arXiv subjects

Yushi Wang

Publications and source records attributed to Yushi Wang.

14 recordsLinked to original sources

arXiv2026

UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations

Universal speech enhancement (USE) aims to restore speech signals from diverse distortions across multiple sampling rates. We propose UniPASE, an extension of the low-hallucination PASE framework tailored for USE. At its core is DeWavLM-Omni, a unified representation-level enhancement module fine-tuned from WavLM via knowledge distillation on a large-scale supervised multi-distortion dataset. This module directly converts degraded waveforms into clean and linguistically faithful phonetic representations, ensuring robust enhancement with minimal linguistic hallucination. Based on these enhanced phonetic representations, an Adapter generates enhanced acoustic representations containing rich acoustic details, which a neural Vocoder uses to reconstruct corresponding high-fidelity 16-kHz waveforms. A PostNet then converts the waveforms to 48~kHz before resampling them to their original rates, enabling seamless handling of inputs and outputs at multiple sampling rates. Experimental results on several evaluation datasets, covering sub-tasks and full tasks, demonstrate that UniPASE achieves superior or competitive performance compared with existing state-of-the-art models. The proposed model also serves as the backbone of our submission to the URGENT 2026 Challenge, which achieved 1st place in the objective evaluation. The source code and audio demos are available at https://github.com/xiaobin-rong/unipase/.

eess.AS↗

arXiv2026

GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement

We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge. The system integrates a generative branch, which performs full-stack speech restoration in a self-supervised representation domain and reconstructs the waveform via a neural vocoder, along with a predictive branch that performs spectrogram-domain enhancement, providing complementary cues. Outputs from both branches are fused by a post-processing module, which also performs bandwidth extension to generate the enhanced waveform at 48 kHz, later downsampled to the original sampling rate. This generative-predictive fusion improves robustness and perceptual quality, achieving top performance in the blind-test phase and ranking 1st in the objective evaluation. Audio examples are available at https://xiaobin-rong.github.io/gap-urgenet_demo.

eess.AS↗

arXiv2025

AutoOdom: Learning Auto-regressive Proprioceptive Odometry for Legged Locomotion

Accurate proprioceptive odometry is fundamental for legged robot navigation in GPS-denied and visually degraded environments where conventional visual odometry systems fail. Current approaches face critical limitations: analytical filtering methods suffer from modeling uncertainties and cumulative drift, hybrid learning-filtering approaches remain constrained by their analytical components, while pure learning-based methods struggle with simulation-to-reality transfer and demand extensive real-world data collection. This paper introduces AutoOdom, a novel autoregressive proprioceptive odometry system that overcomes these challenges through an innovative two-stage training paradigm. Stage 1 employs large-scale simulation data to learn complex nonlinear dynamics and rapidly changing contact states inherent in legged locomotion, while Stage 2 introduces an autoregressive enhancement mechanism using limited real-world data to effectively bridge the sim-to-real gap. The key innovation lies in our autoregressive training approach, where the model learns from its own predictions to develop resilience against sensor noise and improve robustness in highly dynamic environments. Comprehensive experimental validation on the Booster T1 humanoid robot demonstrates that AutoOdom significantly outperforms state-of-the-art methods across all evaluation metrics, achieving 57.2% improvement in absolute trajectory error, 59.2% improvement in Umeyama-aligned error, and 36.2% improvement in relative pose error compared to the Legolas baseline. Extensive ablation studies provide critical insights into sensor modality selection and temporal modeling, revealing counterintuitive findings about IMU acceleration data and validating our systematic design choices for robust proprioceptive odometry in challenging locomotion scenarios.

cs.RO↗

arXiv2025

Numerical simulation of the dual-phase-lag heat conduction equation on a one-dimensional unbounded domain using artificial boundary condition

This paper focuses on the numerical solution of a dual-phase-lag heat conduction equation on a space unbounded domain. First, based on the Laplace transform and the Padé approximation, a high-order local artificial boundary condition is constructed for the considered problem, which effectively transforms the original problem into an initial-boundary value problem on a bounded computational domain. Subsequently, for the resulting reduced problem on the bounded domain equipped with high-order local artificial boundary, a stability result based on the $L^2$-norm is derived. Next, we develop finite difference method for the reduced problem by introducing auxiliary variable to reduce the order of time derivative. The numerical analysis demonstrates that the developed numerical scheme is unconditionally stable and possesses a second-order convergence rate in both space and time. Finally, numerical results are presented to validate the effectiveness of the proposed numerical method and the correctness of the theoretical analysis.

math.NA↗

arXiv2025

Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots

Humanoid soccer poses a representative challenge for embodied intelligence, requiring robots to coordinate agile locomotion with unreliable visual perception in dynamic environments. However, existing systems typically rely on modular pipelines that separate perception from control or assume ideal sensing, making it difficult to achieve coherent and reactive behavior under real-world perceptual limitations. In this work, we present a unified reinforcement learning-based controller that enables humanoid robots to learn vision-driven reactive soccer skills by directly coupling visual perception with locomotion control. The robot is trained in simulation to acquire soccer behaviors, and adversarial motion priors guide policy learning toward natural motion patterns. To support robust performance under imperfect sensing, we introduce an encoder-decoder architecture together with a virtual perception system that models key characteristics of onboard vision, exposing the policy to perceptual noise and detection failures during training. This design encourages the policy to internalize perceptual uncertainty and continuously adapt its motion in a closed loop. The resulting controller produces coordinated soccer behaviors using only onboard vision, including ball searching, chasing, and multidirectional kicking. It reduces ball position estimation error by 46% and shortens time-to-kick by up to 64% compared with a rule-based baseline, achieving around 90% kicking success in frontfield positions. Experiments across diverse environments and dynamic scenarios, including real RoboCup competitions, further demonstrate the robust performance of the controller. These results highlight the practical effectiveness of integrating perceptual uncertainty directly into policy learning for achieving reliable vision-driven behaviors in humanoid robots operating under real-world conditions.

cs.RO↗

arXiv2025

Preference-Conditioned Multi-Objective RL for Integrated Command Tracking and Force Compliance in Humanoid Locomotion

Humanoid locomotion requires not only accurate command tracking for navigation but also compliant responses to external forces during human interaction. Despite significant progress, existing RL approaches mainly emphasize robustness, yielding policies that resist external forces but lack compliance particularly challenging for inherently unstable humanoids. In this work, we address this by formulating humanoid locomotion as a multi-objective optimization problem that balances command tracking and external force compliance. We introduce a preference-conditioned multi-objective RL (MORL) framework that enables a single omnidirectional locomotion policy to trade off between command following and force compliance via a user-specified preference input. External forces are modeled via velocity-resistance factor for consistent reward design, and training leverages an encoder-decoder structure that infers task-relevant privileged features from deployable observations. We validate our approach in both simulation and real-world experiments on a humanoid robot. Experimental results in simulation and on hardware show that the framework trains stably and enables deployable preference-conditioned humanoid locomotion.

cs.RO↗

arXiv2025

Dual-arm Motion Generation for Repositioning Care based on Deep Predictive Learning with Somatosensory Attention Mechanism

Caregiving is a vital role for domestic robots, especially the repositioning care has immense societal value, critically improving the health and quality of life of individuals with limited mobility. However, repositioning task is a challenging area of research, as it requires robots to adapt their motions while interacting flexibly with patients. The task involves several key challenges: (1) applying appropriate force to specific target areas; (2) performing multiple actions seamlessly, each requiring different force application policies; and (3) motion adaptation under uncertain positional conditions. To address these, we propose a deep neural network (DNN)-based architecture utilizing proprioceptive and visual attention mechanisms, along with impedance control to regulate the robot's movements. Using the dual-arm humanoid robot Dry-AIREC, the proposed model successfully generated motions to insert the robot's hand between the bed and a mannequin's back without applying excessive force, and it supported the transition from a supine to a lifted-up position. The project page is here: https://sites.google.com/view/caregiving-robot-airec/repositioning

cs.RO↗

arXiv2025

Booster Gym: An End-to-End Reinforcement Learning Framework for Humanoid Robot Locomotion

Recent advancements in reinforcement learning (RL) have led to significant progress in humanoid robot locomotion, simplifying the design and training of motion policies in simulation. However, the numerous implementation details make transferring these policies to real-world robots a challenging task. To address this, we have developed a comprehensive code framework that covers the entire process from training to deployment, incorporating common RL training methods, domain randomization, reward function design, and solutions for handling parallel structures. This library is made available as a community resource, with detailed descriptions of its design and experimental results. We validate the framework on the Booster T1 robot, demonstrating that the trained policies seamlessly transfer to the physical platform, enabling capabilities such as omnidirectional walking, disturbance resistance, and terrain adaptability. We hope this work provides a convenient tool for the robotics community, accelerating the development of humanoid robots. The code can be found in https://github.com/BoosterRobotics/booster_gym.

cs.RO↗

arXiv2025

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network

Universal speech enhancement aims to handle input speech with different distortions and input formats. To tackle this challenge, we present TS-URGENet, a Three-Stage Universal, Robust, and Generalizable speech Enhancement Network. To address various distortions, the proposed system employs a novel three-stage architecture consisting of a filling stage, a separation stage, and a restoration stage. The filling stage mitigates packet loss by preliminarily filling lost regions under noise interference, ensuring signal continuity. The separation stage suppresses noise, reverberation, and clipping distortion to improve speech clarity. Finally, the restoration stage compensates for bandwidth limitation, codec artifacts, and residual packet loss distortion, refining the overall speech quality. Our proposed TS-URGENet achieved outstanding performance in the Interspeech 2025 URGENT Challenge, ranking 2nd in Track 1.

eess.AS↗

arXiv2025

Close-Fitting Dressing Assistance Based on State Estimation of Feet and Garments with Semantic-based Visual Attention

As the population continues to age, a shortage of caregivers is expected in the future. Dressing assistance, in particular, is crucial for opportunities for social participation. Especially dressing close-fitting garments, such as socks, remains challenging due to the need for fine force adjustments to handle the friction or snagging against the skin, while considering the shape and position of the garment. This study introduces a method uses multi-modal information including not only robot's camera images, joint angles, joint torques, but also tactile forces for proper force interaction that can adapt to individual differences in humans. Furthermore, by introducing semantic information based on object concepts, rather than relying solely on RGB data, it can be generalized to unseen feet and background. In addition, incorporating depth data helps infer relative spatial relationship between the sock and the foot. To validate its capability for semantic object conceptualization and to ensure safety, training data were collected using a mannequin, and subsequent experiments were conducted with human subjects. In experiments, the robot successfully adapted to previously unseen human feet and was able to put socks on 10 participants, achieving a higher success rate than Action Chunking with Transformer and Diffusion Policy. These results demonstrate that the proposed model can estimate the state of both the garment and the foot, enabling precise dressing assistance for close-fitting garments.

cs.RO↗

arXiv2025

HiFAR: Multi-Stage Curriculum Learning for High-Dynamics Humanoid Fall Recovery

Humanoid robots encounter considerable difficulties in autonomously recovering from falls, especially within dynamic and unstructured environments. Conventional control methodologies are often inadequate in addressing the complexities associated with high-dimensional dynamics and the contact-rich nature of fall recovery. Meanwhile, reinforcement learning techniques are hindered by issues related to sparse rewards, intricate collision scenarios, and discrepancies between simulation and real-world applications. In this study, we introduce a multi-stage curriculum learning framework, termed HiFAR. This framework employs a staged learning approach that progressively incorporates increasingly complex and high-dimensional recovery tasks, thereby facilitating the robot's acquisition of efficient and stable fall recovery strategies. Furthermore, it enables the robot to adapt its policy to effectively manage real-world fall incidents. We assess the efficacy of the proposed method using a real humanoid robot, showcasing its capability to autonomously recover from a diverse range of falls with high success rates, rapid recovery times, robustness, and generalization.

cs.RO↗

arXiv2025

Semantic Communication Meets Heterogeneous Network: Emerging Trends, Opportunities, and Challenges

Recent developments in machine learning (ML) techniques enable users to extract, transmit, and reproduce information semantics via ML-based semantic communication (SemCom). This significantly increases network spectral efficiency and transmission robustness. In the network, the semantic encoders and decoders among various users, based on ML, however, require collaborative updating according to new transmission tasks. The various heterogeneous characteristics of most networks in turn introduce emerging but unique challenges for semantic codec updating that are different from other general ML model updating. In this article, we first overview the key components of the SemCom system. We then discuss the unique challenges associated with semantic codec updates in heterogeneous networks. Accordingly, we point out a potential framework and discuss the pros and cons thereof. Finally, several future research directions are also discussed.

eess.SP↗

arXiv2022

Analyzing Deep Learning Based Brain Tumor Segmentation with Missing MRI Modalities

This technical report presents a comparative analysis of existing deep learning (DL) based approaches for brain tumor segmentation with missing MRI modalities. Approaches evaluated include the Adversarial Co-training Network (ACN) and a combination of mmGAN and DeepMedic. A more stable and easy-to-use version of mmGAN is also open-sourced at a GitHub repository. Using the BraTS2018 dataset, this work demonstrates that the state-of-the-art ACN performs better especially when T1c is missing. While a simple combination of mmGAN and DeepMedic also shows strong potentials when only one MRI modality is missing. Additionally, this work initiated discussions with future research directions for brain tumor segmentation with missing MRI modalities.

cs.CV↗

arXiv2021

On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models

High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML), and in particular the development of deep learning (DL). However, since the emergence of the ImageNet dataset and the AlexNet model in 2012, the size of new open-source labeled vision datasets has remained roughly constant. Consequently, only a minority of publications in the computer vision community tackle supervised learning on datasets that are orders of magnitude larger than Imagenet. In this paper, we survey computer vision research domains that study the effects of such large datasets on model performance across different vision tasks. We summarize the community's current understanding of those effects, and highlight some open questions related to training with massive datasets. In particular, we tackle: (a) The largest datasets currently used in computer vision research and the interesting takeaways from training on such datasets; (b) The effectiveness of pre-training on large datasets; (c) Recent advancements and hurdles facing synthetic datasets; (d) An overview of double descent and sample non-monotonicity phenomena; and finally, (e) A brief discussion of lifelong/continual learning and how it fares compared to learning from huge labeled datasets in an offline setting. Overall, our findings are that research on optimization for deep learning focuses on perfecting the training routine and thus making DL models less data hungry, while research on synthetic datasets aims to offset the cost of data labeling. However, for the time being, acquiring non-synthetic labeled data remains indispensable to boost performance.

cs.CV↗