arXiv subjects

Jun Li

Publications and source records attributed to Jun Li.

At least 217 records · Page 12Linked to original sources

arXiv2025

TruckV2X: A Truck-Centered Perception Dataset

Autonomous trucking offers significant benefits, such as improved safety and reduced costs, but faces unique perception challenges due to trucks' large size and dynamic trailer movements. These challenges include extensive blind spots and occlusions that hinder the truck's perception and the capabilities of other road users. To address these limitations, cooperative perception emerges as a promising solution. However, existing datasets predominantly feature light vehicle interactions or lack multi-agent configurations for heavy-duty vehicle scenarios. To bridge this gap, we introduce TruckV2X, the first large-scale truck-centered cooperative perception dataset featuring multi-modal sensing (LiDAR and cameras) and multi-agent cooperation (tractors, trailers, CAVs, and RSUs). We further investigate how trucks influence collaborative perception needs, establishing performance benchmarks while suggesting research priorities for heavy vehicle perception. The dataset provides a foundation for developing cooperative perception systems with enhanced occlusion handling capabilities, and accelerates the deployment of multi-agent autonomous trucking systems. The TruckV2X dataset is available at https://huggingface.co/datasets/XieTenghu1/TruckV2X.

cs.RO↗

arXiv2025

Queue up for takeoff: a transferable deep learning framework for flight delay prediction

Flight delays are a significant challenge in the aviation industry, causing major financial and operational disruptions. To improve passenger experience and reduce revenue loss, flight delay prediction models must be both precise and generalizable across different networks. This paper introduces a novel approach that combines Queue-Theory with a simple attention model, referred to as the Queue-Theory SimAM (QT-SimAM). To validate our model, we used data from the US Bureau of Transportation Statistics, where our proposed QT-SimAM (Bidirectional) model outperformed existing methods with an accuracy of 0.927 and an F1 score of 0.932. To assess transferability, we tested the model on the EUROCONTROL dataset. The results demonstrated strong performance, achieving an accuracy of 0.826 and an F1 score of 0.791. Ultimately, this paper outlines an effective, end-to-end methodology for predicting flight delays. The proposed model's ability to forecast delays with high accuracy across different networks can help reduce passenger anxiety and improve operational decision-making

cs.LG↗

arXiv2025

Semi-Supervised Federated Learning via Dual Contrastive Learning and Soft Labeling for Intelligent Fault Diagnosis

Intelligent fault diagnosis (IFD) plays a crucial role in ensuring the safe operation of industrial machinery and improving production efficiency. However, traditional supervised deep learning methods require a large amount of training data and labels, which are often located in different clients. Additionally, the cost of data labeling is high, making labels difficult to acquire. Meanwhile, differences in data distribution among clients may also hinder the model's performance. To tackle these challenges, this paper proposes a semi-supervised federated learning framework, SSFL-DCSL, which integrates dual contrastive loss and soft labeling to address data and label scarcity for distributed clients with few labeled samples while safeguarding user privacy. It enables representation learning using unlabeled data on the client side and facilitates joint learning among clients through prototypes, thereby achieving mutual knowledge sharing and preventing local model divergence. Specifically, first, a sample weighting function based on the Laplace distribution is designed to alleviate bias caused by low confidence in pseudo labels during the semi-supervised training process. Second, a dual contrastive loss is introduced to mitigate model divergence caused by different data distributions, comprising local contrastive loss and global contrastive loss. Third, local prototypes are aggregated on the server with weighted averaging and updated with momentum to share knowledge among clients. To evaluate the proposed SSFL-DCSL framework, experiments are conducted on two publicly available datasets and a dataset collected on motors from the factory. In the most challenging task, where only 10\% of the data are labeled, the proposed SSFL-DCSL can improve accuracy by 1.15% to 7.85% over state-of-the-art methods.

cs.LG↗

arXiv2025

MurreNet: Modeling Holistic Multimodal Interactions Between Histopathology and Genomic Profiles for Survival Prediction

Cancer survival prediction requires integrating pathological Whole Slide Images (WSIs) and genomic profiles, a challenging task due to the inherent heterogeneity and the complexity of modeling both inter- and intra-modality interactions. Current methods often employ straightforward fusion strategies for multimodal feature integration, failing to comprehensively capture modality-specific and modality-common interactions, resulting in a limited understanding of multimodal correlations and suboptimal predictive performance. To mitigate these limitations, this paper presents a Multimodal Representation Decoupling Network (MurreNet) to advance cancer survival analysis. Specifically, we first propose a Multimodal Representation Decomposition (MRD) module to explicitly decompose paired input data into modality-specific and modality-shared representations, thereby reducing redundancy between modalities. Furthermore, the disentangled representations are further refined then updated through a novel training regularization strategy that imposes constraints on distributional similarity, difference, and representativeness of modality features. Finally, the augmented multimodal features are integrated into a joint representation via proposed Deep Holistic Orthogonal Fusion (DHOF) strategy. Extensive experiments conducted on six TCGA cancer cohorts demonstrate that our MurreNet achieves state-of-the-art (SOTA) performance in survival prediction.

eess.IV↗

arXiv2025

Electric Field Induced Superconductivity in Bilayer Octagraphene

We investigate the energy bands, magnetism, and superconductivity of bilayer octagraphene with A-A stacking under a perpendicular electric field. A tight-binding model is used to analyze the band structure of the system. The doubling of the unit cell results in each band of the single layer splitting into two. We find that applying a perpendicular electric field increases the band splitting. As the electric field strength increases, the nesting of the Fermi Surface(FS) weakens, eventually disrupting the antiferromagnetic order and bilayer octagraphene exhibits superconductivity. Spin fluctuations can induce unconventional superconductivity with s+--wave pairing. Applying a perpendicular electric field to bilayer octagraphene parent weakens the nesting of the FS, ultimately killing the spin-density-wave (SDW) ordered state and transitioning it into the superconducting state, whichworks as a doping effect. We use the random-phase approximation approach to obtain the pairing eigenvalues and pairing symmetries of the perpendicular electric field-tuned bilayer octagraphene in the weak coupling limit. By tuning the strength of the perpendicular electric field, the critical interaction strength for SDW order can be modified, which in turn may promote the emergence of unconventional superconductivity.

cond-mat.supr-con↗

arXiv2025

Exploring the Wolf Approach to Constraining NIR Extinction Laws in the Corona Australis Molecular Cloud

The viability of the star count (Wolf) method is assessed as a means of constraining the near-infrared (NIR) extinction law toward the Corona Australis molecular cloud. Using deep $JHK_S$ photometry from the VISIONS survey, extinction maps with 1 arcmin spatial resolution are constructed. The derived extinction ratios are $A_J/A_H=1.73\pm0.07$, $A_H/A_{K_S}=1.70\pm0.11$, and $A_J/A_{K_S}=3.02\pm0.22$, which are consistent with Galactic literature means. Assuming a power-law form ($A_λ\propto λ^{-α}$) for the NIR extinction law, we derive indices of $α\approx 2.0$ across all wavelength combinations, with no statistically significant wavelength dependence throughout the NIR wavelength range. While spatial variations in extinction properties are tentatively observed across the cloud, concerns persist regarding the impact of photometric completeness, and the role of reference field selection. Continued research is required to refine the approach, and scrutinize the veracity of potential extinction law variations over a more expansive region of sky.

astro-ph.GA↗

arXiv2025

Loop2Net: Data-Driven Generation and Optimization of Airfoil CFD Meshes from Sparse Boundary Coordinates

In this study, an innovative intelligent optimization system for mesh quality is proposed, which is based on a deep convolutional neural network architecture, to achieve mesh generation and optimization. The core of the study is the Loop2Net generator and loss function, it predicts the mesh based on the given wing coordinates. And the model's performance is continuously optimised by two key loss functions during the training. Then discipline by adding penalties, the goal of mesh generation was finally reached.

cs.LG↗

arXiv2025

AirCANS: CFD 2D Mesh Optimisation-based Airfoil Classification and Assessment using Neural Networks

This study explores the possibilities of automating the loading, classification and assessment of Computational Fluid Dynamics (CFD) mesh data by Convolutional Neural Networks (CNNs). The research aim is finding a feasible way to quickly make classification and assessment on airfoil mesh data. For this purpose, this study designed a new framework named CFD-based airfoil Classification and Assessment Network (AirCANS) for CFD mesh data which including the data loader and improved the CNN structure to achieve our target. In our research, we found that CNNs are fully adaptable as well as understandable to CFD airfoil mesh data structures, which suggests that our hypothesis is successful and that neural networks can be used to have a greater positive impact on the CFD industry, such as it can be used to refine the mesh and accelerate the solution. This could allow CFD to spend much less time.

physics.comp-ph↗

arXiv2025

Probing Obscured Star Formation in Galaxy Clusters Using JWST Medium Band Images: 3.3$μ\rm m$ PAH Emitter Sample in Abell 2744

Star-forming galaxies in galaxy clusters play a crucial role in understanding the advanced stages of galaxy evolution within dense environments. We present a sample of 3.3$μ$m PAH-bright galaxies in the Abell 2744 (A2744) galaxy cluster. Using F430M medium band images, we select PAH emitters in the galaxy cluster, which capture the 3.3$μ$m PAH emission at the redshift of A2744. Our multi-wavelength study demonstrates consistent star formation rates (SFRs) derived from PAH emission and SED fitting, indicating the 3.3 $μ$m PAH flux estimated from medium band image alone can reveal the entirety of star formation, immune to dust obscuration. We find that the PAH emitters are located in relatively low mass surface density regions of A2744, with SFRs aligning with the field star-forming main sequence at $z=0.3$. The PAH emission morphologies show more asymmetry than that of the F444W image when asymmetry index $> 0.4$. With these results, we suggest that these star-forming galaxies in A2744 are in the stage of falling into the cluster from the field, and have not been quenched yet. We further explore a potential link between these galaxies and cosmic filaments being accreted onto the cluster, which may channel gas inflows to fuel star formation. JWST medium-band imaging provides a powerful new tool for identifying heavily dust-obscured star-forming populations. Future HI and low-J CO observations should be prioritized to resolve the cold gas kinematics and star formation processes in these systems, which would directly test the role of environmental stripping versus filamentary gas supply.

astro-ph.GA↗

arXiv2025

An improved point-to-surface contact algorithm with penalty method for peridynamics

It is significantly challenging to obtain accurate contact forces in peridynamics (PD) simulations due to the difficulty of surface particles identification, particularly for complex geometries. Here, an improved point-to-surface contact model is proposed for PD with high accuracy. First, the outer surface is identified using the eigenvalue method and then we construct a Verlet list to identify potential contact particle pairs efficiently. Subsequently, a point-to-surface contact search algorithm is utilized to determine precise contact locations with the penalty function method calculating the contact force. Finally, the accuracy of this point-to-surface contact model is validated through several representative contact examples. The results demonstrate that the point-to-surface contact model model can predict contact forces and deformations with high accuracy, aligning well with the classical Hertz contact theory solutions. This work presents a contact model for PD that automatically recognizes external surface particles and accurately calculates the contact force, which provides guidance for the study of multi-body contact as well as complex contact situations.

cs.CE↗

arXiv2025

Conditional Diffusion Model-Driven Generative Channels for Double RIS-Aided Wireless Systems

With the development of the upcoming sixth-generation networks (6G), reconfigurable intelligent surfaces (RISs) have gained significant attention due to its ability of reconfiguring wireless channels via smart reflections. However, traditional channel state information (CSI) acquisition techniques for double-RIS systems face challenges (e.g., high pilot overhead or multipath interference). This paper proposes a new channel generation method in double-RIS communication systems based on the tool of conditional diffusion model (CDM). The CDM is trained on synthetic channel data to capture channel characteristics. It addresses the limitations of traditional CSI generation methods, such as insufficient model understanding capability and poor environmental adaptability. We provide a detailed analysis of the diffusion process for channel generation, and it is validated through simulations. The simulation results demonstrate that the proposed CDM based method outperforms traditional channel acquisition methods in terms of normalized mean squared error (NMSE). This method offers a new paradigm for channel acquisition in double-RIS systems, which is expected to improve the quality of channel acquisition with low pilot overhead.

eess.SP↗

arXiv2025

PIPO: Pipelined Offloading for Efficient Inference on Consumer Devices

The high memory and computation demand of large language models (LLMs) makes them challenging to be deployed on consumer devices due to limited GPU memory. Offloading can mitigate the memory constraint but often suffers from low GPU utilization, leading to low inference efficiency. In this work, we propose a novel framework, called pipelined offloading (PIPO), for efficient inference on consumer devices. PIPO designs a fine-grained offloading pipeline, complemented with optimized data transfer and computation, to achieve high concurrency and efficient scheduling for inference. Experimental results show that compared with state-of-the-art baseline, PIPO increases GPU utilization from below 40% to over 90% and achieves up to 3.1$\times$ higher throughput, running on a laptop equipped with a RTX3060 GPU of 6GB memory.

cs.DC↗

arXiv2025

V2I-Calib++: A Multi-terminal Spatial Calibration Approach in Urban Intersections for Collaborative Perception

Urban intersections, dense with pedestrian and vehicular traffic and compounded by GPS signal obstructions from high-rise buildings, are among the most challenging areas in urban traffic systems. Traditional single-vehicle intelligence systems often perform poorly in such environments due to a lack of global traffic flow information and the ability to respond to unexpected events. Vehicle-to-Everything (V2X) technology, through real-time communication between vehicles (V2V) and vehicles to infrastructure (V2I), offers a robust solution. However, practical applications still face numerous challenges. Calibration among heterogeneous vehicle and infrastructure endpoints in multi-end LiDAR systems is crucial for ensuring the accuracy and consistency of perception system data. Most existing multi-end calibration methods rely on initial calibration values provided by positioning systems, but the instability of GPS signals due to high buildings in urban canyons poses severe challenges to these methods. To address this issue, this paper proposes a novel multi-end LiDAR system calibration method that does not require positioning priors to determine initial external parameters and meets real-time requirements. Our method introduces an innovative multi-end perception object association technique, utilizing a new Overall Distance metric (oDist) to measure the spatial association between perception objects, and effectively combines global consistency search algorithms with optimal transport theory. By this means, we can extract co-observed targets from object association results for further external parameter computation and optimization. Extensive comparative and ablation experiments conducted on the simulated dataset V2X-Sim and the real dataset DAIR-V2X confirm the effectiveness and efficiency of our method. The code for this method can be accessed at: https://github.com/MassimoQu/v2i-calib.

cs.RO↗

arXiv2025

Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning

Modern robot navigation systems encounter difficulties in diverse and complex indoor environments. Traditional approaches rely on multiple modules with small models or rule-based systems and thus lack adaptability to new environments. To address this, we developed Astra, a comprehensive dual-model architecture, Astra-Global and Astra-Local, for mobile robot navigation. Astra-Global, a multimodal LLM, processes vision and language inputs to perform self and goal localization using a hybrid topological-semantic graph as the global map, and outperforms traditional visual place recognition methods. Astra-Local, a multitask network, handles local path planning and odometry estimation. Its 4D spatial-temporal encoder, trained through self-supervised learning, generates robust 4D features for downstream tasks. The planning head utilizes flow matching and a novel masked ESDF loss to minimize collision risks for generating local trajectories, and the odometry head integrates multi-sensor inputs via a transformer encoder to predict the relative pose of the robot. Deployed on real in-house mobile robots, Astra achieves high end-to-end mission success rate across diverse indoor environments.

cs.RO↗

arXiv2025

Progressive Class-level Distillation

In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-student alignment at the logits level. Since high-confidence object classes usually dominate the distillation process, low-probability classes which also contain discriminating information are downplayed in conventional methods, leading to insufficient knowledge transfer. To address this issue, we propose a simple yet effective LD method termed Progressive Class-level Distillation (PCD). In contrast to existing methods which perform all-class ensemble distillation, our PCD approach performs stage-wise distillation for step-by-step knowledge transfer. More specifically, we perform ranking on teacher-student logits difference for identifying distillation priority from scratch, and subsequently divide the entire LD process into multiple stages. Next, bidirectional stage-wise distillation incorporating fine-to-coarse progressive learning and reverse coarse-to-fine refinement is conducted, allowing comprehensive knowledge transfer via sufficient logits alignment within separate class groups in different distillation stages. Extension experiments on public benchmarking datasets demonstrate the superiority of our method compared to state-of-the-arts for both classification and detection tasks.

cs.CV↗

arXiv2025

HelixDesign-Binder: A Scalable Production-Grade Platform for Binder Design Built on HelixFold3

Protein binder design is central to therapeutics, diagnostics, and synthetic biology, yet practical deployment remains challenging due to fragmented workflows, high computational costs, and complex tool integration. We present HelixDesign-Binder, a production-grade, high-throughput platform built on HelixFold3 that automates the full binder design pipeline, from backbone generation and sequence design to structural evaluation and multi-dimensional scoring. By unifying these stages into a scalable and user-friendly system, HelixDesign-Binder enables efficient exploration of binder candidates with favorable structural, energetic, and physicochemical properties. The platform leverages Baidu Cloud's high-performance infrastructure to support large-scale design and incorporates advanced scoring metrics, including ipTM, predicted binding free energy, and interface hydrophobicity. Benchmarking across six protein targets demonstrates that HelixDesign-Binder reliably produces diverse and high-quality binders, some of which match or exceed validated designs in predicted binding affinity. HelixDesign-Binder is accessible via an interactive web interface in PaddleHelix platform, supporting both academic research and industrial applications in antibody and protein binder development.

q-bio.BM↗

arXiv2025

Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoI

Decision Transformer (DT) has recently demonstrated strong generalizability in dynamic resource allocation within unmanned aerial vehicle (UAV) networks, compared to conventional deep reinforcement learning (DRL). However, its performance is hindered due to zero-padding for varying state dimensions, inability to manage long-term energy constraint, and challenges in acquiring expert samples for few-shot fine-tuning in new scenarios. To overcome these limitations, we propose an attention-enhanced prompt Decision Transformer (APDT) framework to optimize trajectory planning and user scheduling, aiming to minimize the average age of information (AoI) under long-term energy constraint in UAV-assisted Internet of Things (IoT) networks. Specifically, we enhance the convenional DT framework by incorporating an attention mechanism to accommodate varying numbers of terrestrial users, introducing a prompt mechanism based on short trajectory demonstrations for rapid adaptation to new scenarios, and designing a token-assisted method to address the UAV's long-term energy constraint. The APDT framework is first pre-trained on offline datasets and then efficiently generalized to new scenarios. Simulations demonstrate that APDT achieves twice faster in terms of convergence rate and reduces average AoI by $8\%$ compared to conventional DT.

eess.SP↗

arXiv2025

S2R-Bench: A Sim-to-Real Evaluation Benchmark for Autonomous Driving

Safety is a long-standing and the final pursuit in the development of autonomous driving systems, with a significant portion of safety challenge arising from perception. How to effectively evaluate the safety as well as the reliability of perception algorithms is becoming an emerging issue. Despite its critical importance, existing perception methods exhibit a limitation in their robustness, primarily due to the use of benchmarks are entierly simulated, which fail to align predicted results with actual outcomes, particularly under extreme weather conditions and sensor anomalies that are prevalent in real-world scenarios. To fill this gap, in this study, we propose a Sim-to-Real Evaluation Benchmark for Autonomous Driving (S2R-Bench). We collect diverse sensor anomaly data under various road conditions to evaluate the robustness of autonomous driving perception methods in a comprehensive and realistic manner. This is the first corruption robustness benchmark based on real-world scenarios, encompassing various road conditions, weather conditions, lighting intensities, and time periods. By comparing real-world data with simulated data, we demonstrate the reliability and practical significance of the collected data for real-world applications. We hope that this dataset will advance future research and contribute to the development of more robust perception models for autonomous driving. This dataset is released on https://github.com/adept-thu/S2R-Bench.

cs.RO↗