arXiv subjects

Yaqin Zhang

Publications and source records attributed to Yaqin Zhang.

15 recordsLinked to original sources

arXiv2026

DriveCode: Domain Specific Numerical Encoding for LLM-Based Autonomous Driving

Large language models (LLMs) have shown great promise for autonomous driving. However, discretizing numbers into tokens limits precise numerical reasoning, fails to reflect the positional significance of digits in the training objective, and makes it difficult to achieve both decoding efficiency and numerical precision. These limitations affect both the processing of sensor measurements and the generation of precise control commands, creating a fundamental barrier for deploying LLM-based autonomous driving systems. In this paper, we introduce DriveCode, a novel numerical encoding method that represents numbers as dedicated embeddings rather than discrete text tokens. DriveCode employs a number projector to map numbers into the language model's hidden space, enabling seamless integration with visual and textual features in a unified multimodal sequence. Evaluated on OmniDrive, DriveGPT4, and DriveGPT4-V2 datasets, DriveCode demonstrates superior performance in trajectory prediction and control signal generation, confirming its effectiveness for LLM-based autonomous driving systems.

cs.CV↗

arXiv2025

Two-stage Respiratory Motion-resolved Radial MR Image Reconstruction Using an Interpretable Deep Unrolled Network

Due to the prolonged MRI encoding process, respiratory motion can cause undesired artifacts and image blurring, degrading image quality and limiting clinical applications in abdominal and pulmonary imaging. In this work, we develop a two-stage respiratory motion-resolved radial MR image reconstruction pipeline using an interpretable deep unrolled network (MoraNet), enabling high-quality imaging under free-breathing conditions. Firstly, low-resolution images are reconstructed from the central region of successive golden-angle radial k-space to extract respiratory motion signals. The binned k-space data based on the respiratory signal are then used to reconstruct the motion-resolved high-resolution image for each motion state. The MoraNet applies nonuniform fast Fourier transform (NUFFT) to operate radial encoding and convolutional neural network (CNN) modules to conduct image regularizations. The MoraNet was trained on retrospectively acquired lung MRI images for both fully sampled and undersampled acquisitions. The performance of the proposed method was evaluated on digital CT/MRI breathing XCAT (CoMBAT) phantom data, QUASAR motion phantom data acquired from a 1.0T MRI scanner and volunteer chest data acquired from a 1.5T MRI scanner. The MoraNet pipeline was compared with motion-averaged reconstruction and a conventional compressed sensing (CS)-based method in terms of SSIM, RMSE and computation time. Simulation and experimental results demonstrated that the proposed network could provide accurate respiratory signal estimation and enable effective motion correction. Compared with the CS method, the MoraNet preserved better structural details with lower RMSE and higher SSIM values at acceleration factor of 4, and meanwhile took ten-fold faster inference time.

physics.med-ph↗

arXiv2025

DRARL: Disengagement-Reason-Augmented Reinforcement Learning for Efficient Improvement of Autonomous Driving Policy

With the increasing presence of automated vehicles on open roads under driver supervision, disengagement cases are becoming more prevalent. While some data-driven planning systems attempt to directly utilize these disengagement cases for policy improvement, the inherent scarcity of disengagement data (often occurring as a single instances) restricts training effectiveness. Furthermore, some disengagement data should be excluded since the disengagement may not always come from the failure of driving policies, e.g. the driver may casually intervene for a while. To this end, this work proposes disengagement-reason-augmented reinforcement learning (DRARL), which enhances driving policy improvement process according to the reason of disengagement cases. Specifically, the reason of disengagement is identified by a out-of-distribution (OOD) state estimation model. When the reason doesn't exist, the case will be identified as a casual disengagement case, which doesn't require additional policy adjustment. Otherwise, the policy can be updated under a reason-augmented imagination environment, improving the policy performance of disengagement cases with similar reasons. The method is evaluated using real-world disengagement cases collected by autonomous driving robotaxi. Experimental results demonstrate that the method accurately identifies policy-related disengagement reasons, allowing the agent to handle both original and semantically similar cases through reason-augmented training. Furthermore, the approach prevents the agent from becoming overly conservative after policy adjustments. Overall, this work provides an efficient way to improve driving policy performance with disengagement cases.

cs.RO↗

arXiv2025

InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer

End-to-end autonomous driving with its holistic optimization capabilities, has gained increasing traction in academia and industry. Vectorized representations, which preserve instance-level topological information while reducing computational overhead, have emerged as a promising paradigm. While existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points, resulting in geometrically inconsistent outputs (e.g., fragmented HD map elements or oscillatory trajectories). To address these limitations, we propose InVDriver, a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers, thereby enhancing planning accuracy and trajectory smoothness. Across all core modules, i.e., perception, prediction, and planning, InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions, enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise. Experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance, surpassing prior methods in both accuracy and safety, while maintaining high computational efficiency. Our work validates that explicit modeling of intra-instance geometric coherence is critical for advancing vectorized autonomous driving systems, bridging the gap between theoretical advantages of end-to-end frameworks and practical deployment requirements.

cs.RO↗

arXiv2025

A Kolmogorov High Order Deep Neural Network for High Frequency Partial Differential Equations in High Dimensions

This paper proposes a Kolmogorov high order deep neural network (K-HOrderDNN) for solving high-dimensional partial differential equations (PDEs), which improves the high order deep neural networks (HOrderDNNs). HOrderDNNs have been demonstrated to outperform conventional DNNs for high frequency problems by introducing a nonlinear transformation layer consisting of $(p+1)^d$ basis functions. However, the number of basis functions grows exponentially with the dimension $d$, which results in the curse of dimensionality (CoD). Inspired by the Kolmogorov superposition theorem (KST), which expresses a multivariate function as superpositions of univariate functions and addition, K-HOrderDNN utilizes a HOrderDNN to efficiently approximate univariate inner functions instead of directly approximating the multivariate function, reducing the number of introduced basis functions to $d(p+1)$. We theoretically demonstrate that CoD is mitigated when target functions belong to a dense subset of continuous multivariate functions. Extensive numerical experiments show that: for high-dimensional problems ($d$=10, 20, 50) where HOrderDNNs($p>1$) are intractable, K-HOrderDNNs($p>1$) exhibit remarkable performance. Specifically, when $d=10$, K-HOrderDNN($p=7$) achieves an error of 4.40E-03, two orders of magnitude lower than that of HOrderDNN($p=1$) (see Table 10); for high frequency problems, K-HOrderDNNs($p>1$) can achieve higher accuracy with fewer parameters and faster convergence rates compared to HOrderDNNs (see Table 8).

math.NA↗

arXiv2024

Adaptive Basis-inspired Deep Neural Network for Solving Partial Differential Equations with Localized Features

This paper proposes an Adaptive Basis-inspired Deep Neural Network (ABI-DNN) for solving partial differential equations with localized phenomena such as sharp gradients and singularities. Like the adaptive finite element method, ABI-DNN incorporates an iteration of "solve, estimate, mark, enhancement", which automatically identifies challenging regions and adds new neurons to enhance its capability. A key challenge is to force new neurons to focus on identified regions with limited understanding of their roles in approximation. To address this, we draw inspiration from the finite element basis function and construct the novel Basis-inspired Block (BI-block), to help understand the contribution of each block. With the help of the BI-block and the famous Kolmogorov Superposition Theorem, we first develop a novel fixed network architecture named the Basis-inspired Deep Neural Network (BI-DNN), and then integrate it into the aforementioned adaptive framework to propose the ABI-DNN. Extensive numerical experiments demonstrate that both BI-DNN and ABI-DNN can effectively capture the challenging singularities in target functions. Compared to PINN, BI-DNN attains significantly lower relative errors with a similar number of trainable parameters. When a specified tolerance is set, ABI-DNN can adaptively learn an appropriate architecture that achieves an error comparable to that of BI-DNN with the same structure.

math.NA↗

arXiv2024

RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image

The generation of high-quality 3D car assets is essential for various applications, including video games, autonomous driving, and virtual reality. Current 3D generation methods utilizing NeRF or 3D-GS as representations for 3D objects, generate a Lambertian object under fixed lighting and lack separated modelings for material and global illumination. As a result, the generated assets are unsuitable for relighting under varying lighting conditions, limiting their applicability in downstream tasks. To address this challenge, we propose a novel relightable 3D object generative framework that automates the creation of 3D car assets, enabling the swift and accurate reconstruction of a vehicle's geometry, texture, and material properties from a single input image. Our approach begins with introducing a large-scale synthetic car dataset comprising over 1,000 high-precision 3D vehicle models. We represent 3D objects using global illumination and relightable 3D Gaussian primitives integrating with BRDF parameters. Building on this representation, we introduce a feed-forward model that takes images as input and outputs both relightable 3D Gaussians and global illumination parameters. Experimental results demonstrate that our method produces photorealistic 3D car assets that can be seamlessly integrated into road scenes with different illuminations, which offers substantial practical benefits for industrial applications.

cs.CV↗

arXiv2024

Policy Bifurcation in Safe Reinforcement Learning

Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems. Existing studies in safe RL implicitly assume continuity in policy functions, where policies map states to actions in a smooth, uninterrupted manner; however, our research finds that in some scenarios, the feasible policy should be discontinuous or multi-valued, interpolating between discontinuous local optima can inevitably lead to constraint violations. We are the first to identify the generating mechanism of such a phenomenon, and employ topological analysis to rigorously prove the existence of policy bifurcation in safe RL, which corresponds to the contractibility of the reachable tuple. Our theorem reveals that in scenarios where the obstacle-free state space is non-simply connected, a feasible policy is required to be bifurcated, meaning its output action needs to change abruptly in response to the varying state. To train such a bifurcated policy, we propose a safe RL algorithm called multimodal policy optimization (MUPO), which utilizes a Gaussian mixture distribution as the policy output. The bifurcated behavior can be achieved by selecting the Gaussian component with the highest mixing coefficient. Besides, MUPO also integrates spectral normalization and forward KL divergence to enhance the policy's capability of exploring different modes. Experiments with vehicle control tasks show that our algorithm successfully learns the bifurcated policy and ensures satisfying safety, while a continuous policy suffers from inevitable constraint violations.

cs.LG↗

arXiv2024

AutoDroid: LLM-powered Task Automation in Android

Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalability due to the limited language understanding ability and the non-trivial manual efforts required from developers or end-users. The recent advance of large language models (LLMs) in language understanding and reasoning inspires us to rethink the problem from a model-centric perspective, where task preparation, comprehension, and execution are handled by a unified language model. In this work, we introduce AutoDroid, a mobile task automation system capable of handling arbitrary tasks on any Android application without manual efforts. The key insight is to combine the commonsense knowledge of LLMs and domain-specific knowledge of apps through automated dynamic analysis. The main components include a functionality-aware UI representation method that bridges the UI with the LLM, exploration-based memory injection techniques that augment the app-specific domain knowledge of LLM, and a multi-granularity query optimization module that reduces the cost of model inference. We integrate AutoDroid with off-the-shelf LLMs including online GPT-4/GPT-3.5 and on-device Vicuna, and evaluate its performance on a new benchmark for memory-augmented Android task automation with 158 common tasks. The results demonstrated that AutoDroid is able to precisely generate actions with an accuracy of 90.9%, and complete tasks with a success rate of 71.3%, outperforming the GPT-4-powered baselines by 36.4% and 39.7%. The demo, benchmark suites, and source code of AutoDroid will be released at url{https://autodroid-sys.github.io/}.

cs.AI↗

arXiv2023

6G Network Operation Support System

6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network security, etc. 6G will realize the transition from serving people and people-things communication to supporting the efficient connection of intelligent agents, and comprehensively leading the digital, intelligent and green transformation of the economy and the society. As the core support system for mobile communication network, 6G OSS needs to achieve high-level network automation, intelligence and digital twinning capabilities to achieve end-to-end autonomous network operation and maintenance, support the operation of typical 6G business scenarios and play a greater social responsibility in the fields of environment, society, and governance (ESG).This paper provides a detailed introduction to the overall vision, potential key technologies, and functional architecture of 6G OSS . It also presents an evolutionary roadmap and technological prospects for the OSS from 5G to 6G.

cs.NI↗

arXiv2023

AIGC Empowering Telecom Sector White Paper_chinese

In the global craze of GPT, people have deeply realized that AI, as a transformative technology and key force in economic and social development, will bring great leaps and breakthroughs to the global industry and profoundly influence the future world competition pattern. As the builder and operator of information and communication infrastructure, the telecom sector provides infrastructure support for the development of AI, and even takes the lead in the implementation of AI applications. How to enable the application of AIGC (GPT) and implement AIGC in the telecom sector are questions that telecom practitioners must ponder and answer. Through the study of GPT, a typical representative of AIGC, the authors have analyzed how GPT empowers the telecom sector in the form of scenarios, discussed the gap between the current GPT general model and telecom services, proposed for the first time a Telco Augmented Cognition capability system, provided answers to how to construct a telecom service GPT in the telecom sector, and carried out various practices. Our counterparts in the industry are expected to focus on collaborative innovation around telecom and AI, build an open and shared innovation ecosystem, promote the deep integration of AI and telecom sector, and accelerate the construction of next-generation information infrastructure, in an effort to facilitate the digital transformation of the economy and society.

cs.AI↗

arXiv2023

6G Network Business Support System

6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network security, etc. 6G will realize the transition from serving people and people-things communication to supporting the efficient connection of intelligent agents, and comprehensively leading the digital, intelligent and green transformation of the economy and the society. As the core support system for mobile communication network, 6 6G BSS need to integrate with new business models brought about by the development of the next-generation Internet and IT, upgrade from "network-centric" to "business and service centric" and "customer-centric". 6G OSS and BSS systems need to strengthen their integration to improve the operational efficiency and benefits of customers by connecting the digital intelligence support capabilities on both sides of supply and demand. This paper provides a detailed introduction to the overall vision, potential key technologies, and functional architecture of 6G BSS systems. It also presents an evolutionary roadmap and technological prospects for the BSS systems from 5G to 6G.

cs.AI↗

arXiv2021

The Next Decade of Telecommunications Artificial Intelligence

It has been an exciting journey since the mobile communications and artificial intelligence were conceived 37 years and 64 years ago. While both fields evolved independently and profoundly changed communications and computing industries, the rapid convergence of 5G and deep learning is beginning to significantly transform the core communication infrastructure, network management and vertical applications. The paper first outlines the individual roadmaps of mobile communications and artificial intelligence in the early stage, with a concentration to review the era from 3G to 5G when AI and mobile communications started to converge. With regard to telecommunications artificial intelligence, the paper further introduces in detail the progress of artificial intelligence in the ecosystem of mobile communications. The paper then summarizes the classifications of AI in telecom ecosystems along with its evolution paths specified by various international telecommunications standardization bodies. Towards the next decade, the paper forecasts the prospective roadmap of telecommunications artificial intelligence. In line with 3GPP and ITU-R timeline of 5G & 6G, the paper further explores the network intelligence following 3GPP and ORAN routes respectively, experience and intention driven network management and operation, network AI signalling system, intelligent middle-office based BSS, intelligent customer experience management and policy control driven by BSS and OSS convergence, evolution from SLA to ELA, and intelligent private network for verticals. The paper is concluded with the vision that AI will reshape the future B5G or 6G landscape and we need pivot our R&D, standardizations, and ecosystem to fully take the unprecedented opportunities.

cs.NI↗

arXiv2021

The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion

Deep learning techniques have made an increasing impact on the field of remote sensing. However, deep neural networks based fusion of multimodal data from different remote sensors with heterogenous characteristics has not been fully explored, due to the lack of availability of big amounts of perfectly aligned multi-sensor image data with diverse scenes of high resolutions, especially for synthetic aperture radar (SAR) data and optical imagery. To promote the development of deep learning based SAR-optical fusion approaches, we release the QXS-SAROPT dataset, which contains 20,000 pairs of SAR-optical image patches. We obtain the SAR patches from SAR satellite GaoFen-3 images and the optical patches from Google Earth images. These images cover three port cities: San Diego, Shanghai and Qingdao. Here, we present a detailed introduction of the construction of the dataset, and show its two representative exemplary applications, namely SAR-optical image matching and SAR ship detection boosted by cross-modal information from optical images. As a large open SAR-optical dataset with multiple scenes of a high resolution, we believe QXS-SAROPT will be of potential value for further research in SAR-optical data fusion technology based on deep learning.

eess.IV↗

arXiv2021

Boosting ship detection in SAR images with complementary pretraining techniques

Deep learning methods have made significant progress in ship detection in synthetic aperture radar (SAR) images. The pretraining technique is usually adopted to support deep neural networks-based SAR ship detectors due to the scarce labeled SAR images. However, directly leveraging ImageNet pretraining is hardly to obtain a good ship detector because of different imaging perspective and geometry. In this paper, to resolve the problem of inconsistent imaging perspective between ImageNet and earth observations, we propose an optical ship detector (OSD) pretraining technique, which transfers the characteristics of ships in earth observations to SAR images from a large-scale aerial image dataset. On the other hand, to handle the problem of different imaging geometry between optical and SAR images, we propose an optical-SAR matching (OSM) pretraining technique, which transfers plentiful texture features from optical images to SAR images by common representation learning on the optical-SAR matching task. Finally, observing that the OSD pretraining based SAR ship detector has a better recall on sea area while the OSM pretraining based SAR ship detector can reduce false alarms on land area, we combine the predictions of the two detectors through weighted boxes fusion to further improve detection results. Extensive experiments on four SAR ship detection datasets and two representative CNN-based detection benchmarks are conducted to show the effectiveness and complementarity of the two proposed detectors, and the state-of-the-art performance of the combination of the two detectors. The proposed method won the sixth place of ship detection in SAR images in 2020 Gaofen challenge.

cs.CV↗