arXiv subjects

Haodong Zhang

Publications and source records attributed to Haodong Zhang.

At least 19 recordsLinked to original sources

arXiv2026

AnomalyCraft-700K: Component-Level Controllable and Verifiable Synthetic Anomalies for Fine-Grained Video Anomaly Understanding

Progress in video anomaly understanding (VAU) has long been limited by inherent deficiencies of real-world anomaly videos, which are hard to collect and offer little control over their content. Synthetic anomaly approaches partially alleviate data scarcity, yet their generation remains largely controlled at the category or prompt level. They also lack component-level verification of video-text consistency and provide insufficient hard normal samples near the normal-anomaly boundary. To address this, we present AnomalyCraft-700K, a component-controllable synthetic anomaly dataset for fine-grained VAU, containing over 40K videos and over 700K task-level textual annotations. From fine-grained semantic components and a progressive three-stage pipeline, we craft anomaly events that are richly detailed, semantically controlled, and temporally structured, and additionally construct per-category hard normal samples to prompt the model to discriminate based on anomaly semantics rather than surface visual cues. Moreover, using the components as verification units, AnomalyCraft-700K further performs component-wise correction of video-text discrepancies introduced during generation, providing reliable annotations with verified cross-modal alignment for six tasks that progress from anomaly detection, through anomaly retrieval and captioning, to fine-grained anomaly reasoning. Evaluations of widely used methods under both traditional and MLLM-based protocols demonstrate that AnomalyCraft-700K serves as an effective source of supervision, from anomaly detection to fine-grained anomaly understanding.

cs.CV↗

arXiv2026

SixthSense: Task-Agnostic Proprioception-Only Whole-Body Wrench Estimation for Humanoids

Humanoid robots are entering our physical world at scale, yet as oversized toys--good at singing and dancing, but short on force-interaction capabilities for practical tasks. Bridging this gap necessitates prioritizing reliable contact perception as a fundamental requirement. Estimating external wrenches in humanoids is complicated by floating-base dynamics and indeterminate contact locations. Existing analytical frameworks require idealistic assumptions and hard-to-obtain measurements, which are often unavailable in practice. To bridge this gap, we propose SixthSense, a task-agnostic approach that infers whole-body contact timing, location, and wrenches from proprioception and IMU data alone. To capture the multi-modal dynamics between unstructured contact inputs and the uncertain motion outputs, we employ conditional flow matching to tokenize proprioceptive histories and estimate a spatiotemporally sparse contact-event flow. SixthSense serves as a plug-and-play perception module for applications including collision detection, physical human-robot interaction, and force-feedback teleoperation. Experiments across standing, walking, and whole-body motion-tracking policies showcased unprecedented performance in diverse behaviors.

cs.RO↗

arXiv2026

HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding

Electroencephalography (EEG) decoding requires models that can effectively extract and integrate complex temporal, spectral, and spatial features from multichannel signals. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time-space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages, while a customized Dynamic Tanh normalization module is introduced to replace traditional Layer Normalization in order to enhance training stability and reduce redundancy. Extensive experiments are conducted on two representative benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related cross-subject classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm that each core component of the proposed framework contributes significantly to the overall decoding performance, demonstrating HCFT's effectiveness in capturing EEG dynamics and its potential for real-world BCI applications.

cs.HC↗

arXiv2025

Vehicle Dynamics Embedded World Models for Autonomous Driving

World models have gained significant attention as a promising approach for autonomous driving. By emulating human-like perception and decision-making processes, these models can predict and adapt to dynamic environments. Existing methods typically map high-dimensional observations into compact latent spaces and learn optimal policies within these latent representations. However, prior work usually jointly learns ego-vehicle dynamics and environmental transition dynamics from the image input, leading to inefficiencies and a lack of robustness to variations in vehicle dynamics. To address these issues, we propose the Vehicle Dynamics embedded Dreamer (VDD) method, which decouples the modeling of ego-vehicle dynamics from environmental transition dynamics. This separation allows the world model to generalize effectively across vehicles with diverse parameters. Additionally, we introduce two strategies to further enhance the robustness of the learned policy: Policy Adjustment during Deployment (PAD) and Policy Augmentation during Training (PAT). Comprehensive experiments in simulated environments demonstrate that the proposed model significantly improves both driving performance and robustness to variations in vehicle dynamics, outperforming existing approaches.

cs.RO↗

arXiv2025

DUPLE: An Intelligent Cross-Deployment Recognition Framework for Fiber-Optic Perimeter Security under Scarce Target Labels

Distributed Fiber Optic Sensing (DFOS) has emerged as a promising technology for long-range and real-time perimeter security in critical infrastructure monitoring. However, DFOS signals collected from different field deployments often exhibit substantial distribution shifts caused by variations in fiber installation, structural coupling, and environmental noise. These deployment-dependent changes make reliable event recognition difficult in practical perimeter security systems, especially when labeled samples from new target sites are scarce or unavailable. To address these challenges, this paper proposes DUPLE, an intelligent cross-deployment recognition framework for fiber-optic perimeter security under label-scarce target deployments. DUPLE employs statistically guided meta-learning to enhance recognition robustness across unseen deployments. Specifically, a dual-domain multi-prototype learner jointly models temporal and frequency-domain evidence to capture intra-class variability under deployment shifts. A statistical guidance network estimates sample-specific domain reliability from raw signal statistics, while a query-aware aggregation mechanism adaptively selects relevant prototypes for each test sample. Extensive experiments on two real-world cross-deployment DFOS benchmarks demonstrate that DUPLE consistently outperforms representative traditional machine learning, deep learning, domain generalization, and meta-learning baselines. Ablation, few-shot, per-deployment, and efficiency analyses further verify the effectiveness and practicality of DUPLE for reliable DFOS-based perimeter security monitoring.

cs.LG↗

arXiv2025

A Scalable Whole-body Motion Transfer via Implicit Kinodynamic Motion Retargeting

Human-to-humanoid imitation learning presents a promising pathway to address the severe data scarcity bottleneck in robotics by utilizing abundant, large-scale human motion collections. However, scaling this paradigm requires addressing two key challenges. First, human motion data acquired from videos, motion capture systems, or generative models often contains spatial noise, jitter, and frame-level flickering, which can be amplified during retargeting and lead to unsafe or physically infeasible robot motions. Second, existing motion retargeting methods typically rely on frame-by-frame numerical optimization, making them too computationally expensive for large-scale dataset synthesis. To overcome these limitations, we introduce Implicit Kinodynamic Motion Retargeting (IKMR), a highly scalable, neural-based data transformation pipeline. IKMR leverages a skeleton-based graph convolutional dual autoencoder to map cross-structural human and humanoid kinematic configurations into a shared topological latent space. To guarantee the physical viability of the generated data, the framework incorporates a physics-informed refinement phase that utilizes simulated physical tracking feedback to learn a robust motion prior. This implicit formulation fundamentally resolves both challenges. By shifting the computational burden from online optimization to offline inference, IKMR achieves an unprecedented data conversion throughput exceeding 5000 frames per second. Furthermore, leveraging the learned motion prior, it functions as an intrinsic data curation mechanism and naturally filters out high-frequency noise and spatial jitters from source data, yielding smooth trajectories that ensure physical hardware safety. Extensive evaluations, including real-world whole-body control deployments on humanoid robot, confirm that IKMR bridges the gap between human motion and robotic data.

cs.RO↗

arXiv2025

DRDCAE-STGNN: An End-to-End Discrimina-tive Autoencoder with Spatio-Temporal Graph Learning for Motor Imagery Classification

Motor imagery (MI) based brain-computer interfaces (BCIs) hold significant potential for assistive technologies and neurorehabilitation. However, the precise and efficient decoding of MI remains challenging due to their non-stationary nature and low signal-to-noise ratio. This paper introduces a novel end-to-end deep learning framework of Discriminative Residual Dense Convolutional Autoencoder with Spatio-Temporal Graph Neural Network (DRDCAE-STGNN) to enhance the MI feature learning and classification. Specifically, the DRDCAE module leverages residual-dense connections to learn discriminative latent representations through joint reconstruction and classifica-tion, while the STGNN module captures dynamic spatial dependencies via a learnable graph adjacency matrix and models temporal dynamics using bidirectional long short-term memory (LSTM). Extensive evaluations on BCI Competition IV 2a, 2b, and PhysioNet datasets demonstrate state-of-the-art performance, with average accuracies of 95.42%, 97.51%, and 90.15%, respectively. Ablation studies confirm the contribution of each component, and interpreta-bility analysis reveals neurophysiologically meaningful connectivity patterns. Moreover, despite its complexity, the model maintains a feasible parameter count and an inference time of 0.32 ms per sample. These results indicate that our method offers a robust, accurate, and interpretable solution for MI-EEG decoding, with strong generalizability across subjects and tasks and meeting the requirements for potential real-time BCI applications.

cs.HC↗

arXiv2025

Foundation Models for Cross-Domain EEG Analysis Application: A Survey

Electroencephalography (EEG) analysis stands at the forefront of neuroscience and artificial intelligence research, where foundation models are reshaping the traditional EEG analysis paradigm by leveraging their powerful representational capacity and cross-modal generalization. However, the rapid proliferation of these techniques has led to a fragmented research landscape, characterized by diverse model roles, inconsistent architectures, and a lack of systematic categorization. To bridge this gap, this study presents the first comprehensive modality-oriented taxonomy for foundation models in EEG analysis, systematically organizing research advances based on output modalities of the native EEG decoding, EEG-text, EEG-vision, EEG-audio, and broader multimodal frameworks. We rigorously analyze each category's research ideas, theoretical foundations, and architectural innovations, while highlighting open challenges such as model interpretability, cross-domain generalization, and real-world applicability in EEG-based systems. By unifying this dispersed field, our work not only provides a reference framework for future methodology development but accelerates the translation of EEG foundation models into scalable, interpretable, and online actionable solutions.

cs.HC↗

arXiv2025

TOP: Time Optimization Policy for Stable and Accurate Standing Manipulation with Humanoid Robots

Humanoid robots have the potential capability to perform a diverse range of manipulation tasks, but this is based on a robust and precise standing controller. Existing methods are either ill-suited to precisely control high-dimensional upper-body joints, or difficult to ensure both robustness and accuracy, especially when upper-body motions are fast. This paper proposes a novel time optimization policy (TOP), to train a standing manipulation control model that ensures balance, precision, and time efficiency simultaneously, with the idea of adjusting the time trajectory of upper-body motions but not only strengthening the disturbance resistance of the lower-body. Our approach consists of three parts. Firstly, we utilize motion prior to represent upper-body motions to enhance the coordination ability between the upper and lower-body by training a variational autoencoder (VAE). Then we decouple the whole-body control into an upper-body PD controller for precision and a lower-body RL controller to enhance robust stability. Finally, we train TOP method in conjunction with the decoupled controller and VAE to reduce the balance burden resulting from fast upper-body motions that would destabilize the robot and exceed the capabilities of the lower-body RL policy. The effectiveness of the proposed approach is evaluated via both simulation and real world experiments, which demonstrate the superiority on standing manipulation tasks stably and accurately. The project page can be found at https://anonymous.4open.science/w/top-258F/.

cs.RO↗

arXiv2025

A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot

Motion imitation is a pivotal and effective approach for humanoid robots to achieve a more diverse range of complex and expressive movements, making their performances more human-like. However, the significant differences in kinematics and dynamics between humanoid robots and humans present a major challenge in accurately imitating motion while maintaining balance. In this paper, we propose a novel whole-body motion imitation framework for a full-size humanoid robot. The proposed method employs contact-aware whole-body motion retargeting to mimic human motion and provide initial values for reference trajectories, and the non-linear centroidal model predictive controller ensures the motion accuracy while maintaining balance and overcoming external disturbances in real time. The assistance of the whole-body controller allows for more precise torque control. Experiments have been conducted to imitate a variety of human motions both in simulation and in a real-world humanoid robot. These experiments demonstrate the capability of performing with accuracy and adaptability, which validates the effectiveness of our approach.

cs.RO↗

arXiv2025

EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation

To support humanoid robots in performing manipulation tasks, it is essential to study stable standing while accommodating upper-body motions. However, the limited controllable range of humanoid robots in a standing position affects the stability of the entire body. Thus we introduce a reinforcement learning based framework for humanoid robots to imitate human upper-body motions while maintaining overall stability. Our approach begins with designing a retargeting network that generates a large-scale upper-body motion dataset for training the reinforcement learning (RL) policy, which enables the humanoid robot to track upper-body motion targets, employing domain randomization for enhanced robustness. To avoid exceeding the robot's execution capability and ensure safety and stability, we propose an Executable Motion Prior (EMP) module, which adjusts the input target movements based on the robot's current state. This adjustment improves standing stability while minimizing changes to motion amplitude. We evaluate our framework through simulation and real-world tests, demonstrating its practical applicability.

cs.RO↗

arXiv2025

Transformer-based EEG Decoding: A Survey

Electroencephalography (EEG) is one of the most common signals used to capture the electrical activity of the brain, and the decoding of EEG, to acquire the user intents, has been at the forefront of brain-computer/machine interfaces (BCIs/BMIs) research. Compared to traditional EEG analysis methods with machine learning, the advent of deep learning approaches have gradually revolutionized the field by providing an end-to-end long-cascaded architecture, which can learn more discriminative features automatically. Among these, Transformer is renowned for its strong handling capability of sequential data by the attention mechanism, and the application of Transformers in various EEG processing tasks is increasingly prevalent. This article delves into a relevant survey, summarizing the latest application of Transformer models in EEG decoding since it appeared. The evolution of the model architecture is followed to sort and organize the related advances, in which we first elucidate the fundamentals of the Transformer that benefits EEG decoding and its direct application. Then, the common hybrid architectures by integrating basic Transformer with other deep learning techniques (convolutional/recurrent/graph/spiking neural netwo-rks, generative adversarial networks, diffusion models, etc.) is overviewed in detail. The research advances of applying the modified intrinsic structures of customized Transformer have also been introduced. Finally, the current challenges and future development prospects in this rapidly evolving field are discussed. This paper aims to help readers gain a clear understanding of the current state of Transformer applications in EEG decoding and to provide valuable insights for future research endeavors.

cs.LG↗

arXiv2025

SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model

Video anomaly detection (VAD) aims to identify unexpected events in videos and has wide applications in safety-critical domains. While semi-supervised methods trained on only normal samples have gained traction, they often suffer from high false alarm rates and poor interpretability. Recently, vision-language models (VLMs) have demonstrated strong multimodal reasoning capabilities, offering new opportunities for explainable anomaly detection. However, their high computational cost and lack of domain adaptation hinder real-time deployment and reliability. Inspired by dual complementary pathways in human visual perception, we propose SlowFastVAD, a hybrid framework that integrates a fast anomaly detector with a slow anomaly detector (namely a retrieval augmented generation (RAG) enhanced VLM), to address these limitations. Specifically, the fast detector first provides coarse anomaly confidence scores, and only a small subset of ambiguous segments, rather than the entire video, is further analyzed by the slower yet more interpretable VLM for elaborate detection and reasoning. Furthermore, to adapt VLMs to domain-specific VAD scenarios, we construct a knowledge base including normal patterns based on few normal samples and abnormal patterns inferred by VLMs. During inference, relevant patterns are retrieved and used to augment prompts for anomaly reasoning. Finally, we smoothly fuse the anomaly confidence of fast and slow detectors to enhance robustness of anomaly detection. Extensive experiments on four benchmarks demonstrate that SlowFastVAD effectively combines the strengths of both fast and slow detectors, and achieves remarkable detection accuracy and interpretability with significantly reduced computational overhead, making it well-suited for real-world VAD applications with high reliability requirements.

cs.CV↗

arXiv2025

Re-Aligning Language to Visual Objects with an Agentic Workflow

Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During the training process, recent studies leverage vision-language models (VLMs) to automatically generate human-like expressions for visual objects, facilitating training data scaling up. In this process, we observe that VLM hallucinations bring inaccurate object descriptions (e.g., object name, color, and shape) to deteriorate VL alignment quality. To reduce VLM hallucinations, we propose an agentic workflow controlled by an LLM to re-align language to visual objects via adaptively adjusting image and text prompts. We name this workflow Real-LOD, which includes planning, tool use, and reflection steps. Given an image with detected objects and VLM raw language expressions, Real-LOD reasons its state automatically and arranges action based on our neural symbolic designs (i.e., planning). The action will adaptively adjust the image and text prompts and send them to VLMs for object re-description (i.e., tool use). Then, we use another LLM to analyze these refined expressions for feedback (i.e., reflection). These steps are conducted in a cyclic form to gradually improve language descriptions for re-aligning to visual objects. We construct a dataset that contains a tiny amount of 0.18M images with re-aligned language expression and train a prevalent LOD model to surpass existing LOD methods by around 50% on the standard benchmarks. Our Real-LOD workflow, with automatic VL refinement, reveals a potential to preserve data quality along with scaling up data quantity, which further improves LOD performance from a data-alignment perspective.

cs.CV↗

arXiv2025

Natural Humanoid Robot Locomotion with Generative Motion Prior

Natural and lifelike locomotion remains a fundamental challenge for humanoid robots to interact with human society. However, previous methods either neglect motion naturalness or rely on unstable and ambiguous style rewards. In this paper, we propose a novel Generative Motion Prior (GMP) that provides fine-grained motion-level supervision for the task of natural humanoid robot locomotion. To leverage natural human motions, we first employ whole-body motion retargeting to effectively transfer them to the robot. Subsequently, we train a generative model offline to predict future natural reference motions for the robot based on a conditional variational auto-encoder. During policy training, the generative motion prior serves as a frozen online motion generator, delivering precise and comprehensive supervision at the trajectory level, including joint angles and keypoint positions. The generative motion prior significantly enhances training stability and improves interpretability by offering detailed and dense guidance throughout the learning process. Experimental results in both simulation and real-world environments demonstrate that our method achieves superior motion naturalness compared to existing approaches. Project page can be found at https://sites.google.com/view/humanoid-gmp

cs.RO↗

arXiv2025

Red Emission from Strain-Relaxed Bulk InGaN Active Region

High-In-content InGaN quantum wells (QWs) in red light-emitting diodes (LEDs) are typically grown at low temperatures to ensure effective In incorporation. In this study, red LEDs based on bulk InGaN active region were demonstrated. The growth temperature of bulk InGaN was ~800C, which is over 100C higher than the typical growth temperature of red QWs. By introducing high-density trench structures in the underlying green multi-quantum wells (MQWs), the compressive strain in bulk InGaN was relaxed by ~96%. With strain relaxation, phase separation occurred in the bulk InGaN, forming low-In-content (blue) and high-In-content (red) phases. The red phase acted as carrier localization centers, enabling red light emission under electrical injection. The red LEDs based on bulk InGaN exhibited a peak wavelength of 645 nm at 20 mA, with on-wafer peak external quantum efficiency of 0.32%. This study presents a new epitaxial strategy for red InGaN LEDs.

cond-mat.mtrl-sci↗

arXiv2025

Slip and friction at fluid-solid interfaces: Concept of adsorption layer

When a fluid flows past a solid surface, its macroscopic motion arises from a subtle interplay between microscopic hydrodynamic and thermodynamic effects at the fluid-solid interface. Classical hydrodynamic models often rely on an unphysical no-slip boundary condition or an arbitrarily prescribed slip length, yet both approaches lack a rigorous physical foundation. This work introduces the concept of an Adsorption Layer (AL), an interfacial region of thickness delta l, where fluid-solid molecular interactions regulate both surface adsorption/depletion and interfacial slip. By applying the energy minimization principle, we derive balance equations within the AL that couple fluid-solid friction, viscous stresses, and surface adsorption dynamics. This framework establishes a self-consistent thermodynamic coupling between the AL and the bulk fluid, unlike conventional sharp-interface models. A key finding is the often-overlooked role and coupling of pressure and chemical potential gradients in the direction normal to the interface. This theoretical advance successfully explains the confinement-induced enhancement of water slippage in carbon nanotubes, quantitatively agreeing with molecular dynamics and experimental data -- an effect classical slip models fail to reproduce. Furthermore, when extended to binary liquids, the theory captures spatial variations in slip velocity near moving contact lines, highlighting the role of interfacial friction in shaping local flow. Our results demonstrate that the slip length is not a fixed material constant but rather an emergent, geometry- and composition-dependent property arising from coupled interfacial thermodynamics and hydrodynamics. This framework provides a physically grounded description of interfacial momentum transfer, with significant implications for microfluidics and surface engineering.

physics.flu-dyn↗

arXiv2025

Bias voltage controlled inversions of tunneling magnetoresistance in van der Waals heterostructures Fe3GaTe2/hBN/Fe3GaTe2

We report the bias voltage controlled inversions of tunneling magnetoresistance (TMR) in magnetic tunnel junctions composed of Fe3GaTe2 electrodes and hBN tunneling barrier, observed at room temperature. The polarity reversal of TMR occurs consistently at around 0.625 V across multiple devices and temperatures, highlighting the robustness of the effect. To understand this behavior, we developed a theoretical model incorporating spin-resolved density of states (DOS) at high energy levels. By adjusting the DOS weighting at different k points to account for misalignment between the crystal structure of electrodes in experimental devices, we improved agreement between experimental and theoretical inversion voltages. Our results provide valuable insight into the voltage-controlled spin injection and detection in two-dimensional magnetic tunnel junctions, with implications for the development of energy-efficient spintronic devices.

cond-mat.mes-hall↗