arXiv subjects

Yu Sheng

Publications and source records attributed to Yu Sheng.

At least 19 recordsLinked to original sources

arXiv2026

StreamAV-Bench: A Comprehensive Benchmark for Streaming Audio-Video Generation

Recent advancements in generative models are pushing video generation toward unbounded streaming audio-video generation for real-time interactive worlds. However, existing benchmarks primarily evaluate completed sequences and struggle to capture streaming properties. To bridge this gap, we introduce StreamAV-Bench, the first comprehensive benchmark tailored for streaming audio-video generation. StreamAV-Bench establishes a unified evaluation framework, including the progressive track for instruction adherence and long-horizon stability, and the interactive track for interactive response and state retention and reuse. With expert-verified evaluation cases across 32 fine-grained dimensions, we conduct an extensive evaluation of 13 representative systems. Our analysis reveals that current models suffer from temporal drift in progressive generation and responsiveness bottlenecks during interactive control. Based on a comprehensive failure analysis, we share insights to advance the development of native joint audio-video streaming models.

cs.SD↗

arXiv2026

Learning Surgical Robotic Manipulation with 3D Spatial Priors

Achieving 3D spatial awareness is crucial for surgical robotic manipulation, where precise and delicate operations are required. Existing methods either explicitly reconstruct the surgical scene prior to manipulation, or enhance multi-view features by adding wrist-mounted cameras to supplement the default stereo endoscopes. However, both paradigms suffer from notable limitations: the former easily leads to error accumulation and prevents end-to-end optimization due to its multi-stage nature, while the latter is rarely adopted in clinical practice since wrist-mounted cameras can interfere with the motion of surgical robot arms. In this work, we introduce the Spatial Surgical Transformer (SST), an end-to-end visuomotor policy that empowers surgical robots with 3D spatial awareness by directly exploring 3D spatial cues embedded in endoscopic images. First, we build Surgical3D, a large-scale photorealistic dataset containing 30K stereo endoscopic image pairs with accurate 3D geometry, addressing the scarcity of 3D data in surgical scenes. Based on Surgical3D, we finetune a powerful geometric transformer to extract robust 3D latent representations from stereo endoscopes images. These representations are then seamlessly aligned with the robot's action space via a lightweight multi-level spatial feature connector (MSFC), all within an endoscope-centric coordinate frame. Extensive real-robot experiments demonstrate that SST achieves state-of-the-art performance and strong spatial generalization on complex surgical tasks such as knot tying and ex-vivo organ dissection, representing a significant step toward practical clinical deployment. The dataset and code will be released.

cs.RO↗

arXiv2025

SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images

A major breakthrough in 3D reconstruction is the feedforward paradigm to generate pixel-wise 3D points or Gaussian primitives from sparse, unposed images. To further incorporate semantics while avoiding the significant memory and storage costs of high-dimensional semantic features, existing methods extend this paradigm by associating each primitive with a compressed semantic feature vector. However, these methods have two major limitations: (a) the naively compressed feature compromises expressiveness, affecting the model's ability to capture fine-grained semantics, and (b) the pixel-wise primitive prediction introduces redundancy in overlapping areas, causing unnecessary memory overhead. To this end, we introduce \textbf{SpatialSplat}, a feedforward framework that produces redundancy-aware Gaussians and capitalizes on a dual-field semantic representation. Particularly, with the insight that primitives within the same instance exhibit high semantic consistency, we decompose the semantic representation into a coarse feature field that encodes uncompressed semantics with minimal primitives, and a fine-grained yet low-dimensional feature field that captures detailed inter-instance relationships. Moreover, we propose a selective Gaussian mechanism, which retains only essential Gaussians in the scene, effectively eliminating redundant primitives. Our proposed Spatialsplat learns accurate semantic information and detailed instances prior with more compact 3D Gaussians, making semantic 3D reconstruction more applicable. We conduct extensive experiments to evaluate our method, demonstrating a remarkable 60\% reduction in scene representation parameters while achieving superior performance over state-of-the-art methods. The code is available at https://github.com/shengyuuu/SpatialSplat.git

cs.CV↗

arXiv2025

Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?

Recent advances in handling long sequences have facilitated the exploration of long-context in-context learning (ICL). While much of the existing research emphasizes performance improvements driven by additional in-context examples, the influence on the trustworthiness of generated responses remains underexplored. This paper addresses this gap by investigating how increased examples influence predictive uncertainty, an essential aspect in trustworthiness. We begin by systematically quantifying the uncertainty of ICL with varying shot counts, analyzing the impact of example quantity. Through uncertainty decomposition, we introduce a novel perspective on performance enhancement, with a focus on epistemic uncertainty (EU). Our results reveal that additional examples reduce total uncertainty in both simple and complex tasks by injecting task-specific knowledge, thereby diminishing EU and enhancing performance. For complex tasks, these advantages emerge only after addressing the increased noise and uncertainty associated with longer inputs. Finally, we explore the evolution of internal confidence across layers, unveiling the mechanisms driving the reduction in uncertainty.

cs.CL↗

arXiv2025

ElectricSight: 3D Hazard Monitoring for Power Lines Using Low-Cost Sensors

Protecting power transmission lines from potential hazards involves critical tasks, one of which is the accurate measurement of distances between power lines and potential threats, such as large cranes. The challenge with this task is that the current sensor-based methods face challenges in balancing accuracy and cost in distance measurement. A common practice is to install cameras on transmission towers, which, however, struggle to measure true 3D distances due to the lack of depth information. Although 3D lasers can provide accurate depth data, their high cost makes large-scale deployment impractical. To address this challenge, we present ElectricSight, a system designed for 3D distance measurement and monitoring of potential hazards to power transmission lines. This work's key innovations lie in both the overall system framework and a monocular depth estimation method. Specifically, the system framework combines real-time images with environmental point cloud priors, enabling cost-effective and precise 3D distance measurements. As a core component of the system, the monocular depth estimation method enhances the performance by integrating 3D point cloud data into image-based estimates, improving both the accuracy and reliability of the system. To assess ElectricSight's performance, we conducted tests with data from a real-world power transmission scenario. The experimental results demonstrate that ElectricSight achieves an average accuracy of 1.08 m for distance measurements and an early warning accuracy of 92%.

cs.CV↗

arXiv2025

Building-Guided Pseudo-Label Learning for Cross-Modal Building Damage Mapping

Accurate building damage assessment using bi-temporal multi-modal remote sensing images is essential for effective disaster response and recovery planning. This study proposes a novel Building-Guided Pseudo-Label Learning Framework to address the challenges of mapping building damage from pre-disaster optical and post-disaster SAR images. First, we train a series of building extraction models using pre-disaster optical images and building labels. To enhance building segmentation, we employ multi-model fusion and test-time augmentation strategies to generate pseudo-probabilities, followed by a low-uncertainty pseudo-label training method for further refinement. Next, a change detection model is trained on bi-temporal cross-modal images and damaged building labels. To improve damage classification accuracy, we introduce a building-guided low-uncertainty pseudo-label refinement strategy, which leverages building priors from the previous step to guide pseudo-label generation for damaged buildings, reducing uncertainty and enhancing reliability. Experimental results on the 2025 IEEE GRSS Data Fusion Contest dataset demonstrate the effectiveness of our approach, which achieved the highest mIoU score (54.28%) and secured first place in the competition.

cs.CV↗

arXiv2024

Topology-aware Mamba for Crack Segmentation in Structures

CrackMamba, a Mamba-based model, is designed for efficient and accurate crack segmentation for monitoring the structural health of infrastructure. Traditional Convolutional Neural Network (CNN) models struggle with limited receptive fields, and while Vision Transformers (ViT) improve segmentation accuracy, they are computationally intensive. CrackMamba addresses these challenges by utilizing the VMambaV2 with pre-trained ImageNet-1k weights as the encoder and a newly designed decoder for better performance. To handle the random and complex nature of crack development, a Snake Scan module is proposed to reshape crack feature sequences, enhancing feature extraction. Additionally, the three-branch Snake Conv VSS (SCVSS) block is proposed to target cracks more effectively. Experiments show that CrackMamba achieves state-of-the-art (SOTA) performance on the CrackSeg9k and SewerCrack datasets, and demonstrates competitive performance on the retinal vessel segmentation dataset CHASE\underline{~}DB1, highlighting its generalization capability. The code is publicly available at: {https://github.com/shengyu27/CrackMamba.}

cs.CV↗

arXiv2024

MSGField: A Unified Scene Representation Integrating Motion, Semantics, and Geometry for Robotic Manipulation

Combining accurate geometry with rich semantics has been proven to be highly effective for language-guided robotic manipulation. Existing methods for dynamic scenes either fail to update in real-time or rely on additional depth sensors for simple scene editing, limiting their applicability in real-world. In this paper, we introduce MSGField, a representation that uses a collection of 2D Gaussians for high-quality reconstruction, further enhanced with attributes to encode semantic and motion information. Specially, we represent the motion field compactly by decomposing each primitive's motion into a combination of a limited set of motion bases. Leveraging the differentiable real-time rendering of Gaussian splatting, we can quickly optimize object motion, even for complex non-rigid motions, with image supervision from only two camera views. Additionally, we designed a pipeline that utilizes object priors to efficiently obtain well-defined semantics. In our challenging dataset, which includes flexible and extremely small objects, our method achieve a success rate of 79.2% in static and 63.3% in dynamic environments for language-guided manipulation. For specified object grasping, we achieve a success rate of 90%, on par with point cloud-based methods. Code and dataset will be released at:https://shengyu724.github.io/MSGField.github.io.

cs.RO↗

arXiv2024

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons

In this paper, we investigate whether Large Language Models (LLMs) actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. Through an analysis of LLMs' internal factual recall at each reasoning step via Knowledge Neurons, we reveal that LLMs fail to harness the critical factual associations under certain circumstances. Instead, they tend to opt for alternative, shortcut-like pathways to answer reasoning questions. By manually manipulating the recall process of parametric knowledge in LLMs, we demonstrate that enhancing this recall process directly improves reasoning performance whereas suppressing it leads to notable degradation. Furthermore, we assess the effect of Chain-of-Thought (CoT) prompting, a powerful technique for addressing complex reasoning tasks. Our findings indicate that CoT can intensify the recall of factual knowledge by encouraging LLMs to engage in orderly and reliable reasoning. Furthermore, we explored how contextual conflicts affect the retrieval of facts during the reasoning process to gain a comprehensive understanding of the factual recall behaviors of LLMs. Code and data will be available soon.

cs.CL↗

arXiv2024

Multi-label Sewer Pipe Defect Recognition with Mask Attention Feature Enhancement and Label Correlation Learning

The coexistence of multiple defect categories as well as the substantial class imbalance problem significantly impair the detection of sewer pipeline defects. To solve this problem, a multi-label pipe defect recognition method is proposed based on mask attention guided feature enhancement and label correlation learning. The proposed method can achieve current approximate state-of-the-art classification performance using just 1/16 of the Sewer-ML training dataset and exceeds the current best method by 11.87\% in terms of F2 metric on the full dataset, while also proving the superiority of the model. The major contribution of this study is the development of a more efficient model for identifying and locating multiple defects in sewer pipe images for a more accurate sewer pipeline condition assessment. Moreover, by employing class activation maps, our method can accurately pinpoint multiple defect categories in the image which demonstrates a strong model interpretability. Our code is available at \href{https://github.com/shengyu27/MA-Q2L}{\textcolor{black}{https://github.com/shengyu27/MA-Q2L.}

cs.CV↗

arXiv2024

Electric-field control of the perpendicular magnetization switching in ferroelectric/ferrimagnet heterostructures

Electric field control of the magnetic state in ferrimagnets holds great promise for developing spintronic devices due to low power consumption. Here, we demonstrate a non-volatile reversal of perpendicular net magnetization in a ferrimagnet by manipulating the electric-field driven polarization within the Pb (Zr0.2Ti0.8) O3 (PZT)/CoGd heterostructure. Electron energy loss spectra and X-ray absorption spectrum directly verify that the oxygen ion migration at the PZT/CoGd interface associated with reversing the polarization causes the enhanced/reduced oxidation in CoGd. Ab initio calculations further substantiate that the migrated oxygen ions can modulate the relative magnetization of Co/Gd sublattices, facilitating perpendicular net magnetization switching. Our findings offer an approach to effectively control ferrimagnetic net magnetization, holding significant implications for ferrimagnetic spintronic applications.

cond-mat.mtrl-sci↗

arXiv2024

Rendering-Enhanced Automatic Image-to-Point Cloud Registration for Roadside Scenes

Prior point cloud provides 3D environmental context, which enhances the capabilities of monocular camera in downstream vision tasks, such as 3D object detection, via data fusion. However, the absence of accurate and automated registration methods for estimating camera extrinsic parameters in roadside scene point clouds notably constrains the potential applications of roadside cameras. This paper proposes a novel approach for the automatic registration between prior point clouds and images from roadside scenes. The main idea involves rendering photorealistic grayscale views taken at specific perspectives from the prior point cloud with the help of their features like RGB or intensity values. These generated views can reduce the modality differences between images and prior point clouds, thereby improve the robustness and accuracy of the registration results. Particularly, we specify an efficient algorithm, named neighbor rendering, for the rendering process. Then we introduce a method for automatically estimating the initial guess using only rough guesses of camera's position. At last, we propose a procedure for iteratively refining the extrinsic parameters by minimizing the reprojection error for line features extracted from both generated and camera images using Segment Anything Model (SAM). We assess our method using a self-collected dataset, comprising eight cameras strategically positioned throughout the university campus. Experiments demonstrate our method's capability to automatically align prior point cloud with roadside camera image, achieving a rotation accuracy of 0.202 degrees and a translation precision of 0.079m. Furthermore, we validate our approach's effectiveness in visual applications by substantially improving monocular 3D object detection performance.

cs.RO↗

arXiv2024

MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes

Localization and mapping are critical tasks for various applications such as autonomous vehicles and robotics. The challenges posed by outdoor environments present particular complexities due to their unbounded characteristics. In this work, we present MM-Gaussian, a LiDAR-camera multi-modal fusion system for localization and mapping in unbounded scenes. Our approach is inspired by the recently developed 3D Gaussians, which demonstrate remarkable capabilities in achieving high rendering quality and fast rendering speed. Specifically, our system fully utilizes the geometric structure information provided by solid-state LiDAR to address the problem of inaccurate depth encountered when relying solely on visual solutions in unbounded, outdoor scenarios. Additionally, we utilize 3D Gaussian point clouds, with the assistance of pixel-level gradient descent, to fully exploit the color information in photos, thereby achieving realistic rendering effects. To further bolster the robustness of our system, we designed a relocalization module, which assists in returning to the correct trajectory in the event of a localization failure. Experiments conducted in multiple scenarios demonstrate the effectiveness of our method.

cs.RO↗

arXiv2023

EdgeCalib: Multi-Frame Weighted Edge Features for Automatic Targetless LiDAR-Camera Calibration

In multimodal perception systems, achieving precise extrinsic calibration between LiDAR and camera is of critical importance. Previous calibration methods often required specific targets or manual adjustments, making them both labor-intensive and costly. Online calibration methods based on features have been proposed, but these methods encounter challenges such as imprecise feature extraction, unreliable cross-modality associations, and high scene-specific requirements. To address this, we introduce an edge-based approach for automatic online calibration of LiDAR and cameras in real-world scenarios. The edge features, which are prevalent in various environments, are aligned in both images and point clouds to determine the extrinsic parameters. Specifically, stable and robust image edge features are extracted using a SAM-based method and the edge features extracted from the point cloud are weighted through a multi-frame weighting strategy for feature filtering. Finally, accurate extrinsic parameters are optimized based on edge correspondence constraints. We conducted evaluations on both the KITTI dataset and our dataset. The results show a state-of-the-art rotation accuracy of 0.086{\deg} and a translation accuracy of 0.977 cm, outperforming existing edge-based calibration methods in both precision and robustness.

cs.CV↗

arXiv2023

Judicial Intelligent Assistant System: Extracting Events from Divorce Cases to Detect Disputes for the Judge

In formal procedure of civil cases, the textual materials provided by different parties describe the development process of the cases. It is a difficult but necessary task to extract the key information for the cases from these textual materials and to clarify the dispute focus of related parties. Currently, officers read the materials manually and use methods, such as keyword searching and regular matching, to get the target information. These approaches are time-consuming and heavily depending on prior knowledge and carefulness of the officers. To assist the officers to enhance working efficiency and accuracy, we propose an approach to detect disputes from divorce cases based on a two-round-labeling event extracting technique in this paper. We implement the Judicial Intelligent Assistant (JIA) system according to the proposed approach to 1) automatically extract focus events from divorce case materials, 2) align events by identifying co-reference among them, and 3) detect conflicts among events brought by the plaintiff and the defendant. With the JIA system, it is convenient for judges to determine the disputed issues. Experimental results demonstrate that the proposed approach and system can obtain the focus of cases and detect conflicts more effectively and efficiently comparing with existing method.

cs.CL↗

arXiv2022

Tunable Rapid Electron Transport in Titanium Oxide Thin Films

Rapid electron transport in the quantum well triggers many novel physical phenomena and becomes a critical point for the high-speed electronics. Here, we found electrical properties of the titanium oxide changed from semiconducting to metallic as the degree of oxidation decreased and Schottky quantum well was formed at the interface. We take the asymmetry interface electron scattering effect into consideration when studying the electrical transport properties of the multilayer thin films. A novel physical conductivity model for the multilayer thin films was developed. We found electron would be transferred from the low-mobility semiconducting and metallic conductive channels to the high-mobility Schottky quantum well conductive channel with an in-plane applied electric field. Electron concentration and mobility of the forming 2DEG in the Schottky quantum well could be tuned thus the nano-devices exhibited non-linear voltage-current curves. The differential resistivity of the nano-devices could decrease by two orders with increasing electric field at room temperature. Weak electron localization of electrons has been experimentally observed in our nano-devices at low temperature, which further demonstrated the existence of 2DEG in the Schottky quantum well. Our work will provide us new physics about the rapid electron transport in the multilayer thin films, and bring novel functional devices for the modern microelectronic industry.

physics.app-ph↗

arXiv2022

Electrically function switchable magnetic domain-wall memory

More-versatile memory is strongly desired for end-users to protect their information in the information era. In particular, bit-level switchable memory, from rewritable to read-only function, allows end-users to prevent any important data from being tampered with. However, no such switchable memory has been reported. We demonstrated the rewritable function can be converted into a read-only function by a sufficiently large current pulse in a U-shaped domain-wall memory composed of an asymmetric Pt/Co/Ru/AlOx heterostructure with strong Dzyaloshinskii-Moriya interaction. Wafer-scale switchable magnetic domain-wall memory arrays on 4-inch Si/SiO2 substrate were designed and fabricated. Furthermore, we confirmed the information can be stored in rewritable or read-only state at bit-level according to the security-needs of end-users. Our work not only provides a solution for personal confidential data, but also paves the way for developing multi-functional spintronic devices.

physics.app-ph↗

arXiv2022

MRI-based Multi-task Decoupling Learning for Alzheimer's Disease Detection and MMSE Score Prediction: A Multi-site Validation

Accurately detecting Alzheimer's disease (AD) and predicting mini-mental state examination (MMSE) score are important tasks in elderly health by magnetic resonance imaging (MRI). Most of the previous methods on these two tasks are based on single-task learning and rarely consider the correlation between them. Since the MMSE score, which is an important basis for AD diagnosis, can also reflect the progress of cognitive impairment, some studies have begun to apply multi-task learning methods to these two tasks. However, how to exploit feature correlation remains a challenging problem for these methods. To comprehensively address this challenge, we propose a MRI-based multi-task decoupled learning method for AD detection and MMSE score prediction. First, a multi-task learning network is proposed to implement AD detection and MMSE score prediction, which exploits feature correlation by adding three multi-task interaction layers between the backbones of the two tasks. Each multi-task interaction layer contains two feature decoupling modules and one feature interaction module. Furthermore, to enhance the generalization between tasks of the features selected by the feature decoupling module, we propose the feature consistency loss constrained feature decoupling module. Finally, in order to exploit the specific distribution information of MMSE score in different groups, a distribution loss is proposed to further enhance the model performance. We evaluate our proposed method on multi-site datasets. Experimental results show that our proposed multi-task decoupled representation learning method achieves good performance, outperforming single-task learning and other existing state-of-the-art methods.

eess.IV↗