broader hyperparameter range $b > 0$, which were not derived in Steck's original paper. Additionally, we propose an efficient algorithm based on Miller's matrix inverse theorem to ensure the computational tractability for the $b > 0$ case. Empirical results on benchmark datasets show that the $b > 0$ solutions provided by DEQL outperform the $b = 0$ EDLAE baseline, demonstrating that DEQL expands the solution space and enables the discovery of models with better testing performance.

cs.LG↗
arXiv2026

Real-Time Glottis Detection Framework via Spatial-decoupled Feature Learning for Nasal Transnasal Intubation

Nasotracheal intubation (NTI) is a vital procedure in emergency airway management, where rapid and accurate glottis detection is essential to ensure patient safety. However, existing machine assisted visual detection systems often rely on high performance computational resources and suffer from significant inference delays, which limits their applicability in time critical and resource constrained scenarios. To overcome these limitations, we propose Mobile GlottisNet, a lightweight and efficient glottis detection framework designed for real time inference on embedded and edge devices. The model incorporates structural awareness and spatial alignment mechanisms, enabling robust glottis localization under complex anatomical and visual conditions. We implement a hierarchical dynamic thresholding strategy to enhance sample assignment, and introduce an adaptive feature decoupling module based on deformable convolution to support dynamic spatial reconstruction. A cross layer dynamic weighting scheme further facilitates the fusion of semantic and detail features across multiple scales. Experimental results demonstrate that the model, with a size of only 5MB on both our PID dataset and Clinical datasets, achieves inference speeds of over 62 FPS on devices and 33 FPS on edge platforms, showing great potential in the application of emergency NTI.

cs.CV↗
arXiv2026

$π^3$: Permutation-Equivariant Visual Geometry Learning

We introduce $π^3$, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Previous methods often anchor their reconstructions to a designated viewpoint, an inductive bias that can lead to instability and failures if the reference is suboptimal. In contrast, $π^3$ employs a fully permutation-equivariant architecture to predict affine-invariant camera poses and scale-invariant local point maps without any reference frames. This design not only makes our model inherently robust to input ordering, but also leads to higher accuracy and performance. These advantages enable our simple and bias-free approach to achieve state-of-the-art performance on a wide range of tasks, including camera pose estimation, monocular/video depth estimation, and dense point map reconstruction. Code and models are available at https://github.com/yyfz/Pi3.

cs.CV↗
arXiv2026

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving, this vision gives rise to driving world models: generative simulators that imagine ego and agent futures, enabling scalable simulation, safe testing of corner cases, and rich synthetic data generation. Yet, despite fast-growing research activity, the field lacks a rigorous benchmark to measure progress and guide priorities. Existing evaluations remain limited: generic video metrics overlook safety-critical imaging factors; trajectory plausibility is rarely quantified; temporal and agent-level consistency is neglected; and controllability with respect to ego conditioning is ignored. Moreover, current datasets fail to cover the diversity of conditions required for real-world deployment. To address these gaps, we present DrivingGen, the first comprehensive benchmark for generative driving world models. DrivingGen combines a diverse evaluation dataset curated from both driving datasets and internet-scale video sources, spanning varied weather, time of day, geographic regions, and complex maneuvers, with a suite of new metrics that jointly assess visual realism, trajectory plausibility, temporal coherence, and controllability. Benchmarking 14 state-of-the-art models reveals clear trade-offs: general models look better but break physics, while driving-specific ones capture motion realistically but lag in visual quality. DrivingGen offers a unified evaluation framework to foster reliable, controllable, and deployable driving world models, enabling scalable simulation, planning, and data-driven decision-making.

cs.CV↗
arXiv2026

Explicit Hecke eigenform product identities for Hilbert modular forms

Let $F$ be a totally real number field, and $g,f,h$ be Hilbert modular forms over $F$ that are Hecke eigenforms satisfying $g=f\cdot h$. We characterize such product identities among all real quadratic fields of narrow class number one, proving they occur only for $F=\mathbb Q(\sqrt{5})$, with precisely two such identities. We also shed some light on the general totally real case by showing that no such identity exists when both $f$ and $h$ are Eisenstein series of distinct weights.

math.NT↗
arXiv2026

Learning to Select Like Humans: Explainable Active Learning for Medical Imaging

Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for the annotation purpose, but traditional methods solely rely on predictive uncertainty while ignoring whether models learn from clinically meaningful features a critical requirement for clinical deployment. We propose an explainability-guided active learning framework that integrates spatial attention alignment into a sample acquisition process. Our approach advocates for a dual-criterion selection strategy combining: (i) classification uncertainty to identify informative examples, and (ii) attention misalignment with radiologist-defined regions-of-interest (ROIs) to target samples where the model focuses on incorrect features. By measuring misalignment between Grad-CAM attention maps and expert annotations using Dice similarity, our acquisition function judiciously identifies samples that enhance both predictive performance and spatial interpretability. We evaluate the framework using three expert-annotated medical imaging datasets, namely, BraTS (MRI brain tumors), VinDr-CXR (chest X-rays), and SIIM-COVID-19 (chest X-rays). Using only 570 strategically selected samples, our explainability-guided approach consistently outperforms random sampling across all the datasets, achieving 77.22% accuracy on BraTS, 52.37% on VinDr-CXR, and 52.66% on SIIM-COVID. Grad-CAM visualizations confirm that the models trained by our dual-criterion selection focus on diagnostically relevant regions, demonstrating that incorporating explanation guidance into sample acquisition yields superior data efficiency while maintaining clinical interpretability.

eess.IV↗
arXiv2026

InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions

Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence.

cs.CV↗
arXiv2026

UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios

Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing. However, current methods have fundamental drawbacks: mask-based approaches suffer from local color discrepancies, while mask-free methods struggle with global background texture misalignment. Furthermore, most methods struggle with diverse real-world scenarios such as stylized avatars, face occlusion, and extreme lighting conditions. In this paper, we propose UniSync, a unified framework designed for achieving high-fidelity lip synchronization in diverse scenarios. Specifically, UniSync uses a mask-free pose-anchored training strategy to keep head motion and eliminate synthesis color artifacts, while employing mask-based blending consistent inference to ensure structural precision and smooth blending. Notably, fine-tuning on compact but diverse videos empowers our model with exceptional domain adaptability, handling complex corner cases effectively. We also introduce the RealWorld-LipSync benchmark to evaluate models under real-world demands, which covers diverse application scenarios including both human faces and stylized avatars. Extensive experiments demonstrate that UniSync significantly outperforms state-of-the-art methods, advancing the field towards truly generalizable and production-ready lip synchronization.

cs.CV↗
arXiv2026

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

Recent advances have showcased the extraordinary capabilities of Large Language Model (LLM) agents in tackling web-based information-seeking tasks. However, existing efforts mainly focus on single-fact retrieval and rely on outcome-only verification, thereby limiting their scalability in realistic knowledge-intensive scenarios that involve long-horizon web tasks requiring large-scale retrieval and synthesis of information from diverse sources. In this work, we introduce VeriWeb, a novel verifiable long-chain web benchmark designed to facilitate the evaluation and development of web agents within realistic web environments. Our benchmark emphasizes two critical dimensions: (1) long-chain complexity, encompassing both breadth- and depth-oriented search tasks to assess how effectively web agents ensure comprehensive information coverage and consistent context tracking in multi-hop reasoning; and (2) subtask-level verifiability, where tasks are decomposed into a sequence of interdependent verifiable subtasks. This structure enables diverse exploration strategies within each subtask, while ensuring that each subtask-level answer remains unchanged and verifiable. The benchmark consists of 302 tasks across five real-world domains, each with a complete trajectory demonstration, annotated by human experts. Extensive experiments on VeriWeb using various agents powered by different foundation models reveal significant performance gaps in handling long-horizon web tasks, highlighting the need for more powerful agentic information-seeking capabilities.

cs.HC↗
arXiv2026

Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting

Due to the real-time rendering performance, 3D Gaussian Splatting (3DGS) has emerged as the leading method for radiance field reconstruction. However, its reliance on spherical harmonics for color encoding inherently limits its ability to separate diffuse and specular components, making it challenging to accurately represent complex reflections. To address this, we propose a novel enhanced Gaussian kernel that explicitly models specular effects through view-dependent opacity. Meanwhile, we introduce an error-driven compensation strategy to improve rendering quality in existing 3DGS scenes. Our method begins with 2D Gaussian initialization and then adaptively inserts and optimizes enhanced Gaussian kernels, ultimately producing an augmented radiance field. Experiments demonstrate that our method not only surpasses state-of-the-art NeRF methods in rendering performance but also achieves greater parameter efficiency. Project page at: https://xiaoxinyyx.github.io/augs.

cs.CV↗
arXiv2026

Learning from geometry-aware near misses to real-time COR: A corridor-wide grouped random parameters GEV framework

Real-time corridor-wide crash-occurrence risk (COR) prediction is challenging because existing near-miss extreme value theory (EVT) models often oversimplify collision geometry, neglect vehicle-infrastructure (V-I) interactions, and inadequately account for spatial heterogeneity in traffic and roadway conditions. This study develops a geometry-aware two-dimensional time-to-collision (2D-TTC) near-miss extraction framework and integrates it with a hierarchical Bayesian grouped random parameter unified generalized extreme value model (HBSGRP-UGEV) to estimate short-term COR in urban corridors. The proposed framework builds on prior grouped EVT formulations while explicitly accommodating both vehicle-vehicle (V-V) and vehicle-infrastructure (V-I) near-miss processes within a unified corridor-wide modeling structure. High-resolution trajectories from the Argoverse-2 dataset were analyzed across 28 sites along Miami's Biscayne Boulevard to extract extreme near-miss events. The model incorporates vehicle dynamics and roadway features as covariates, with partial pooling across segments and intersections to capture corridor-wide heterogeneity. Results indicate that the HBSGRP-UGEV framework outperforms the fixed-parameter HBSFP-UGEV model, reducing the deviance information criterion (DIC) by up to 7.5 percent for V-V interactions and 3.1 percent for V-I interactions. Predictive validation using receiver operating characteristic area under the curve (ROC-AUC) demonstrates strong classification performance, with values of 0.89 for V-V segments, 0.82 for V-V intersections, 0.79 for V-I segments, and 0.75 for V-I intersections.

stat.AP↗
arXiv2026

A fluctuating lattice Boltzmann formulation based on orthogonal central moments

Thermal fluctuations play a central role in fluid dynamics at mesoscopic scales and must be incorporated into numerical schemes in a manner consistent with statistical mechanics. In this work, we develop a fluctuating lattice Boltzmann formulation based on an orthogonal central-moments-based representation. Stochastic forcing is introduced directly in the space of central moments (CMs) and consistently paired with mode-dependent relaxation, yielding a discrete kinetic model that satisfies the fluctuation-dissipation theorem exactly at the lattice level. Owing to the orthogonality of the basis, the equilibrium covariance matrix of the central moments is diagonal, and each non-conserved mode can be interpreted as an independent discrete Ornstein-Uhlenbeck process with variance fixed by equilibrium thermodynamics. The resulting formulation guarantees exact equipartition of kinetic energy at equilibrium, preserves Galilean invariance, and retains the enhanced numerical stability characteristic of CMs-based collision operators. Explicit fluctuating schemes are constructed for the D2Q9 and D3Q27 lattices. The extension to reduced-velocity discretisation is discussed too. A comprehensive set of numerical tests verifies correct thermalisation, isotropy of equilibrium statistics, and the expected scaling of velocity fluctuations with thermal energy, density, and relaxation time. In contrast to fluctuating BGK formulations, the present method remains stable and well posed in the over-relaxation regime, including in the immediate vicinity of the stability limit. These results demonstrate that CMs-based lattice Boltzmann methods provide a natural and robust framework for fluctuating hydrodynamics, in which dissipation, noise, and kinetic mode structure are consistently aligned at the discrete level.

physics.flu-dyn↗
arXiv2026

Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection

Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD is restricted to coarse category-level semantics, while RSVG is structurally limited to single-target localization. These limitations prevent existing methods from simultaneously supporting rich semantic understanding and multi-target detection. To address this, we propose OTA-Det, the first unified framework that bridges both paradigms into a cohesive architecture. Specifically, we introduce a task reformulation strategy that unifies task objectives and supervision mechanisms, enabling joint training across datasets from both paradigms with dense supervision signals. Furthermore, we propose a dense semantic alignment strategy that establishes explicit correspondence at multiple granularities, from holistic expressions to individual attributes, enabling fine-grained semantic understanding. To ensure real-time efficiency, OTA-Det builds upon the RT-DETR architecture, extending it from closed-set detection to open-text detection by introducing several high efficient modules, achieving state-of-the-art performance on six benchmarks spanning both OVAD and RSVG tasks while maintaining real-time inference at 34 FPS.

cs.CV↗
arXiv2026

LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery

Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and whose explanations do not transfer across domains. In this study, we introduce LUCID (Learning Unified vision-language sparse Codes for Interpretable concept Discovery), a unified vision-language sparse autoencoder that learns a shared latent dictionary for image patch and text token representations, while reserving private capacity for modality-specific details. We achieve feature alignment by coupling the shared codes with a learned optimal transport matching objective without the need of labeling. LUCID yields interpretable shared features that support patch-level grounding, establish cross-modal neuron correspondence, and enhance robustness against the concept clustering problem in similarity-based evaluation. Leveraging the alignment properties, we develop an automated dictionary interpretation pipeline based on term clustering without manual observations. Our analysis reveals that LUCID's shared features capture diverse semantic categories beyond objects, including actions, attributes, and abstract concepts, demonstrating a comprehensive approach to interpretable multimodal representations.

cs.CV↗
arXiv2026

Stability conditions in the mathematical Gauged Linear Sigma Model

The theory of Mixed-Spin-P (MSP) fields was introduced by Chang-Li-Li-Liu for the quintic threefold, aiming at studying its higher-genus Gromov-Witten invariants. Chang-Guo-Li has successfully applied it to prove conjectures including the BCOV Feynman rule, Yamaguchi-Yau's polynomiality conjecture and the Holomorphic Anomaly Equation. Meanwhile, Fan-Jarvis-Ruan introduced a mathematical theory of Gauged Linear Sigma Model (GLSM), associating a counting theory to a GIT quotient with a super-potential, under suitable assumptions. This paper provides a common generalization of both works, by introducing new stability conditions in the mathematical GLSM. We show that our stability condition guarantees the separatedness and properness of the cosection degeneracy locus in the moduli. It generalizes the MSP fields construction to more general GIT quotients, including Calabi-Yau global complete intersections in toric varieties. This hopefully provides a geometric platform to effectively compute their higher-genus Gromov-Witten invariants.

math.AG↗