arXiv subjects

Yangsong Zhang

Publications and source records attributed to Yangsong Zhang.

At least 19 recordsLinked to original sources

arXiv2026

A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scale VLM backbones and iterative diffusion/flow-based action heads incur high latency and compute, making real-time control expensive on commodity hardware. We present A1, a fully open-source and transparent VLA framework designed for low-cost, high-throughput inference without sacrificing manipulation success; Our approach leverages pretrained VLMs that provide implicit affordance priors for action generation. We release the full training stack (training code, data/data-processing pipeline, intermediate checkpoints, and evaluation scripts) to enable end-to-end reproducibility. Beyond optimizing the VLM alone, A1 targets the full inference pipeline by introducing a budget-aware adaptive inference scheme that jointly accelerates the backbone and the action head. Specifically, we monitor action consistency across intermediate VLM layers to trigger early termination, and propose Inter-Layer Truncated Flow Matching that warm-starts denoising across layers, enabling accurate actions with substantially fewer effective denoising iterations. Across simulation benchmarks (LIBERO, VLABench) and real robots (Franka, AgiBot), A1 achieves state-of-the-art success rates while significantly reducing inference cost (e.g., up to 72% lower per-episode latency for flow-matching inference and up to 76.6% backbone computation reduction with minor performance degradation). On RoboChallenge, A1 achieves an average success rate of 29.00%, outperforming baselines including pi0(28.33%), X-VLA (21.33%), and RDT-1B (15.00%).

cs.RO↗

arXiv2026

PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization

Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Building on this progress, recent methods attempt to transfer such models for character animation and real robot control by applying a Whole-Body Controller (WBC) that converts diffusion-generated motions into executable trajectories. While WBC trajectories become compliant with physics, they may expose substantial deviations from original motion. To address this issue, we here propose PhysMoDPO, a Direct Preference Optimization framework. Unlike prior work that relies on hand-crafted physics-aware heuristics such as foot-sliding penalties, we integrate WBC into our training pipeline and optimize diffusion model such that the output of WBC becomes compliant both with physics and original text instructions. To train PhysMoDPO we deploy physics-based and task-specific rewards and use them to assign preference to synthesized trajectories. Our extensive experiments on text-to-motion and spatial control tasks demonstrate consistent improvements of PhysMoDPO in both physical realism and task-related metrics on simulated robots. Moreover, we demonstrate that PhysMoDPO results in significant improvements when applied to zero-shot motion transfer in simulation and for real-world deployment on a G1 humanoid robot.

cs.LG↗

arXiv2025

SPECTRE: Spectral Pre-training Embeddings with Cylindrical Temporal Rotary Position Encoding for Fine-Grained sEMG-Based Movement Decoding

Decoding fine-grained movement from non-invasive surface Electromyography (sEMG) is a challenge for prosthetic control due to signal non-stationarity and low signal-to-noise ratios. Generic self-supervised learning (SSL) frameworks often yield suboptimal results on sEMG as they attempt to reconstruct noisy raw signals and lack the inductive bias to model the cylindrical topology of electrode arrays. To overcome these limitations, we introduce SPECTRE, a domain-specific SSL framework. SPECTRE features two primary contributions: a physiologically-grounded pre-training task and a novel positional encoding. The pre-training involves masked prediction of discrete pseudo-labels from clustered Short-Time Fourier Transform (STFT) representations, compelling the model to learn robust, physiologically relevant frequency patterns. Additionally, our Cylindrical Rotary Position Embedding (CyRoPE) factorizes embeddings along linear temporal and annular spatial dimensions, explicitly modeling the forearm sensor topology to capture muscle synergies. Evaluations on multiple datasets, including challenging data from individuals with amputation, demonstrate that SPECTRE establishes a new state-of-the-art for movement decoding, significantly outperforming both supervised baselines and generic SSL approaches. Ablation studies validate the critical roles of both spectral pre-training and CyRoPE. SPECTRE provides a robust foundation for practical myoelectric interfaces capable of handling real-world sEMG complexities.

cs.HC↗

arXiv2025

InterPose: Learning to Generate Human-Object Interactions from Large-Scale Web Videos

Human motion generation has shown great advances thanks to the recent diffusion models trained on large-scale motion capture data. Most of existing works, however, currently target animation of isolated people in empty scenes. Meanwhile, synthesizing realistic human-object interactions in complex 3D scenes remains a critical challenge in computer graphics and robotics. One obstacle towards generating versatile high-fidelity human-object interactions is the lack of large-scale datasets with diverse object manipulations. Indeed, existing motion capture data is typically restricted to single people and manipulations of limited sets of objects. To address this issue, we propose an automatic motion extraction pipeline and use it to collect interaction-rich human motions. Our new dataset InterPose contains 73.8K sequences of 3D human motions and corresponding text captions automatically obtained from 45.8K videos with human-object interactions. We perform extensive experiments and demonstrate InterPose to bring significant improvements to state-of-the-art methods for human motion generation. Moreover, using InterPose we develop an LLM-based agent enabling zero-shot animation of people interacting with diverse objects and scenes.

cs.CV↗

arXiv2025

Multi-Site rs-fMRI Domain Alignment for Autism Spectrum Disorder Auxiliary Diagnosis Based on Hyperbolic Space

Increasing the volume of training data can enable the auxiliary diagnostic algorithms for Autism Spectrum Disorder (ASD) to learn more accurate and stable models. However, due to the significant heterogeneity and domain shift in rs-fMRI data across different sites, the accuracy of auxiliary diagnosis remains unsatisfactory. Moreover, there has been limited exploration of multi-source domain adaptation models on ASD recognition, and many existing models lack inherent interpretability, as they do not explicitly incorporate prior neurobiological knowledge such as the hierarchical structure of functional brain networks. To address these challenges, we proposed a domain-adaptive algorithm based on hyperbolic space embedding. Hyperbolic space is naturally suited for representing the topology of complex networks such as brain functional networks. Therefore, we embedded the brain functional network into hyperbolic space and constructed the corresponding hyperbolic space community network to effectively extract latent representations. To address the heterogeneity of data across different sites and the issue of domain shift, we introduce a constraint loss function, Hyperbolic Maximum Mean Discrepancy (HMMD), to align the marginal distributions in the hyperbolic space. Additionally, we employ class prototype alignment to mitigate discrepancies in conditional distributions across domains. Experimental results indicate that the proposed algorithm achieves superior classification performance for ASD compared to baseline models, with improved robustness to multi-site heterogeneity. Specifically, our method achieves an average accuracy improvement of 4.03%. Moreover, its generalization capability is further validated through experiments conducted on extra Major Depressive Disorder (MDD) datasets. The code is available at https://github.com/LYQbyte/H2MSDA.

q-bio.NC↗

arXiv2025

Hierarchical feature extraction on functional brain networks for autism spectrum disorder identification with resting-state fMRI data

Autism Spectrum Disorder (ASD) is a pervasive developmental disorder of the central nervous system, primarily manifesting in childhood. It is characterized by atypical and repetitive behaviors. Currently, diagnostic methods mainly rely on questionnaire surveys and behavioral observations, which are prone to misdiagnosis due to their subjective nature. With advancements in medical imaging, MR imaging-based diagnostics have emerged as a more objective alternative. In this paper, we propose a Hierarchical Neural Network model for ASD identification, termed ASD-HNet, which hierarchically extracts features from functional brain networks based on resting-state functional magnetic resonance imaging (rs-fMRI) data. This hierarchical approach enhances the extraction of brain representations, improving diagnostic accuracy and aiding in the identification of brain regions associated with ASD. Specifically, features are extracted at three levels: (1) the local region of interest (ROI) scale, (2) the community scale, and (3) the global representation scale. At the ROI scale, graph convolution is employed to transfer features between ROIs. At the community scale, functional gradients are introduced, and a K-Means clustering algorithm is applied to group ROIs with similar functional gradients into communities. Features from ROIs within the same community are then extracted to characterize the communities. At the global representation scale, we extract global features from the whole community-scale brain networks to represent the entire brain. We validate the effectiveness of our method using the publicly available Autism Brain Imaging Data Exchange I (ABIDE-I) dataset. Experimental results demonstrate that ASD-HNet outperforms existing methods. The code is available at https://github.com/LYQbyte/ASD-HNet.

q-bio.NC↗

arXiv2023

Short-length SSVEP data extension by a novel generative adversarial networks based framework

Steady-state visual evoked potentials (SSVEPs) based brain-computer interface (BCI) has received considerable attention due to its high information transfer rate (ITR) and available quantity of targets. However, the performance of frequency identification methods heavily hinges on the amount of user calibration data and data length, which hinders the deployment in real-world applications. Recently, generative adversarial networks (GANs)-based data generation methods have been widely adopted to create synthetic electroencephalography (EEG) data, holds promise to address these issues. In this paper, we proposed a GAN-based end-to-end signal transformation network for Time-window length Extension, termed as TEGAN. TEGAN transforms short-length SSVEP signals into long-length artificial SSVEP signals. By incorporating a novel U-Net generator architecture and an auxiliary classifier into the network architecture, the TEGAN could produce conditioned features in the synthetic data. Additionally, we introduced a two-stage training strategy and the LeCam-divergence regularization term to regularize the training process of GAN during the network implementation. The proposed TEGAN was evaluated on two public SSVEP datasets (a 4-class dataset and a 12-class dataset). With the assistance of TEGAN, the performance of traditional frequency recognition methods and deep learning-based methods have been significantly improved under limited calibration data. And the classification performance gap of various frequency recognition methods has been narrowed. This study substantiates the feasibility of the proposed method to extend the data length for short-time SSVEP signals for developing a high-performance BCI system. The proposed GAN-based methods have the great potential of shortening the calibration time and cutting down the budget for various real-world BCI-based applications.

q-bio.NC↗

arXiv2023

T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations

In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive approaches, including recent diffusion-based approaches. For example, on HumanML3D, which is currently the largest dataset, we achieve comparable performance on the consistency between text and generated motion (R-Precision), but with FID 0.116 largely outperforming MotionDiffuse of 0.630. Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach. Our work suggests that VQ-VAE still remains a competitive approach for human motion generation.

cs.CV↗

arXiv2023

Markov Chain-Guided Graph Construction and Sampling Depth Optimization for EEG-Based Mental Disorder Detection

Graph Neural Networks (GNNs) have received considerable attention since its introduction. It has been widely applied in various fields due to its ability to represent graph structured data. However, the application of GNNs is constrained by two main issues. Firstly, the "over-smoothing" problem restricts the use of deeper network structures. Secondly, GNNs' applicability is greatly limited when nodes and edges are not clearly defined and expressed, as is the case with EEG data.In this study, we proposed an innovative approach that harnesses the distinctive properties of the graph structure's Markov Chain to optimize the sampling depth of deep graph convolution networks. We introduced a tailored method for constructing graph structures specifically designed for analyzing EEG data, alongside the development of a vertex-level GNN classification model for precise detection of mental disorders. In order to verify the method's performance, we conduct experiments on two disease datasets using a subject-independent experiment scenario. For the Schizophrenia (SZ) data, our method achieves an average accuracy of 100% using only the first 300 seconds of data from each subject. Similarly, for Major Depressive Disorder (MDD) data, the method yields average accuracies of over 99%. These experiments demonstrate the method's ability to effectively distinguish between healthy control (HC) subjects and patients with mental disorders. We believe this method shows great promise for clinical diagnosis.

q-bio.NC↗

arXiv2022

A Transformer-based deep neural network model for SSVEP classification

Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signal in the brain-computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data become urgent. In recent years, developing the methods that can work in inter-subject classification scenario has become a promising new direction. As the popular deep learning model nowadays, Transformer has excellent performance and has been used in EEG signal classification tasks. Therefore, in this study, we propose a deep learning model for SSVEP classification based on Transformer structure in inter-subject classification scenario, termed as SSVEPformer, which is the first application of the transformer to the classification of SSVEP. Inspired by previous studies, the model adopts the frequency spectrum of SSVEP data as input, and explores the spectral and spatial domain information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) is proposed to further improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12-class task; Dataset 2: 35 subjects, 40-class task) in the inter-subject classification scenario. The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate, compared with other baseline methods. The proposed model validates the feasibility of deep learning models based on Transformer structure for SSVEP classification task, and could serve as a potential model to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.

q-bio.NC↗

arXiv2022

Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation

In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions. To address MTDA, we propose a self-training strategy that employs pseudo-labels to induce cooperation among multiple domain-specific classifiers. We employ feature stylization as an efficient way to generate image views that forms an integral part of self-training. Additionally, to prevent the network from overfitting to noisy pseudo-labels, we devise a rectification strategy that leverages the predictions from different classifiers to estimate the quality of pseudo-labels. Our extensive experiments on numerous settings, based on four different semantic segmentation datasets, validate the effectiveness of the proposed self-training strategy and show that our method outperforms state-of-the-art MTDA approaches. Code available at: https://github.com/Mael-zys/CoaST

cs.CV↗

arXiv2022

Simultaneously exploring multi-scale and asymmetric EEG features for emotion recognition

In recent years, emotion recognition based on electroencephalography (EEG) has received growing interests in the brain-computer interaction (BCI) field. The neuroscience researches indicate that the left and right brain hemispheres demonstrate activity differences under different emotional activities, which could be an important principle for designing deep learning (DL) model for emotion recognition. Besides, owing to the nonstationarity of EEG signals, using convolution kernels of a single size may not sufficiently extract the abundant features for EEG classification tasks. Based on these two angles, we proposed a model termed Multi-Scales Bi-hemispheric Asymmetric Model (MSBAM) based on convolutional neural network (CNN) structure. Evaluated on the public DEAP and DREAMER datasets, MSBAM achieved over 99% accuracy for the two-class classification of low-level and high-level states in each of four emotional dimensions, i.e., arousal, valence, dominance and liking, respectively. This study further demonstrated the promising potential to design the DL model from the multi-scale characteristics of the EEG data and the neural mechanisms of the emotion cognition.

q-bio.NC↗

arXiv2022

Schizophrenia detection based on EEG using Recurrent Auto-Encoder framework

Schizophrenia (SZ) is a serious mental disorder that could seriously affect the patient's quality of life. In recent years, detection of SZ based on deep learning (DL) using electroencephalogram (EEG) has received increasing attention. In this paper, we proposed an end-to-end recurrent auto-encoder (RAE) model to detect SZ. In the RAE model, the raw data was input into one auto-encoder block, and the reconstructed data were recurrently input into the same block. The extracted code by auto-encoder block was simultaneously served as an input of a classifier block to discriminate SZ patients from healthy controls (HC). Evaluated on the dataset containing 14 SZ patients and 14 HC subjects, and the proposed method achieved an average classification accuracy of 81.81% in subject-independent experiment scenario. This study demonstrated that the structure of RAE is able to capture the differential features between SZ patients and HC subjects.

q-bio.NC↗

arXiv2020

Towards a Fast Steady-State Visual Evoked Potentials (SSVEP) Brain-Computer Interface (BCI)

Steady-state visual evoked potentials (SSVEP) brain-computer interface (BCI) provides reliable responses leading to high accuracy and information throughput. But achieving high accuracy typically requires a relatively long time window of one second or more. Various methods were proposed to improve sub-second response accuracy through subject-specific training and calibration. Substantial performance improvements were achieved with tedious calibration and subject-specific training; resulting in the user's discomfort. So, we propose a training-free method by combining spatial-filtering and temporal alignment (CSTA) to recognize SSVEP responses in sub-second response time. CSTA exploits linear correlation and non-linear similarity between steady-state responses and stimulus templates with complementary fusion to achieve desirable performance improvements. We evaluated the performance of CSTA in terms of accuracy and Information Transfer Rate (ITR) in comparison with both training-based and training-free methods using two SSVEP data-sets. We observed that CSTA achieves the maximum mean accuracy of 97.43$\pm$2.26 % and 85.71$\pm$13.41 % with four-class and forty-class SSVEP data-sets respectively in sub-second response time in offline analysis. CSTA yields significantly higher mean performance (p<0.001) than the training-free method on both data-sets. Compared with training-based methods, CSTA shows 29.33$\pm$19.65 % higher mean accuracy with statistically significant differences in time window less than 0.5 s. In longer time windows, CSTA exhibits either better or comparable performance though not statistically significantly better than training-based methods. We show that the proposed method brings advantages of subject-independent SSVEP classification without requiring training while enabling high target recognition performance in sub-second response time.

cs.LG↗

arXiv2020

Hierarchical emotion-recognition framework based on discriminative brain neural network topology and ensemble co-decision strategy

Brain neural networks characterize various information propagation patterns for different emotional states. However, the statistical features based on traditional graph theory may ignore the spacial network difference. To reveal these inherent spatial features and increase the stability of emotional recognition, we proposed a hierarchical framework that can perform the multiple emotion recognitions with the multiple emotion-related spatial network topology patterns (MESNP) by combining a supervised learning with ensemble co-decision strategy. To evaluate the performance of our proposed MESNP approach, we conduct both off-line and simulated on-line experiments with two public datasets i.e., MAHNOB and DEAP. The experiment results demonstrated that MESNP can significantly enhance the classification performance for the multiple emotions. The highest accuracies of off-line experiments for MAHNOB-HCI and DEAP achieved 99.93% (3 classes) and 83.66% (4 classes), respectively. For simulated on-line experiments, we also obtained the best classification accuracies with 100% (3 classes) for MAHNOB and 99.22% (4 classes) for DEAP by proposed MESNP. These results further proved the efficiency of MESNP for structured feature extraction in mult-classification emotional task.

q-bio.NC↗

arXiv2019

Hierarchical feature fusion framework for frequency recognition in SSVEP-based BCIs

Effective frequency recognition algorithms are critical in steady-state visual evoked potential (SSVEP) based brain-computer interfaces (BCIs). In this study, we present a hierarchical feature fusion framework which can be used to design high-performance frequency recognition methods. The proposed framework includes two primary technique for fusing features: spatial dimension fusion (SD) and frequency dimension fusion (FD). Both SD and FD fusions are obtained using a weighted strategy with a nonlinear function. To assess our novel methods, we used the correlated component analysis (CORRCA) method to investigate the efficiency and effectiveness of the proposed framework. Experimental results were obtained from a benchmark dataset of thirty-five subjects and indicate that the extended CORRCA method used within the framework significantly outperforms the original CORCCA method. Accordingly, the proposed framework holds promise to enhance the performance of frequency recognition methods in SSVEP-based BCIs.

q-bio.NC↗

arXiv2018

Reconfiguration of Brain Network between Resting-state and Oddball Paradigm

The oddball paradigm is widely applied to the investigation of multiple cognitive functions. Prior studies have explored the cortical oscillation and power spectral differing from the resting-state conduction to oddball paradigm, but whether brain networks existing the significant difference is still unclear. Our study addressed how the brain reconfigures its architecture from a resting-state condition (i.e., baseline) to P300 stimulus task in the visual oddball paradigm. In this study, electroencephalogram (EEG) datasets were collected from 24 postgraduate students, who were required to only mentally count the number of target stimulus; afterwards the functional EEG networks constructed in different frequency bands were compared between baseline and oddball task conditions to evaluate the reconfiguration of functional network in the brain. Compared to the baseline, our results showed the significantly (p < 0.05) enhanced delta/theta EEG connectivity and decreased alpha default mode network in the progress of brain reconfiguration to the P300 task. Furthermore, the reconfigured coupling strengths were demonstrated to relate to P300 amplitudes, which were then regarded as input features to train a classifier to differentiate the high and low P300 amplitudes groups with an accuracy of 77.78%. The findings of our study help us to understand the changes of functional brain connectivity from resting-state to oddball stimulus task, and the reconfigured network pattern has the potential for the selection of good subjects for P300-based brain- computer interface.

eess.SP↗

arXiv2018

Heterogeneity of Synaptic Input Connectivity Regulates Spike-based Neuronal Avalanches

Our mysterious brain is believed to operate near a non-equilibrium point and generate critical self-organized avalanches in neuronal activity. Recent experimental evidence has revealed significant heterogeneity in both synaptic input and output connectivity, but whether the structural heterogeneity participates in the regulation of neuronal avalanches remains poorly understood. By computational modelling, we predict that different types of structural heterogeneity contribute distinct effects on avalanche neurodynamics. In particular, neuronal avalanches can be triggered at an intermediate level of input heterogeneity, but heterogeneous output connectivity cannot evoke avalanche dynamics. In the criticality region, the co-emergence of multi-scale cortical activities is observed, and both the avalanche dynamics and neuronal oscillations are modulated by the input heterogeneity. Remarkably, we show similar results can be reproduced in networks with various types of in- and out-degree distributions. Overall, these findings not only provide details on the underlying circuitry mechanisms of nonrandom synaptic connectivity in the regulation of neuronal avalanches, but also inspire testable hypotheses for future experimental studies.

q-bio.NC↗