arXiv subjects

Long Xu

Publications and source records attributed to Long Xu.

At least 19 recordsLinked to original sources

arXiv2026

GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning

Robot manipulation foundation models require scalable evaluation and data generation across diverse scenarios, with simulation providing an environment for both. Automated scene generation offers a promising path, yet prior work has largely emphasized coarse-grained scene layouts rather than fine-grained functional object compositions. Motivated by this gap, we present GIF, an agentic Generation framework for Interactive and Functional object compositions. In this framework, we recast this problem as disentangled reconstruction followed by relative pose recovery. CoGen produces instance-disentangled meshes with coarse initial poses leveraging complementary strengths of 2D and 3D generative models. GPRM refines the relative pose under joint geometric and physical guidance, and a VLM verifier selects the candidate that best matches the structured specification. We further construct a benchmark spanning eight representative contact-geometry classes and compare with state-of-the-art generators; GIF improves both asset quality and relation matching, while reducing collision rate to below 1%. Finally, we synthesize data for policy learning, revealing diversity scaling in both simulation and real-world deployment.

cs.RO↗

arXiv2026

The 1st AI Children Challenge

The First AI Children Challenge aims to advance real-world applications of computer vision and AI in child healthcare, child education, and pediatrics. The 2026 CV4CHL edition featured the first track in this domain: Children Gait Visual Analysis. The main goal of Children Gait Visual Analysis is the fine-grained analysis of children's gait behaviors from keypoint sequences. This is still a big challenge for human action recognition. Experienced medical doctors can distinguish these subtle nuances, but none of the people test AI models in this domain. To bridge this gap, we introduce thousands of 2D children keypoint sequences walking around videos across various age groups of children (3-16 years old). There is a significant opportunity for batch analysis of these videos to provide clinically relevant insights into medical diagnosis. The Challenge will be launched with two problem tracks: Edinburgh Visual Gait Score (EVGS) Scoring and Classification of Gait Patterns in Bilateral Spastic Cerebral Palsy. Each track is chosen in consultation with board-certified pediatricians based on the value of potential solutions. With the first available dataset for such tasks and ground truth for each track, the challenge enabled participants to evaluate their solutions. Final rankings will be revealed after the competition concludes, fostering reproducibility and mitigating overfitting.

cs.CV↗

arXiv2026

MORE: A Multilingual Document Parsing Benchmark and Evaluation

Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an evaluation blind spot concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introduce MORE, a large-scale benchmark designed for multilingual document parsing evaluation. MORE distinguishes itself through three key dimensions: (1) Unprecedented Scale: It covers 149 languages, making it the most linguistically diverse benchmark to date; (2) Structural Complexity: Unlike previous works, it extends evaluation beyond plain text to include structural elements such as code blocks, tables, and catalogs; and (3) Data Authenticity: All samples are curated from real-world documents via a model-assisted, human-refined annotation pipeline. We evaluate state-of-the-art models using MORE, establishing new performance baselines for long-tail languages and validating the benchmark's effectiveness in diagnosing model capabilities in realistic, diverse scenarios. The MORE dataset will be available at https://github.com/zimoqingfeng/MORE.

cs.CV↗

arXiv2026

Direct imaging of enantiomer-specific orientation dynamics in unidirectionally rotating chiral molecules

Selectively controlling the dynamics of molecular enantiomers underlies advances across chemistry, biology, and physics, yet direct imaging of enantiomer-specific motion has so far remained elusive. Here, we image ultrafast enantioselective orientation dynamics in isolated chiral molecules. Unidirectional coherent rotation induced by a femtosecond laser-pulse pair generates equal and opposite out-of-plane orientations of the two enantiomers. Applying this scheme to 2-methyloxirane, we follow the rotational wave packets by time-resolved Coulomb explosion imaging with two orthogonally arranged detectors. The measured angular distributions reveal that the unidirectional rotation is identical for both enantiomers, while the out-of-plane orientations are mirror images that persist through both early-time quasi-classical and quantum dynamics regimes, in quantitative agreement with simulations. We demonstrate that full angular distributions provide richer dynamical information, with some qualitatively different distributions yielding similar orientation factors upon integration. Our approach opens a route to real-time observation and control of chiral dynamics in the gas phase.

physics.chem-ph↗

arXiv2026

ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment

Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capability, termed compositional 3D reconstruction, is pivotal for the advancement of Spatial Intelligence and Embodied AI. However, existing methods struggle to achieve practical deployment due to the insufficient integration of cross-modal information, leaving them dependent on manual object prompting, reliant on auxiliary visual inputs, and restricted to overly simplistic scenes by training biases. To address these limitations, we propose ReplicateAnyScene, a framework capable of fully automated and zero-shot transformation of casually captured videos into compositional 3D scenes. Specifically, our pipeline incorporates a five-stage cascade to extract and structurally align generic priors from vision foundation models across textual, visual, and spatial dimensions, grounding them into structured 3D representations and ensuring semantic coherence and physical plausibility of the constructed scenes. To facilitate a more comprehensive evaluation of this task, we further introduce the C3DR benchmark to assess reconstruction quality from diverse aspects. Extensive experiments demonstrate the superiority of our method over existing baselines in generating high-quality compositional 3D scenes.

cs.CV↗

arXiv2026

Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application

Just Recognizable Difference (JRD) boosts coding efficiency for machine vision through visibility threshold modeling, but is currently limited to a single-task scenario. To address this issue, we propose a Multi-Task JRD (MT-JRD) dataset and an Attribute-assisted MT-JRD (AMT-JRD) model for Video Coding for Machines (VCM), enhancing both prediction accuracy and coding efficiency. First, we construct a dataset comprising 27,264 JRD annotations from machines, supporting three representative tasks including object detection, instance segmentation, and keypoint detection. Secondly, we propose the AMT-JRD prediction model, which integrates Generalized Feature Extraction Module (GFEM) and Specialized Feature Extraction Module (SFEM) to facilitate joint learning across multiple tasks. Thirdly, we innovatively incorporate object attribute information into object-wise JRD prediction through the Attribute Feature Fusion Module (AFFM), which introduces prior knowledge about object size and location. This design effectively compensates for the limitations of relying solely on image features and enhances the model's capacity to represent the perceptual mechanisms of machine vision. Finally, we apply the AMT-JRD model to VCM, where the accurately predicted JRDs are applied to reduce the coding bit rate while preserving accuracy across multiple machine vision tasks. Extensive experimental results demonstrate that AMT-JRD achieves precise and robust multi-task prediction with a mean absolute error of 3.781 and error variance of 5.332 across three tasks, outperforming the state-of-the-art single-task prediction model by 6.7% and 6.3%, respectively. Coding experiments further reveal that compared to the baseline VVC and JPEG, the AMT-JRD-based VCM improves an average of 3.861% and 7.886% Bjontegaard Delta-mean Average Precision (BD-mAP), respectively.

eess.IV↗

arXiv2026

Primitive-based Truncated Diffusion for Efficient Trajectory Generation of Differential Drive Mobile Manipulators

We present a learning-enhanced motion planner for differential drive mobile manipulators to improve efficiency, success rate, and optimality. For task representation encoder, we propose a keypoint sequence extraction module that maps boundary states to 3D space via differentiable forward kinematics. Point clouds and keypoints are encoded separately and fused with attention, enabling effective integration of environment and boundary states information. We also propose a primitive-based truncated diffusion model that samples from a biased distribution. Compared with vanilla diffusion model, this framework improves the efficiency and diversity of the solution. Denoised paths are refined by trajectory optimization to ensure dynamic feasibility and task-specific optimality. In cluttered 3D simulations, our method achieves higher success rate, improved trajectory diversity, and competitive runtime compared to vanilla diffusion and classical baselines. The source code is released at https://github.com/nmoma/nmoma .

cs.RO↗

arXiv2026

DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction

Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationships across diverse molecular modalities. Existing approaches frequently exhibit entangled representations--conflating structural, chemical, and functional factors--thereby limiting interpretability and transferability. Furthermore, conventional methods inadequately exploit complementary information from graphs, sequences, and geometries, often relying on naive concatenation that neglects inter-modal dependencies. In this work, we propose DMMRL, which employs variational autoencoders to disentangle molecular representations into shared (structure-relevant) and private (modality-specific) latent spaces, enhancing both interpretability and predictive performance. The proposed variational disentanglement mechanism effectively isolates the most informative features for property prediction, while orthogonality and alignment regularizations promote statistical independence and cross-modal consistency. Additionally, a gated attention fusion module adaptively integrates shared representations, capturing complex inter-modal relationships. Experimental validation across seven benchmark datasets demonstrates DMMRL's superior performance relative to state-of-the-art approaches. The code and data underlying this article are freely available at https://github.com/xulong0826/DMMRL.

cs.LG↗

arXiv2025

Deep-Learning Based Super-Resolution Functional Ultrasound Imaging of Transient Brain-Wide Neurovascular Activity on a Microscopic Scale

Transient brain-wide neuroimaging on a microscopic scale is pivotal for brain research, yet existing imaging modalities face challenges in meeting such spatiotemporal requirements. Functional ultrasound (fUS) enables transient neurovascular imaging through red blood cell backscattering, but suffers from diffraction-limited spatial resolution. Functional ultrasound localization microscopy (fULM) has addressed this limitation by integrating ULM with fUS; but this approach requires repeated stimulation and data accumulation. Here, we introduce super-resolution functional ultrasound (SR-fUS), a deep learning-based framework that reconstructs super-resolution ULM images from contrast-free ultrafast Doppler data. By incorporating red blood cell radial gradient fluctuation priors with uncertainty-driven loss, SR-fUS enables microscopic scale hemodynamic imaging with 25-{\mu}m spatial spatial resolution. In rat brains, SR-fUS visualized transient pain-evoked hemodynamic responses, distinguished stimulus-specific microvascular activation patterns during single-whisker stimulation, and dynamically tracked isoflurane anesthesia-induced microvascular dilation. The accuracy of SR-fUS was further preliminarily assessed through a comparative study with two-photon microscopy.

physics.med-ph↗

arXiv2025

MSCoD: An Enhanced Bayesian Updating Framework with Multi-Scale Information Bottleneck and Cooperative Attention for Structure-Based Drug Design

Structure-Based Drug Design (SBDD) is a powerful strategy in computational drug discovery, utilizing three-dimensional protein structures to guide the design of molecules with improved binding affinity. However, capturing complex protein-ligand interactions across multiple scales remains challenging, as current methods often overlook the hierarchical organization and intrinsic asymmetry of these interactions. To address these limitations, we propose MSCoD, a novel Bayesian updating-based generative framework for structure-based drug design. In our MSCoD, Multi-Scale Information Bottleneck (MSIB) was developed, which enables semantic compression at multiple abstraction levels for efficient hierarchical feature extraction. Furthermore, a multi-head cooperative attention (MHCA) mechanism was developed, which employs asymmetric protein-to-ligand attention to capture diverse interaction types while addressing the dimensionality disparity between proteins and ligands. Empirical studies showed that MSCoD outperforms state-of-the-art methods on the benchmark dataset. Its real-world applicability is confirmed by case studies on difficult targets like KRAS G12D (7XKJ). Additionally, the MSIB and MHCA modules prove transferable, boosting the performance of GraphDTA on standard drug target affinity prediction benchmarks (Davis and Kiba). The code and data underlying this article are freely available at https://github.com/xulong0826/MSCoD.

cs.LG↗

arXiv2025

DCVC-MV: Deep Contextual Multiview Video Compression with Efficient Inter-View Prediction

Multiview video is a key format for 3D applications such as free-viewpoint broadcasting and virtual reality, yet its large data volume poses significant challenges for efficient storage and transmission. As deep contextual video compression matures and moves toward standardization, extending such learned codecs to multiview scenarios has become essential for practical deployment---yet this direction remains largely unexplored. In this paper, we propose DCVC-MV, a novel deep contextual multiview video compression framework that satisfies three fundamental requirements. First, it maintains backward compatibility, ensuring that the primary view's bitstream can be decoded independently by a single-view decoder without being affected by other views. Second, it supports random-access capability, enabling flexible switching between different viewing perspectives. Third, it effectively exploits inter-view correlations to achieve high compression efficiency. This is realized through four dedicated components: (1) an inter-view motion feature propagation method, which propagates decoded independent-view motion features as conditions to promote dependent-view motion encoding; (2) an inter-view motion conditional entropy model designed to learn motion conditional priors across views for more accurate probability estimation of motion latent representations; (3) an implicit inter-view context prediction method, which predicts inter-view contexts from low-resolution independent-view content features without explicit disparity estimation; and (4) an inter-view contextual conditional entropy model that learns contextual conditional priors across views to further enhance content compression.

cs.CV↗

arXiv2025

TopAY: Efficient Trajectory Planning for Differential Drive Mobile Manipulators via Topological Paths Search and Arc Length-Yaw Parameterization

Differential drive mobile manipulators combine the mobility of wheeled bases with the manipulation capability of multi-joint arms, enabling versatile applications but posing considerable challenges for trajectory planning due to their high-dimensional state space and nonholonomic constraints. This paper introduces TopAY, an optimization-based planning framework designed for efficient and safe trajectory generation for differential drive mobile manipulators. The framework employs a hierarchical initial value acquisition strategy, including topological paths search for the base and parallel sampling for the manipulator. A polynomial trajectory representation with arc length-yaw parameterization is also proposed to reduce optimization complexity while preserving dynamic feasibility. Extensive simulation and real-world experiments validate that TopAY achieves higher planning efficiency and success rates than state-of-the-art method in dense and complex scenarios. The source code is released at https://github.com/TopAY-Planner/TopAY .

cs.RO↗

arXiv2025

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this issue, this paper proposes for the first time a novel adversarial defense method based on denoise diffusion probabilistic models, termed DiffDf, aimed at effectively improving the robustness of existing visual tracking methods against adversarial attacks. DiffDf establishes a multi-scale defense mechanism by combining pixel-level reconstruction loss, semantic consistency loss, and structural similarity loss, effectively suppressing adversarial perturbations through a gradual denoising process. Extensive experimental results on several mainstream datasets show that the DiffDf method demonstrates excellent generalization performance for trackers with different architectures, significantly improving various evaluation metrics while achieving real-time inference speeds of over 30 FPS, showcasing outstanding defense performance and efficiency. Codes are available at https://github.com/pgao-lab/DiffDf.

cs.CV↗

arXiv2025

Towards Adaptive Meta-Gradient Adversarial Examples for Visual Tracking

In recent years, visual tracking methods based on convolutional neural networks and Transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security issues exposed by deep learning models have gradually affected the reliable application of visual tracking methods in real-world scenarios. Therefore, how to reveal the security vulnerabilities of existing visual trackers through effective adversarial attacks has become a critical problem that needs to be addressed. To this end, we propose an adaptive meta-gradient adversarial attack (AMGA) method for visual tracking. This method integrates multi-model ensembles and meta-learning strategies, combining momentum mechanisms and Gaussian smoothing, which can significantly enhance the transferability and attack effectiveness of adversarial examples. AMGA randomly selects models from a large model repository, constructs diverse tracking scenarios, and iteratively performs both white- and black-box adversarial attacks in each scenario, optimizing the gradient directions of each model. This paradigm minimizes the gap between white- and black-box adversarial attacks, thus achieving excellent attack performance in black-box scenarios. Extensive experimental results on large-scale datasets such as OTB2015, LaSOT, and GOT-10k demonstrate that AMGA significantly improves the attack performance, transferability, and deception of adversarial examples. Codes and data are available at https://github.com/pgao-lab/AMGA.

cs.CV↗

arXiv2025

Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process

Terrain analysis is critical for the practical ap- plication of ground mobile robots in real-world tasks, espe- cially in outdoor unstructured environments. In this paper, we propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to effectively navigate through complex terrains. Our approach utilizes sparse Gaussian processes (SGP) to extract geometric features (curvature, gradient, elevation, etc.) directly from point cloud scans. These features are then used to construct a high- resolution local traversability map. Then, we design a spatial- temporal Bayesian Gaussian kernel (BGK) inference method to dynamically evaluate traversability scores, integrating historical and real-time data while considering factors such as slope, flatness, gradient, and uncertainty metrics. GPU acceleration is applied in the feature extraction step, and the system achieves real-time performance. Extensive simulation experiments across diverse terrain scenarios demonstrate that our method outper- forms SOTA approaches in both accuracy and computational efficiency. Additionally, we develop an autonomous navigation framework integrated with the traversability map and validate it with a differential driven vehicle in complex outdoor envi- ronments. Our code will be open-source for further research and development by the community, https://github.com/ZJU-FAST-Lab/FSGP_BGK.

cs.RO↗

arXiv2025

SEB-Naver: A SE(2)-based Local Navigation Framework for Car-like Robots on Uneven Terrain

Autonomous navigation of car-like robots on uneven terrain poses unique challenges compared to flat terrain, particularly in traversability assessment and terrain-associated kinematic modelling for motion planning. This paper introduces SEB-Naver, a novel SE(2)-based local navigation framework designed to overcome these challenges. First, we propose an efficient traversability assessment method for SE(2) grids, leveraging GPU parallel computing to enable real-time updates and maintenance of local maps. Second, inspired by differential flatness, we present an optimization-based trajectory planning method that integrates terrain-associated kinematic models, significantly improving both planning efficiency and trajectory quality. Finally, we unify these components into SEB-Naver, achieving real-time terrain assessment and trajectory optimization. Extensive simulations and real-world experiments demonstrate the effectiveness and efficiency of our approach. The code is at https://github.com/ZJU-FAST-Lab/seb_naver.

cs.RO↗

arXiv2025

Tracailer: An Efficient Trajectory Planner for Tractor-Trailer Robots in Unstructured Environments

The tractor-trailer robot consists of a drivable tractor and one or more non-drivable trailers connected via hitches. Compared to typical car-like robots, the addition of trailers provides greater transportation capability. However, this also complicates motion planning due to the robot's complex kinematics, high-dimensional state space, and deformable structure. To efficiently plan safe, time-optimal trajectories that adhere to the kinematic constraints of the robot and address the challenges posed by its unique features, this paper introduces a lightweight, compact, and high-order smooth trajectory representation for tractor-trailer robots. Based on it, we design an efficiently solvable spatial-temporal trajectory optimization problem. To deal with deformable structures, which leads to difficulties in collision avoidance, we fully leverage the collisionfree regions of the environment, directly applying deformations to trajectories in continuous space. This approach not requires constructing safe regions from the environment using convex approximations through collision-free seed points before each optimization, avoiding the loss of the solution space, thus reducing the dependency of the optimization on initial values. Moreover, a multi-terminal fast path search algorithm is proposed to generate the initial values for optimization. Extensive simulation experiments demonstrate that our approach achieves severalfold improvements in efficiency compared to existing algorithms, while also ensuring lower curvature and trajectory duration. Real-world experiments involving the transportation, loading and unloading of goods in both indoor and outdoor scenarios further validate the effectiveness of our method. The source code is accessible at https://github.com/Tracailer/Tracailer.

cs.RO↗

arXiv2025

"Molecular waveplate" for the control of ultrashort pulses carrying orbital angular momentum

Ultrashort laser pulses carrying orbital angular momentum (OAM) have become essential tools in Atomic, Molecular, and Optical (AMO) studies, particularly for investigating strong-field light-matter interactions. However, controlling and generating ultrashort vortex pulses presents significant challenges, since their broad spectral content complicates manipulation with conventional optical elements, while the high peak power inherent in short-duration pulses risks damaging optical components. Here, we introduce a novel method for generating and controlling broadband ultrashort vortex beams by exploiting the non-adiabatic alignment of linear gas-phase molecules induced by vector beams. The interaction between the vector beam and the gas-phase molecules results in spatially varying polarizability, imparting a phase modulation to a probe laser. This process effectively creates a tunable ``molecular waveplate'' that adapts naturally to a broad spectral range. By leveraging this approach, we can generate ultrashort vortex pulses across a wide range of wavelengths. Under optimized gas pressure and interaction length conditions, this method allows for highly efficient conversion of circularly polarized light into the desired OAM pulse, thus enabling the generation of few-cycle, high-intensity vortex beams. This molecular waveplate, which overcomes the limitations imposed by conventional optical elements, opens up new possibilities for exploring strong-field physics, ultrafast science, and other applications that require high-intensity vortex beams.

physics.optics↗