arXiv subjects

Xiangyu Li

Publications and source records attributed to Xiangyu Li.

At least 109 records · Page 6Linked to original sources

arXiv2025

Event-based multi-view photogrammetry for high-dynamic, high-velocity target measurement

The characterization of mechanical properties for high-dynamic, high-velocity target motion is essential in industries. It provides crucial data for validating weapon systems and precision manufacturing processes etc. However, existing measurement methods face challenges such as limited dynamic range, discontinuous observations, and high costs. This paper presents a new approach leveraging an event-based multi-view photogrammetric system, which aims to address the aforementioned challenges. First, the monotonicity in the spatiotemporal distribution of events is leveraged to extract the target's leading-edge features, eliminating the tailing effect that complicates motion measurements. Then, reprojection error is used to associate events with the target's trajectory, providing more data than traditional intersection methods. Finally, a target velocity decay model is employed to fit the data, enabling accurate motion measurements via ours multi-view data joint computation. In a light gas gun fragment test, the proposed method showed a measurement deviation of 4.47% compared to the electromagnetic speedometer.

cs.CV↗

arXiv2025

SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment

Citations are crucial in scientific research articles as they highlight the connection between the current study and prior work. However, this process is often time-consuming for researchers. In this study, we propose the SciRGC framework, which aims to automatically recommend citation articles and generate citation sentences for citation locations within articles. The framework addresses two key challenges in academic citation generation: 1) how to accurately identify the author's citation intent and find relevant citation papers, and 2) how to generate high-quality citation sentences that align with human preferences. We enhance citation recommendation accuracy in the citation article recommendation module by incorporating citation networks and sentiment intent, and generate reasoning-based citation sentences in the citation sentence generation module by using the original article abstract, local context, citation intent, and recommended articles as inputs. Additionally, we propose a new evaluation metric to fairly assess the quality of generated citation sentences. Through comparisons with baseline models and ablation experiments, the SciRGC framework not only improves the accuracy and relevance of citation recommendations but also ensures the appropriateness of the generated citation sentences in context, providing a valuable tool for interdisciplinary researchers.

cs.DL↗

arXiv2025

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint

Recent work has demonstrated the remarkable potential of Large Language Models (LLMs) in test-time scaling. By making models think before answering, they are able to achieve much higher accuracy with extra inference computation. However, in many real-world scenarios, models are used under time constraints, where an answer should be given within a certain output length. It is unclear whether and how the reasoning ability of different LLMs remain effective under strict constraints. We take a first look at this problem by conducting an in-depth empirical study. Specifically, we test 30 LLMs on common reasoning datasets under a wide range of output length budgets, and we analyze the correlation between the inference accuracy and various properties including model type, model size, prompt style, etc. We also consider the mappings between token budgets and actual on-device latency budgets. The results have demonstrated several interesting findings regarding the budget-aware LLM reasoning ability that differ from the unconstrained situation, e.g. the optimal choices of either model size or prompt style change under different budgets. These findings offer timely evaluation to this area and practical guidance for users to deploy LLMs under real-world latency constraints.

cs.AI↗

arXiv2025

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising direction. However, the numerous denoising steps in the robotic diffusion policy and the more dynamic, open-world nature of traffic scenes pose substantial challenges for generating diverse driving actions at a real-time speed. To address these challenges, we propose a novel truncated diffusion policy that incorporates prior multi-mode anchors and truncates the diffusion schedule, enabling the model to learn denoising from anchored Gaussian distribution to the multi-mode driving action distribution. Additionally, we design an efficient cascade diffusion decoder for enhanced interaction with conditional scene context. The proposed model, DiffusionDrive, demonstrates 10$\times$ reduction in denoising steps compared to vanilla diffusion policy, delivering superior diversity and quality in just 2 steps. On the planning-oriented NAVSIM dataset, with the aligned ResNet-34 backbone, DiffusionDrive achieves 88.1 PDMS without bells and whistles, setting a new record, while running at a real-time speed of 45 FPS on an NVIDIA 4090. Qualitative results on challenging scenarios further confirm that DiffusionDrive can robustly generate diverse plausible driving actions. Code and model will be available at https://github.com/hustvl/DiffusionDrive.

cs.CV↗

arXiv2025

Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson's Disease Screening in OCT

Parkinson's disease (PD) is a prevalent neurodegenerative disorder globally. The eye's retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness.

eess.IV↗

arXiv2025

Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal

High-fidelity imaging is crucial for the successful safety supervision and intelligent deployment of vision-based measurement systems (VBMS). It ensures high-quality imaging in VBMS, which is fundamental for reliable visual measurement and analysis. However, imaging quality can be significantly impaired by adverse weather conditions, particularly rain, leading to blurred images and reduced contrast. Such impairments increase the risk of inaccurate evaluations and misinterpretations in VBMS. To address these limitations, we propose an Expectation Maximization Reconstruction Transformer (EMResformer) for single image rain streak removal. The EMResformer retains the key self-attention values for feature aggregation, enhancing local features to produce superior image reconstruction. Specifically, we propose an Expectation Maximization Block seamlessly integrated into the single image rain streak removal network, enhancing its ability to eliminate superfluous information and restore a cleaner background image. Additionally, to further enhance local information for improved detail rendition, we introduce a Local Model Residual Block, which integrates two local model blocks along with a sequence of convolutions and activation functions. This integration synergistically facilitates the extraction of more pertinent features for enhanced single image rain streak removal. Extensive experiments validate that our proposed EMResformer surpasses current state-of-the-art single image rain streak removal methods on both synthetic and real-world datasets, achieving an improved balance between model complexity and single image deraining performance. Furthermore, we evaluate the effectiveness of our method in VBMS scenarios, demonstrating that high-quality imaging significantly improves the accuracy and reliability of VBMS tasks.

cs.CV↗

arXiv2025

A Network Flow Approach to Optimal Scheduling in Supply Chain Logistics

In the evolving digital landscape, network flow models have transcended traditional applications to become integral in diverse sectors, including supply chain management. This research develops a robust network flow model for semiconductor wafer supply chains, optimizing resource allocation and addressing maximum flow challenges in production and logistics. The model incorporates the stochastic nature of wafer batch transfers and employs a dual-layer optimization framework to reduce variability and exceedance probabilities in finished goods. Empirical comparisons reveal significant enhancements in cost efficiency, productivity, and resource utilization, with a 20% reduction in time and production costs, and a 10% increase in transportation and storage capacities. The model's efficacy is underscored by a 15% decrease in transportation time and a 6700 kg increase in total capacity, demonstrating its capability to resolve logistical bottlenecks in semiconductor manufacturing. This study concludes that network flow models are a potent tool for optimizing supply chain logistics, offering a 23% improvement in resource utilization and a 13% boost in accuracy. The findings provide valuable insights for supply chain logistics optimization.

math.OC↗

arXiv2025

Advancing Multi-Connectivity in Satellite-Terrestrial Integrated Networks: Architectures, Challenges, and Applications

Multi-connectivity (MC) in satellite-terrestrial integrated networks (STINs), included in the Third-Generation Partnership Project (3GPP) standards, is regarded as a promising technology for future networks, especially the non-terrestrial network (NTN). The significant advantages of MC in improving coverage, communication, and sensing through satellite-terrestrial collaboration have sparked widespread interest. This article introduces three fundamental deployment architectures of MC systems in STINs, including multi-satellite, single-satellite single-base-station, and multi-satellite multi-base-station configurations. Considering the emerging but still evolving satellite networking, we explore system design challenges such as satellite networking schemes, such as cell-free and multi-tier satellite networks. Subsequently, key technical challenges severely influencing the quality of mutual communications, including beamforming, channel estimation, and synchronization, are discussed. Furthermore, typical applications such as coverage enhancement, traffic offloading, collaborative sensing, and low-altitude communication are demonstrated, followed by a case study comparing coverage performance in MC and single-connectivity (SC) configurations. Several essential future research directions for MC in STINs are presented to facilitate further exploration.

eess.SP↗

arXiv2025

HedgeAgents: A Balanced-aware Multi-agent Financial Trading System

As automated trading gains traction in the financial market, algorithmic investment strategies are increasingly prominent. While Large Language Models (LLMs) and Agent-based models exhibit promising potential in real-time market analysis and trading decisions, they still experience a significant -20% loss when confronted with rapid declines or frequent fluctuations, impeding their practical application. Hence, there is an imperative to explore a more robust and resilient framework. This paper introduces an innovative multi-agent system, HedgeAgents, aimed at bolstering system robustness via ``hedging'' strategies. In this well-balanced system, an array of hedging agents has been tailored, where HedgeAgents consist of a central fund manager and multiple hedging experts specializing in various financial asset classes. These agents leverage LLMs' cognitive capabilities to make decisions and coordinate through three types of conferences. Benefiting from the powerful understanding of LLMs, our HedgeAgents attained a 70% annualized return and a 400% total return over a period of 3 years. Moreover, we have observed with delight that HedgeAgents can even formulate investment experience comparable to those of human experts (https://hedgeagents.github.io/).

cs.MA↗

arXiv2025

Single-Impulse Reachable Set in Arbitrary Dynamics Using Polynomials

This paper presents a method to determine the reachable set (RS) of spacecraft after a single velocity impulse with an arbitrary direction, which is appropriate for the RS in both the state and observation spaces under arbitrary dynamics, extending the applications of current RS methods from two-body to arbitrary dynamics. First, the single-impulse RS model is generalized as a family of two-variable parameterized polynomials in the differential algebra scheme. Then, using the envelope theory, the boundary of RS is identified by solving the envelope equation. A framework is proposed to reduce the complexity of solving the envelope equation by converting it to the problem of searching the root of a one-variable polynomial. Moreover, a high-order local polynomial approximation for the RS envelope is derived to improve computational efficiency. The method successfully determines the RSs of two near-rectilinear halo orbits in the cislunar space. Simulation results show that the RSs in both state and observation spaces can be accurately approximated under the three-body dynamics, with relative errors of less than 0.0658%. In addition, using the local polynomial approximation, the computational time for solving the envelope equation is reduced by more than 84%.

astro-ph.IM↗

arXiv2025

MedFILIP: Medical Fine-grained Language-Image Pre-training

Medical vision-language pretraining (VLP) that leverages naturally-paired medical image-report data is crucial for medical image analysis. However, existing methods struggle to accurately characterize associations between images and diseases, leading to inaccurate or incomplete diagnostic results. In this work, we propose MedFILIP, a fine-grained VLP model, introduces medical image-specific knowledge through contrastive learning, specifically: 1) An information extractor based on a large language model is proposed to decouple comprehensive disease details from reports, which excels in extracting disease deals through flexible prompt engineering, thereby effectively reducing text complexity while retaining rich information at a tiny cost. 2) A knowledge injector is proposed to construct relationships between categories and visual attributes, which help the model to make judgments based on image features, and fosters knowledge extrapolation to unfamiliar disease categories. 3) A semantic similarity matrix based on fine-grained annotations is proposed, providing smoother, information-richer labels, thus allowing fine-grained image-text alignment. 4) We validate MedFILIP on numerous datasets, e.g., RSNA-Pneumonia, NIH ChestX-ray14, VinBigData, and COVID-19. For single-label, multi-label, and fine-grained classification, our model achieves state-of-the-art performance, the classification accuracy has increased by a maximum of 6.69\%. The code is available in https://github.com/PerceptionComputingLab/MedFILIP.

cs.CV↗

arXiv2025

Spectrum Sharing in 6G Space-Ground Integrated Networks: A Ground Protection Zone-Based Design

Space-ground integrated network (SGIN) has been envisioned as a competitive solution for large scale and wide coverage of future wireless networks. By integrating both the non-terrestrial network (NTN) and the terrestrial network (TN), SGIN can provide high speed and omnipresent wireless network access for the users using the predefined licensed spectrums. Considering the scarcity of the spectrum resource and the low spectrum efficiency of the SGIN, we enable the NTN and TN to share the spectrum to improve overall system performance, i.e., weighted-sum area data rate (WS-ADR). However, mutual interference between NTN and TN is often inevitable and thus causes SGIN performance degradation. In this work, we consider a ground protection zone for the TN base stations, in which the NTN users are only allowed to use the NTN reserved spectrum to mitigate the NTN and TN mutual interference. We analytically derive the coverage probability and area data rate (ADR) of the typical users and study the performance under various protection zone sizes and spectrum allocation parameter settings. Simulation and numerical results demonstrate that the WS-ADR could be maximized by selecting the appropriate radius of protection zone and bandwidth allocation factor in the SGIN.

cs.IT↗

arXiv2024

Benchmarking and Understanding Compositional Relational Reasoning of LLMs

Compositional relational reasoning (CRR) is a hallmark of human intelligence, but we lack a clear understanding of whether and how existing transformer large language models (LLMs) can solve CRR tasks. To enable systematic exploration of the CRR capability of LLMs, we first propose a new synthetic benchmark called Generalized Associative Recall (GAR) by integrating and generalizing the essence of several tasks in mechanistic interpretability (MI) study in a unified framework. Evaluation shows that GAR is challenging enough for existing LLMs, revealing their fundamental deficiency in CRR. Meanwhile, it is easy enough for systematic MI study. Then, to understand how LLMs solve GAR tasks, we use attribution patching to discover the core circuits reused by Vicuna-33B across different tasks and a set of vital attention heads. Intervention experiments show that the correct functioning of these heads significantly impacts task performance. Especially, we identify two classes of heads whose activations represent the abstract notion of true and false in GAR tasks respectively. They play a fundamental role in CRR across various models and tasks. The dataset and code are available at https://github.com/Caiyun-AI/GAR.

cs.CL↗

arXiv2024

ChainStream: An LLM-based Framework for Unified Synthetic Sensing

Many applications demand context sensing to offer personalized and timely services. Yet, developing sensing programs can be challenging for developers and using them is privacy-concerning for end-users. In this paper, we propose to use natural language as the unified interface to process personal data and sense user context, which can effectively ease app development and make the data pipeline more transparent. Our work is inspired by large language models (LLMs) and other generative models, while directly applying them does not solve the problem - letting the model directly process the data cannot handle complex sensing requests and letting the model write the data processing program suffers error-prone code generation. We address the problem with 1) a unified data processing framework that makes context-sensing programs simpler and 2) a feedback-guided query optimizer that makes data query more informative. To evaluate the performance of natural language-based context sensing, we create a benchmark that contains 133 context sensing tasks. Extensive evaluation has shown that our approach is able to automatically solve the context-sensing tasks efficiently and precisely. The code is opensourced at https://github.com/MobileLLM/ChainStream.

cs.CL↗

arXiv2024

Time-Varying Directional State Transition Tensor for Orbit Uncertainty Propagation

The directional state transition tensor (DSTT) reduces the complexity of state transition tensor (STT) by aligning the STT terms in sensitive directions only, which provides comparable accuracy in orbital uncertainty propagation. The DSTT assumes the sensitive directions to be constant during the integration and only works at a predefined epoch. This paper proposes a time-varying STT (TDSTT) to improve the DSTT. The proposed TDSTT computes the sensitive directions with time; thereby, it can perform uncertainty propagation analysis at any point instead of only a predefined epoch as the DSTT does. First, the derivatives of the sensitive directions are derived. Then, the differential equations for the high-order TDSTTs are derived and simplified using the orthogonality of sensitive directions. Next, complexity analysis is implemented to show the advantages of the proposed TDSTT over the STT. Finally, the TDSTT is applied to solve orbital uncertainty propagation problems in highly nonlinear three-body systems. Numerical results show that the proposed TDSTT can yield nearly the same level of accuracy as the STT and DSTT. It is approximately 94% faster than the STT and has hundreds of improvements in speed over the DSTT when one wants to investigate the evolutions of orbital uncertainties.

astro-ph.IM↗

arXiv2024

Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge

Efficient automatic segmentation of multi-level (i.e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications. However, most existing methods concentrate only on main PA or branch PA segmentation separately and ignore segmentation efficiency. Besides, there is no public large-scale dataset focused on PA segmentation, which makes it highly challenging to compare the different methods. To benchmark multi-level PA segmentation algorithms, we organized the first \textbf{P}ulmonary \textbf{AR}tery \textbf{SE}gmentation (PARSE) challenge. On the one hand, we focus on both the main PA and the branch PA segmentation. On the other hand, for better clinical application, we assign the same score weight to segmentation efficiency (mainly running time and GPU memory consumption during inference) while ensuring PA segmentation accuracy. We present a summary of the top algorithms and offer some suggestions for efficient and accurate multi-level PA automatic segmentation. We provide the PARSE challenge as open-access for the community to benchmark future algorithm developments at \url{https://parse2022.grand-challenge.org/Parse2022/}.

eess.IV↗

arXiv2024

A Bistatic Sensing System in Space-Air-Ground Integrated Networks

Sensing is anticipated to have wider extensions in communication systems with the boom of non-terrestrial networks (NTNs) during the past years. In this paper, we study a bistatic sensing system by maximizing the signal-to-interference-plus-noise ration (SINR) from the target aircraft in the space-air-ground integrated network (SAGIN). We formulate a joint optimization problem for the transmit beamforming of low-earth orbit (LEO) satellite and the receive filtering of ground base station. To tackle this problem, we decompose the original problem into two sub-problems and use the alternating optimization to solve them iteratively. Using techniques of fractional programming and generalized Rayleigh quotient, the closed-form solution for each sub-problem is returned. Simulation results show that the proposed algorithm has good convergence performance.Moreover, the optimization of receive filtering dominates the optimality, especially when the satellite altitude becomes higher, which provides valuable network design insights.

eess.SP↗

arXiv2024

An Analytical Model for Coordinated Multi-Satellite Joint Transmission System

Satellite communication is one of the key technologies that is enabling next-generation networks. However, nearest-satellite-supported downlink transmission may not meet a user's requirements due to limited signal strength, especially in emergent scenarios. In this paper, we investigate a coordinated multi-satellite joint transmission system from a system-level perspective, where a user can be served by multiple satellites to improve its quality-of-service (QoS). Furthermore, we analyze the coverage and rate of a typical user in the joint transmission system. Simulation and numerical results show that the introduced system achieves a higher coverage probability than the traditional nearest-satellite-supported network. Moreover, a user's ergodic rate can be maximized by selecting an appropriate number of serving satellites.

eess.SP↗