arXiv subjects

Xiaoli Xu

Publications and source records attributed to Xiaoli Xu.

At least 19 recordsLinked to original sources

arXiv2026

Exploring the Performance Frontier of Compact Unified Image Generation Models

We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through systematic training engineering under a constrained computational budget. Swift-Image adopts an efficient 6B single-stream DiT and a progressive training pipeline that evolves from broad semantic coverage to higher resolution, stronger visual quality, and unified generation-editing supervision. For post-training, we employ parallel expert reinforcement learning followed by multi-teacher on-policy distillation to alleviate interference among heterogeneous objectives. We further decouple high-level reasoning from pixel-level rendering with a Prompt Enhancer that translates user requests into generator-aligned visual specifications. For efficient deployment, structural pruning and few-step distillation produce 3B and accelerated variants. Swift-Image achieves leading aggregate performance among evaluated open-source models with only 6B parameters and 243K GPU training hours; the compressed 3B model incurs nearly no loss, while few-step distillation further improves aggregate editing performance with substantially fewer sampling steps. Our study also summarizes practical lessons for architecture, data curriculum, post-training, prompt enhancement, and model compression.

cs.CV↗

arXiv2026

From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation

Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically optimize task-specific datasets in isolation. A central challenge is not only how to curate each task-specific corpus, but also how to organize heterogeneous supervision according to the dependencies among generative capabilities. We present a \textbf{capability-driven data infrastructure} that couples capability-specific supervision construction with capability-aligned curriculum scheduling. Its three specialized yet interoperable data engines build complementary relational supervision for text-image grounding, inter-image transformation, and image-knowledge association, while caption experts align T2I and editing supervision across tasks and granularities. A multi-stage curriculum jointly evolves task composition, visual-concept distribution, data quality, and image resolution along the dependency order of capability acquisition, with capability-aware evaluation closing the loop through targeted retrieval, expert construction, and gap-aware resampling. At scale, the framework curates a 440M-image T2I corpus, 120M editing pairs, and over 27M image-entity pairs. With this infrastructure, we train multimodal diffusion models at two scales from scratch, with 3B and 6B sizes respectively. We conduct quantitative evaluation on CPI-Bench, along with qualitative evaluations across diverse text-to-image and editing scenarios. Experimental results present broad visual coverage, versatile rendering, and effective transfer across generative capabilities.

cs.CV↗

arXiv2026

CPI-Bench: A Comprehensive, Practical and Intelligent Benchmark for Real-World Image Editing

With the rapid advancement of image editing models and their widespread application across various domains, there is an increasingly urgent need to deploy these model capabilities directly into real-world scenarios. However, existing benchmarks remain confined to simple single-image tasks, suffering from limited coverage dimensions and an inability to effectively differentiate performance among diverse models. Consequently, they fail to reliably evaluate model performance in complex multi-image editing, highly demanding reasoning instructions, and practical deployment settings. To address these limitations, we propose CPI-Bench, a Comprehensive, Practical and Intelligent benchmark for real-world image editing. CPI-Bench comprises three core subsets: CPI-General-Bench, which comprehensively covers diverse editing tasks and introduces multi-image editing evaluation; CPI-Practical-Bench, which focuses on high-frequency real-user application scenarios; and CPI-Intelligent-Bench, which is dedicated to evaluating capabilities in highly demanding reasoning-based editing. Evaluation results of mainstream image editing models based on CPI-Bench demonstrate that CPI-Bench enhances performance differentiation among models. It provides a comprehensive and reliable quantification of gaps in general editing capabilities, practical deployment efficacy, and advanced reasoning-based editing, offering invaluable guidance for the future optimization of image editing models. Crucially, our ranking analysis reveals that CPI-Bench achieves the highest alignment with the Arena Image Edit Leaderboard, indicating stronger consistency with public human preference rankings, serving as an effective proxy for public human evaluations.

cs.CV↗

arXiv2026

Low-Altitude UAV-Assisted Bistatic ISAC: Closed-form 3D CRLB and Coverage Analysis

This paper investigates the fundamental performance limits of three-dimensional (3D) localization in unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) systems. Specifically, a base station (BS) estimates the 3D position of a sensing target with the aid of a UAV acting as a flexible aerial anchor node. We derive a closed-form expression for the 3D Cramer-Rao lower bound (CRLB), which explicitly quantifies the achievable localization accuracy as a function of both the UAV's location and the target's position. The CRLB is shown to decompose naturally into three distinct components, arising from signal propagation delay, angular measurements, and their coupling effect, respectively. To validate the analytical results, we consider a representative orthogonal frequency-division multiplexing (OFDM)-based ISAC system and demonstrate that the derived CRLB closely predicts the performance of maximum-likelihood estimation across diverse geometric configurations and UAV mobility patterns. Furthermore, we introduce the notion of CRLB-constrained sensing coverage to characterize the spatial region within which a prescribed localization accuracy can be guaranteed. Through local boundary approximations and coverage-size evaluations, we reveal how UAV displacement, altitude, and the CRLB threshold jointly shape the extent and geometry of the reliable sensing region.

eess.SP↗

arXiv2026

CRLB and Parameter Estimation for OFDM-ISAC with Non-Uniform Sparse Resource Allocation

Integrated sensing and communication (ISAC) holds great promise in expanding the applications of wireless communication networks. However, in current communication-centric systems, the time-frequency resources available for sensing may be limited, and also usually non-uniformly and sparsely distributed across the time-frequency domain. Such a non-uniformity destroys the "thumbtack-shaped" ambiguity function of the orthogonal frequency division multiplexing (OFDM) waveform, leading to degraded sensing performance. To this end, this paper explores the parameter estimation algorithm for OFDM-ISAC systems with non-uniform sparse resource allocation. Specifically, for the single target case, we derive the closed-form Cramer-Rao lower bound (CRLB) for parameter estimation as a function of resource indices. Furthermore, we show that simply filling unused resource locations with zeros and applying the classic periodogram estimation is equivalent to maximum likelihood (ML) estimation, which is asymptotically optimal. For the multi-target case, we generate a virtual resource using the autocorrelation function of the original signal, which exhibits a significantly larger virtual bandwidth compared to the original signal, at the cost of higher peak-to-sidelobe ratio (PSLR). Simulation results demonstrate that the proposed approach outperforms the conventional periodogram method for non-uniform sparse resource allocation.

eess.SP↗

arXiv2026

Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items

Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, severe illumination variations, motion blur, and other in-the-wild conditions. Second, it delivers highly photorealistic results with fine-grained details, faithfully preserving garment texture, material properties, and structural characteristics, while largely avoiding common AI-generated artifacts. Third, beyond apparel try-on, our model supports flexible multi-image composition (up to 6 reference images) across 8 fashion categories, with coordinated control over person identity and background. Fourth, to overcome the latency bottlenecks of commercial deployment, our system is heavily optimized for inference speed, delivering near real-time generation for a seamless user experience. These capabilities are enabled by an integrated system design spanning end-to-end model architecture, a scalable data engine, robust infrastructure, and a multi-stage training paradigm. Extensive evaluation and large-scale product deployment demonstrate that Tstars-Tryon1.0 achieves leading overall performance. To support future research, we also release a comprehensive benchmark. The model has been deployed at an industrial scale on the Taobao App, serving millions of users with tens of millions of requests.

cs.CV↗

arXiv2026

Hybrid Mono- and Bi-static OFDM-ISAC via BS-UE Cooperation: Closed-Form CRLB and Coverage Analysis

This paper proposes a hybrid mono- and bi-static sensing framework, by leveraging the base station (BS) and user equipment (UE) cooperation in integrated sensing and communication (ISAC) systems. This scheme is built on 3GPP-supported sensing modes, and it does not incur any extra spectrum cost or inter-cell coordination. To reveal the fundamental performance limit of the proposed hybrid sensing mode, we derive closed-form Cram\'{e}r-Rao lower bound (CRLB) for sensing target localization and velocity estimation, as functions of target and UE positions. The results reveal that significant performance gains can be achieved over the purely mono- or bi-static sensing, especially when the BS-target-UE form a favorable geometry, which is close to a right triangle. The analytical results are validated by simulations using effective parameter estimation algorithm and weighted mean square error (MSE) fusion method. Based on the derived sensing bound, we further analyze the sensing coverage by varying the UE positions, which shows that sensing coverage first improves then degrades as the BS-UE separation increases. Furthermore, the sensing accuracy for a potential target with best UE selection is derived as a function of the UE density in the network.

cs.IT↗

arXiv2026

OpenISAC: An Open-Source Real-Time Experimentation Platform for OFDM-ISAC

Integrated sensing and communication (ISAC) is envisioned to be one of the key usage scenarios for the sixth generation (6G) mobile communication networks. While significant progresses have been achieved for the theoretical studies, the further advancement of ISAC is hampered by the lack of accessible, open-source, and real-time experimental platforms. To address this gap, we introduce OpenISAC, a versatile and high-performance open-source platform for real-time ISAC experimentation. OpenISAC utilizes orthogonal frequency division multiplexing (OFDM) waveform and implements crucial sensing functionalities, including both monostatic and bistatic delay-Doppler sensing. A key feature of our platform is a novel over-the-air (OTA) synchronization mechanism that enables robust bistatic operations without requiring a wired connection between nodes. The platform is built entirely on open-source software, leveraging the universal software radio peripheral (USRP) hardware driver (UHD) library, thus eliminating the need for any commercial licenses. It supports a wide range of software-defined radios, from the cost-effective USRP B200 series to the high-performance X400 series. The physical layer modulator and demodulator are implemented with C++ for high-speed processing, while the sensing data is streamed to a Python environment, providing a user-friendly interface for rapid prototyping and validation of sensing signal processing algorithms. With flexible parameter selection and real-time communication and sensing operation, OpenISAC serves as a powerful and accessible tool for the academic and research communities to explore and innovate within the field of OFDM-ISAC.

eess.SP↗

arXiv2026

Channel Knowledge Map Construction via Guided Flow Matching

The efficient construction of accurate channel knowledge maps (CKMs) is crucial for unleashing the full potential of environment-aware wireless networks, yet it remains a difficult ill-posed problem due to the sparsity of available location-specific channel knowledge data. Although diffusion-based methods such as denoising diffusion probabilistic models (DDPMs) have been exploited for CKM construction, they rely on iterative stochastic sampling, rendering them too slow for real-time wireless applications. To bridge the gap between high fidelity and efficient CKM construction, this letter introduces a novel framework based on linear transport guided flow matching (LT-GFM). Deviating from the noise-removal paradigm of diffusion models, our approach models the CKM generation process as a deterministic ordinary differential equation (ODE) that follows linear optimal transport paths, thereby drastically reducing the number of required inference steps. We propose a unified architecture that is applicable to not only the conventional channel gain map (CGM) construction, but also the more challenging spatial correlation map (SCM) construction. To achieve physics-informed CKM constructions, we integrate environmental semantics (e.g., building masks) for edge recovery and enforce Hermitian symmetry for property of the SCM. Simulation results verify that LT-GFM achieves superior distributional fidelity with significantly lower Fr\'echet Inception Distance (FID) and accelerates inference speed by a factor of 25 compared to DDPMs.

cs.IT↗

arXiv2025

CKM-Enabled Joint Spatial-Doppler Domain Clutter Suppression for Low-Altitude UAV ISAC

The rapid development of low-altitude economy has placed higher demands on the sensing of small-sized unmanned aerial vehicle (UAV) targets. However, the complex and dynamic low-altitude environment, like the urban and mountainous areas, makes clutter a significant factor affecting the sensing performance. Traditional clutter suppression methods based on Doppler difference or signal strength are inadequate for scenarios with dynamic clutter and slow-moving targets like low-altitude UAVs. In this paper, motivated by the concept of channel knowledge map (CKM), we propose a novel clutter suppression technique for orthogonal frequency division multiplexing (OFDM) integrated sensing and communication (ISAC) system, by leveraging a new type of CKM named clutter angle map (CLAM). CLAM is a site-specific database, containing location-specific primary clutter angles for the coverage area of the ISAC base station (BS). With CLAM, the sensing signal components corresponding to the clutter environment can be effectively removed before target detection and parameter estimation, which greatly enhances the sensing performance. Besides, to take into account the scenarios when the targets and clutters are in close directions so that pure CLAM-based spatial domain clutter suppression is no longer effective, we further propose a two-step CLAM-enabled joint spatial-Doppler domain clutter suppression algorithm. Simulation results demonstrate that the proposed technique effectively suppresses clutter and enhances target sensing performance, achieving accurate parameter estimation for sensing slow-moving low-altitude UAV targets.

eess.SP↗

arXiv2025

Data Fusion for BS-UE Cooperative MIMO-OFDM ISAC

Integrated sensing and communication (ISAC) is a promising technique for expanding the functionalities of wireless networks with enhanced spectral efficiency. The 3rd Generation Partnership Project (3GPP) has defined six basic sensing operation modes in wireless networks. To further enhance the sensing capability of wireless networks, this paper proposes a new sensing operation mode, i.e., the base station (BS) and user equipment (UE) cooperative sensing. Specifically, after decoding the communication data, the UE further processes the received signal to extract the target sensing information. We propose an efficient algorithm for fusing the sensing results obtained by the BS and UE, by exploiting the geometric relationship among BS, UE and targets as well as the expected sensing quality in the BS monostatic and BS-UE bistatic sensing. The results show that the proposed data fusion method for cooperative sensing can effectively improve the position and velocity estimation accuracy of multiple targets, and provide a new approach on the expansion of the sensing pattern.

eess.SP↗

arXiv2025

BS-1-to-N: Diffusion-Based Environment-Aware Cross-BS Channel Knowledge Map Generation for Cell-Free Networks

Channel knowledge map (CKM) inference across base stations (BSs) is the key to achieving efficient environmentaware communications. This paper proposes an environmentaware cross-BS CKM inference method called BS-1-to-N based on the generative diffusion model. To this end, we first design the BS location embedding (BSLE) method tailored for cross-BS CKM inference to embed BS location information in the feature vector of CKM. Further, we utilize the cross- and self-attention mechanism for the proposed BS-1-to-N model to respectively learn the relationships between source and target BSs, as well as that among target BSs. Therefore, given the locations of the source and target BSs, together with the source CKMs as control conditions, cross-BS CKM inference can be performed for an arbitrary number of source and target BSs. Specifically, in architectures with massive distributed nodes like cell-free networks, traditional methods of sequentially traversing each BS for CKM construction are prohibitively costly. By contrast, the proposed BS-1-to-N model is able to achieve efficient CKM inference for a target BS at any potential location based on the CKMs of source BSs. This is achieved by exploiting the fact that within a given area, different BSs share the same wireless environment that leads to their respective CKMs. Therefore, similar to multi-view synthesis, CKMs of different BSs are representations of the same wireless environment from different BS locations. By mining the implicit correlation between CKM and BS location based on the wireless environment, the proposed BS-1-to-N method achieves efficient CKM inference across BSs. We provide extensive comparisons of CKM inference between the proposed BS-1-to-N generative model versus benchmarking schemes, and provide one use case study to demonstrate its practical application for the optimization of BS deployment.

eess.SP↗

arXiv2025

Coverage Probability and Average Rate Analysis of Hybrid Cellular and Cell-free Network

Cell-free wireless networks deploy distributed access points (APs) to simultaneously serve user equipments (UEs) across the service region and are regarded as one of the most promising network architectural paradigms. Despite recent advances in the performance analysis and optimization of cellfree wireless networks, it remains an open question whether large-scale deployment of APs in existing wireless networks can cost-effectively achieve communication capacity growth. Besides, the realization of a cell-free network is considered to be a gradual long-term evolutionary process in which cell-free APs will be incrementally introduced into existing cellular networks, and form a hybrid communication network with the existing cellular base stations (BSs). Such a collaboration will bridge the gap between the established cellular network and the innovative cellfree network. Therefore, hybrid cellular and cell-free networks (HCCNs) emerge as a practical and feasible solution for advancing cell-free network development, and it is worthwhile to further explore its performance limits. This paper presents a stochastic geometry-based hybrid cellular and cell-free network model to analyze the distributions of signal and interference and reveal their mutual coupling. Specifically, in order to benefit the UEs from both the cellular BSs and the cell-free APs, a conjugate beamforming design is employed, and the aggregated signal is analyzed using moment matching. Then, the coverage probability of the hybrid network is characterized by deriving the Laplace transforms and their higher-order derivatives of interference components. Furthermore, the average achievable rate of the hybrid network over channel fading is derived based on the interference coupling analysis.

eess.SP↗

arXiv2025

A Tutorial on MIMO-OFDM ISAC: From Far-Field to Near-Field

Integrated sensing and communication (ISAC) is one of the key usage scenarios for future sixth-generation (6G) mobile communication networks, where communication and sensing (C&S) services are simultaneously provided through shared wireless spectrum, signal processing modules, hardware, and network infrastructure. Such an integration is strengthened by the technology trends in 6G, such as denser network nodes, larger antenna arrays, wider bandwidths, higher frequency bands, and more efficient utilization of spectrum and hardware resources, which incentivize and empower enhanced sensing capabilities. As the dominant waveform used in contemporary communication systems, orthogonal frequency division multiplexing (OFDM) is still expected to be a very competitive technology for 6G, rendering it necessary to thoroughly investigate the potential and challenges of OFDM ISAC. Thus, this paper aims to provide a comprehensive tutorial overview of ISAC systems enabled by large-scale multi-input multi-output (MIMO) and OFDM technologies and to discuss their fundamental principles, advantages, and enabling signal processing methods. To this end, a unified MIMO-OFDM ISAC system model is first introduced, followed by four frameworks for estimating parameters across the spatial, delay, and Doppler domains, including parallel one-domain, sequential one-domain, joint two-domain, and joint three-domain parameter estimation. Next, sensing algorithms and performance analyses are presented in detail for far-field scenarios where uniform plane wave (UPW) propagation is valid, followed by their extensions to near-field scenarios where uniform spherical wave (USW) characteristics need to be considered. Finally, this paper points out open challenges and outlines promising avenues for future research on MIMO-OFDM ISAC.

eess.SP↗

arXiv2025

How Does CP Length Affect the Sensing Range for OFDM-ISAC?

Orthogonal frequency division multiplexing (OFDM), which has been the dominating waveform for contemporary wireless communications, is also regarded as a competitive candidate for future integrated sensing and communication (ISAC) systems. Existing works on OFDM-ISAC usually assume that the maximum sensing range should be limited by the cyclic prefix (CP) length since inter-symbol interference (ISI) and inter-carrier interference (ICI) should be avoided. However, in this paper, we provide rigorous analysis to reveal that the random data embedded in OFDM-ISAC signal can actually act as a free ``mask" for ISI, which makes ISI/ICI random and hence greatly attenuated after radar signal processing. The derived signal-to-interference-plus-noise ratio (SINR) in the range profile demonstrates that the maximum sensing range of OFDM-ISAC can greatly exceed the ISI-free distance that is limited by the CP length, which is validated by simulation results. To further mitigate power degradation for long-range targets, a novel sliding window sensing method is proposed, which iteratively detects and cancels short-range targets before shifting the detection window. The shifted detection window can effectively compensate the power degradation due to insufficient CP length for long-range targets. Such results provide valuable guidance for the CP length design in OFDM-ISAC systems.

eess.SP↗

arXiv2024

An Overview of Cellular ISAC for Low-Altitude UAV: New Opportunities and Challenges

Low-altitude unmanned aerial vehicles (UAVs) are expected to play an important role in future wireless networks, either as aerial base stations (BSs) or aerial users connected to the cellular network. In addition, integrated sensing and communication (ISAC) has been identified as one of the six usage scenarios for the forthcoming sixth-generation (6G) mobile networks, aimed at improving network functionalities and realizing situational awareness of the physical world. While most existing research efforts focus on terrestrial two-dimensional (2D) communication and sensing, UAV as an aerial platform offers a new degree of freedom for designing three-dimensional (3D) air-ground (AG) ISAC networks. In this article, we provide an overview of cellular-connected UAV ISAC, by elaborating the UAV's roles as a target to be sensed and as an aerial anchor to provide sensing functionality, respectively. In particular, we pay attention to the network coverage issue and topics specific to UAV networking, emphasizing the new opportunities as well as unique challenges to be addressed.

cs.IT↗

arXiv2024

Generating CKM Using Others' Data: Cross-AP CKM Inference with Deep Learning

Channel knowledge map (CKM) is a promising paradigm shift towards environment-aware communication and sensing by providing location-specific prior channel knowledge before real-time communication. Although CKM is particularly appealing for dense networks such as cell-free networks, it remains a challenge to efficiently generate CKMs in dense networks. For a dense network with CKMs of existing access points (APs), it will be useful to efficiently generate CKMs of potentially new APs with only AP location information. The generation of inferred CKMs across APs can help dense networks achieve convenient initial CKM generation, environment-aware AP deployment, and cost-effective CKM updates. Considering that different APs in the same region share the same physical environment, there exists a natural correlation between the channel knowledge of different APs. Therefore, by mining the implicit correlation between location-specific channel knowledge, cross-AP CKM inference can be realized using data from other APs. This paper proposes a cross-AP inference method to generate CKMs of potentially new APs with deep learning. The location of the target AP is fed into the UNet model in combination with the channel knowledge of other existing APs, and supervised learning is performed based on the channel knowledge of the target AP. Based on the trained UNet and the channel knowledge of the existing APs, the CKM inference of the potentially new AP can be generated across APs. The generation results of the inferred CKM validate the feasibility and effectiveness of cross-AP CKM inference with other APs' channel knowledge.

eess.SP↗

arXiv2024

Deep Learning-Based CKM Construction with Image Super-Resolution

Channel knowledge map (CKM) is a novel technique for achieving environment awareness, and thereby improving the communication and sensing performance for wireless systems. A fundamental problem associated with CKM is how to construct a complete CKM that provides channel knowledge for a large number of locations based solely on sparse data measurements. This problem bears similarities to the super-resolution (SR) problem in image processing. In this letter, we propose an effective deep learning-based CKM construction method that leverages the image SR network known as SRResNet. Unlike most existing studies, our approach does not require any additional input beyond the sparsely measured data. In addition to the conventional path loss map construction, our approach can also be applied to construct channel angle maps (CAMs), thanks to the use of a new dataset called CKMImageNet. The numerical results demonstrate that our method outperforms interpolation-based methods such as nearest neighbour and bicubic interpolation, as well as the SRGAN method in CKM construction. Furthermore, only 1/16 of the locations need to be measured in order to achieve a root mean square error (RMSE) of 1.1 dB in path loss.

eess.SP↗