arXiv subjects

Yinuo Wang

Publications and source records attributed to Yinuo Wang.

35 records · Page 2Linked to original sources

arXiv2025

LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mamba

We introduce LocoMamba, a vision-driven cross-modal DRL framework built on selective state-space models, specifically leveraging Mamba, that achieves near-linear-time sequence modeling, effectively captures long-range dependencies, and enables efficient training with longer sequences. First, we embed proprioceptive states with a multilayer perceptron and patchify depth images with a lightweight convolutional neural network, producing compact tokens that improve state representation. Second, stacked Mamba layers fuse these tokens via near-linear-time selective scanning, reducing latency and memory footprint, remaining robust to token length and image resolution, and providing an inductive bias that mitigates overfitting. Third, we train the policy end-to-end with Proximal Policy Optimization under terrain and appearance randomization and an obstacle-density curriculum, using a compact state-centric reward that balances progress, smoothness, and safety. We evaluate our method in challenging simulated environments with static and moving obstacles as well as uneven terrain. Compared with state-of-the-art baselines, our method achieves higher returns and success rates with fewer collisions, exhibits stronger generalization to unseen terrains and obstacle densities, and improves training efficiency by converging in fewer updates under the same compute budget.

cs.RO↗

arXiv2025

PrivacyCD: Hierarchical Unlearning for Protecting Student Privacy in Cognitive Diagnosis

The need to remove specific student data from cognitive diagnosis (CD) models has become a pressing requirement, driven by users' growing assertion of their "right to be forgotten". However, existing CD models are largely designed without privacy considerations and lack effective data unlearning mechanisms. Directly applying general purpose unlearning algorithms is suboptimal, as they struggle to balance unlearning completeness, model utility, and efficiency when confronted with the unique heterogeneous structure of CD models. To address this, our paper presents the first systematic study of the data unlearning problem for CD models, proposing a novel and efficient algorithm: hierarchical importanceguided forgetting (HIF). Our key insight is that parameter importance in CD models exhibits distinct layer wise characteristics. HIF leverages this via an innovative smoothing mechanism that combines individual and layer, level importance, enabling a more precise distinction of parameters associated with the data to be unlearned. Experiments on three real world datasets show that HIF significantly outperforms baselines on key metrics, offering the first effective solution for CD models to respond to user data removal requests and for deploying high-performance, privacy preserving AI systems

cs.LG↗

arXiv2025

P-MIA: A Profiled-Based Membership Inference Attack on Cognitive Diagnosis Models

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While membership inference attacks (MIA) have been studied in various domains, their application to CDMs remains a critical research gap, leaving their privacy risks unquantified. This paper is the first to systematically investigate MIA against CDMs. We introduce a novel and realistic grey box threat model that exploits the explainability features of these platforms, where a model's internal knowledge state vectors are exposed to users through visualizations such as radar charts. We demonstrate that these vectors can be accurately reverse-engineered from such visualizations, creating a potent attack surface. Based on this threat model, we propose a profile-based MIA (P-MIA) framework that leverages both the model's final prediction probabilities and the exposed internal knowledge state vectors as features. Extensive experiments on three real-world datasets against mainstream CDMs show that our grey-box attack significantly outperforms standard black-box baselines. Furthermore, we showcase the utility of P-MIA as an auditing tool by successfully evaluating the efficacy of machine unlearning techniques and revealing their limitations.

cs.CR↗

arXiv2025

Trustworthy Medical Question Answering: An Evaluation-Centric Survey

Trustworthiness in healthcare question-answering (QA) systems is important for ensuring patient safety, clinical effectiveness, and user confidence. As large language models (LLMs) become increasingly integrated into medical settings, the reliability of their responses directly influences clinical decision-making and patient outcomes. However, achieving comprehensive trustworthiness in medical QA poses significant challenges due to the inherent complexity of healthcare data, the critical nature of clinical scenarios, and the multifaceted dimensions of trustworthy AI. In this survey, we systematically examine six key dimensions of trustworthiness in medical QA, i.e., Factuality, Robustness, Fairness, Safety, Explainability, and Calibration. We review how each dimension is evaluated in existing LLM-based medical QA systems. We compile and compare major benchmarks designed to assess these dimensions and analyze evaluation-guided techniques that drive model improvements, such as retrieval-augmented grounding, adversarial fine-tuning, and safety alignment. Finally, we identify open challenges-such as scalable expert evaluation, integrated multi-dimensional metrics, and real-world deployment studies-and propose future research directions to advance the safe, reliable, and transparent deployment of LLM-powered medical QA.

cs.CL↗

arXiv2025

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

Exploration is fundamental to reinforcement learning (RL), as it determines how effectively an agent discovers and exploits the underlying structure of its environment to achieve optimal performance. Existing exploration methods generally fall into two categories: active exploration and passive exploration. The former introduces stochasticity into the policy but struggles in high-dimensional environments, while the latter adaptively prioritizes transitions in the replay buffer to enhance exploration, yet remains constrained by limited sample diversity. To address the limitation in passive exploration, we propose Modelic Generative Exploration (MoGE), which augments exploration through the generation of under-explored critical states and synthesis of dynamics-consistent experiences through transition models. MoGE is composed of two components: (1) a diffusion-based generator that synthesizes critical states under the guidance of a utility function evaluating each state's potential influence on policy exploration, and (2) a one-step imagination world model for constructing critical transitions based on the critical states for agent learning. Our method adopts a modular formulation that aligns with the principles of off-policy learning, allowing seamless integration with existing algorithms to improve exploration without altering their core structures. Empirical results on OpenAI Gym and DeepMind Control Suite reveal that MoGE effectively bridges exploration and policy learning, leading to remarkable gains in both sample efficiency and performance across complex control tasks.

cs.AI↗

arXiv2025

Zero-Shot Multi-modal Large Language Model v.s. Supervised Deep Learning: A Comparative Study on CT-Based Intracranial Hemorrhage Subtyping

Introduction: Timely identification of intracranial hemorrhage (ICH) subtypes on non-contrast computed tomography is critical for prognosis prediction and therapeutic decision-making, yet remains challenging due to low contrast and blurring boundaries. This study evaluates the performance of zero-shot multi-modal large language models (MLLMs) compared to traditional deep learning methods in ICH binary classification and subtyping. Methods: We utilized a dataset provided by RSNA, comprising 192 NCCT volumes. The study compares various MLLMs, including GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet V2, with conventional deep learning models, including ResNet50 and Vision Transformer. Carefully crafted prompts were used to guide MLLMs in tasks such as ICH presence, subtype classification, localization, and volume estimation. Results: The results indicate that in the ICH binary classification task, traditional deep learning models outperform MLLMs comprehensively. For subtype classification, MLLMs also exhibit inferior performance compared to traditional deep learning models, with Gemini 2.0 Flash achieving an macro-averaged precision of 0.41 and a macro-averaged F1 score of 0.31. Conclusion: While MLLMs excel in interactive capabilities, their overall accuracy in ICH subtyping is inferior to deep networks. However, MLLMs enhance interpretability through language interactions, indicating potential in medical imaging analysis. Future efforts will focus on model refinement and developing more precise MLLMs to improve performance in three-dimensional medical image processing.

cs.CV↗

arXiv2025

GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation

Accurate 6D pose estimation of 3D objects is a fundamental task in computer vision, and current research typically predicts the 6D pose by establishing correspondences between 2D image features and 3D model features. However, these methods often face difficulties with textureless objects and varying illumination conditions. To overcome these limitations, we propose GS2POSE, a novel approach for 6D object pose estimation. GS2POSE formulates a pose regression algorithm inspired by the principles of Bundle Adjustment (BA). By leveraging Lie algebra, we extend the capabilities of 3DGS to develop a pose-differentiable rendering pipeline, which iteratively optimizes the pose by comparing the input image to the rendered image. Additionally, GS2POSE updates color parameters within the 3DGS model, enhancing its adaptability to changes in illumination. Compared to previous models, GS2POSE demonstrates accuracy improvements of 1.4\%, 2.8\% and 2.5\% on the T-LESS, LineMod-Occlusion and LineMod datasets, respectively.

cs.CV↗

arXiv2025

Enhanced DACER Algorithm with High Diffusion Efficiency

Due to their expressive capacity, diffusion models have shown great promise in offline RL and imitation learning. Diffusion Actor-Critic with Entropy Regulator (DACER) extended this capability to online RL by using the reverse diffusion process as a policy approximator, achieving state-of-the-art performance. However, it still suffers from a core trade-off: more diffusion steps ensure high performance but reduce efficiency, while fewer steps degrade performance. This remains a major bottleneck for deploying diffusion policies in real-time online RL. To mitigate this, we propose DACERv2, which leverages a Q-gradient field objective with respect to action as an auxiliary optimization target to guide the denoising process at each diffusion step, thereby introducing intermediate supervisory signals that enhance the efficiency of single-step diffusion. Additionally, we observe that the independence of the Q-gradient field from the diffusion time step is inconsistent with the characteristics of the diffusion process. To address this issue, a temporal weighting mechanism is introduced, allowing the model to effectively eliminate large-scale noise during the early stages and refine its outputs in the later stages. Experimental results on OpenAI Gym benchmarks and multimodal tasks demonstrate that, compared with classical and diffusion-based online RL algorithms, DACERv2 achieves higher performance in most complex control environments with only five diffusion steps and shows greater multimodality.

cs.LG↗

arXiv2025

QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning

We address vision-guided quadruped motion control with reinforcement learning (RL) and highlight the necessity of combining proprioception with vision for robust control. We propose QuadKAN, a spline-parameterized cross-modal policy instantiated with Kolmogorov-Arnold Networks (KANs). The framework incorporates a spline encoder for proprioception and a spline fusion head for proprioception-vision inputs. This structured function class aligns the state-to-action mapping with the piecewise-smooth nature of gait, improving sample efficiency, reducing action jitter and energy consumption, and providing interpretable posture-action sensitivities. We adopt Multi-Modal Delay Randomization (MMDR) and perform end-to-end training with Proximal Policy Optimization (PPO). Evaluations across diverse terrains, including both even and uneven surfaces and scenarios with static or dynamic obstacles, demonstrate that QuadKAN achieves consistently higher returns, greater distances, and fewer collisions than state-of-the-art (SOTA) baselines. These results show that spline-parameterized policies offer a simple, effective, and interpretable alternative for robust vision-guided locomotion. A repository will be made available upon acceptance.

cs.RO↗

arXiv2025

MMStencil: Optimizing High-order Stencils on Multicore CPU using Matrix Unit

Matrix-accelerated stencil computation is a hot research topic, yet its application to three-dimensional (3D) high-order stencils and HPC remains underexplored. With the emergence of matrix units on multicore CPUs, we analyze matrix-based acceleration strategies and tailor an optimal approach for 3D high-order stencils. We introduce algorithmic optimizations based on SIMD and matrix units to address strided memory accesses, alignment conflicts, and redundant accesses. We propose memory optimizations to boost on-package memory efficiency, and a novel multi-thread parallelism paradigm to overcome data-sharing challenges caused by the absence of shared data caches. MMStencil sustains consistently high hardware utilization across diverse stencil shapes and dimensions. Our DMA-based inter-NUMA communication further mitigates NUMA effects and MPI limitations in hybrid parallelism. Combining all the innovations, MMStencil outperforms state-of-the-art libraries on Nvidia A100 GPGPU by up to 2.1x. Moreover, the performance improvements translate directly to real-world HPC applications and enable RTM applications to yield 1.8x speedup versus a highly optimized industrial Nvidia A100 GPGPU version.

cs.DC↗

arXiv2025

Distributional Soft Actor-Critic with Diffusion Policy

Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional reinforcement learning algorithm called DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy representations. A multimodal distributional policy iteration framework that can converge to the optimal policy was established by introducing policy entropy and value distribution function. A diffusion value network that can accurately characterize the distribution of multi peaks was constructed by generating a set of reward samples through reverse sampling using a diffusion model. Based on this, a distributional reinforcement learning algorithm with dual diffusion of the value network and the policy network was derived. MuJoCo testing tasks demonstrate that the proposed algorithm not only learns multimodal policy, but also achieves state-of-the-art (SOTA) performance in all 9 control tasks, with significant suppression of estimation bias and total average return improvement of over 10% compared to existing mainstream algorithms. The results of real vehicle testing show that DSAC-D can accurately characterize the multimodal distribution of different driving styles, and the diffusion policy network can characterize multimodal trajectories.

cs.LG↗

arXiv2025

Deep-Learning-Assisted Highly-Accurate COVID-19 Diagnosis on Lung Computed Tomography Images

COVID-19 is a severe and acute viral disease that can cause symptoms consistent with pneumonia in which inflammation is caused in the alveolous regions of the lungs leading to a build-up of fluid and breathing difficulties. Thus, the diagnosis of COVID using CT scans has been effective in assisting with RT-PCR diagnosis and severity classifications. In this paper, we proposed a new data quality control pipeline to refine the quality of CT images based on GAN and sliding windows. Also, we use class-sensitive cost functions including Label Distribution Aware Loss(LDAM Loss) and Class-balanced(CB) Loss to solve the long-tail problem existing in datasets. Our model reaches more than 0.983 MCC in the benchmark test dataset.

eess.IV↗

arXiv2025

The Overview of Segmental Durations Modification Algorithms on Speech Signal Characteristics

This paper deeply evaluates and analyzes several mainstream algorithms that can arbitrarily modify the duration of any portion of a given speech signal without changing the essential properties (e.g., pitch contour, power spectrum, etc.) of the original signal. Arbitrary modification in this context means that the duration of any region of the signal can be changed by specifying the starting and ending time for modification or the target duration of the specified interval, which can be either a fixed value of duration in the time domain or a scaling factor of the original duration. In addition, arbitrary modification also indicates any number of intervals can be modified at the same time.

eess.AS↗

arXiv2025

MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration

Capturing voxel-wise spatial correspondence across distinct modalities is crucial for medical image analysis. However, current registration approaches are not practical enough in terms of registration accuracy and clinical applicability. In this paper, we introduce MambaMorph, a novel multi-modality deformable registration framework. Specifically, MambaMorph utilizes a Mamba-based registration module and a fine-grained, yet simple, feature extractor for efficient long-range correspondence modeling and high-dimensional feature learning, respectively. Additionally, we develop a well-annotated brain MR-CT registration dataset, SR-Reg, to address the scarcity of data in multi-modality registration. To validate MambaMorph's multi-modality registration capabilities, we conduct quantitative experiments on both our SR-Reg dataset and a public T1-T2 dataset. The experimental results on both datasets demonstrate that MambaMorph significantly outperforms the current state-of-the-art learning-based registration methods in terms of registration accuracy. Further study underscores the efficiency of the Mamba-based registration module and the lightweight feature extractor, which achieve notable registration quality while maintaining reasonable computational costs and speeds. We believe that MambaMorph holds significant potential for practical applications in medical image registration. The code for MambaMorph is available at: https://github.com/Guo-Stone/MambaMorph.

cs.CV↗

arXiv2024

Diffusion Actor-Critic with Entropy Regulator

Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function and leverages the capability of the diffusion model to fit multimodal distributions, thereby enhancing the representational capacity of the policy. Since the distribution of the diffusion policy lacks an analytical expression, its entropy cannot be determined analytically. To mitigate this, we propose a method to estimate the entropy of the diffusion policy utilizing Gaussian mixture model. Building on the estimated entropy, we can learn a parameter $α$ that modulates the degree of exploration and exploitation. Parameter $α$ will be employed to adaptively regulate the variance of the added noise, which is applied to the action output by the diffusion model. Experimental trials on MuJoCo benchmarks and a multimodal task demonstrate that the DACER algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting a stronger representational capacity of the diffusion policy.

cs.LG↗

arXiv2024

Simultaneous vibrational resonance in the amplitude and phase quadratures of an optical field based on Kerr nonlinearity

Vibrational resonance (VR) is a nonlinear phenomenon in which the system response to a weak signal can be resonantly enhanced by applying a high-frequency modulation signal with an appropriate amplitude. The majority of VR research has focused on amplifying the amplitude or intensity of the system response to a weak signal, whereas the study of the phase information of system responses in VR remains limited. Here, we investigate the VR phenomena in both amplitude and phase quadratures of an optical field in a Kerr nonlinear cavity driven by a near-resonant weak signal and a far-detuned modulation signal. Analytical and numerical results demonstrated that the resonant enhancement in the amplitude and phase quadratures of the system response to a weak signal simultaneously occurs as the amplitude of the modulation signal is varied. There is a linear relation between the amplitude and frequency of the modulation signal for achieving an optimal VR effect. Furthermore, we generalized our study to investigate the quadrature at an arbitrary phase and determined that the VR enhancement sensitively depends on the phase. Our findings not only broaden the scope of VR research by incorporating phase information but also introduces an approach for amplifying an optical field by manipulating another optical field.

physics.optics↗

arXiv2023

SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation

Segment Anything Model (SAM), a vision foundation model trained on large-scale annotations, has recently continued raising awareness within medical image segmentation. Despite the impressive capabilities of SAM on natural scenes, it struggles with performance decline when confronted with medical images, especially those involving blurry boundaries and highly irregular regions of low contrast. In this paper, a SAM-based parameter-efficient fine-tuning method, called SAMIHS, is proposed for intracranial hemorrhage segmentation, which is a crucial and challenging step in stroke diagnosis and surgical planning. Distinguished from previous SAM and SAM-based methods, SAMIHS incorporates parameter-refactoring adapters into SAM's image encoder and considers the efficient and flexible utilization of adapters' parameters. Additionally, we employ a combo loss that combines binary cross-entropy loss and boundary-sensitive loss to enhance SAMIHS's ability to recognize the boundary regions. Our experimental results on two public datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/mileswyn/SAMIHS .

eess.IV↗