arXiv subjects

Chenxi Li

Publications and source records attributed to Chenxi Li.

At least 55 records · Page 3Linked to original sources

arXiv2025

Variable Selection with Broken Adaptive Ridge Regression for Interval-Censored Competing Risks Data

Competing risks data refer to situations where the occurrence of one event pre- cludes the possibility of other events happening, resulting in multiple mutually exclusive events. This data type is commonly encountered in medical research and clinical trials, exploring the interplay between different events and informing decision-making in fields such as healthcare and epidemiology. We develop a penal- ized variable selection procedure to handle such complex data in an interval-censored setting. We consider a broad class of semiparametric transformation regression mod- els, including popular models such as proportional and non-proportional hazards models. To promote sparsity and select variables specific to each event, we employ the broken adaptive ridge (BAR) penalty. This approach allows us to simultane- ously select important risk factors and estimate their effects for each event under investigation. We establish the oracle property of the BAR procedure and evaluate its performance through simulation studies. The proposed method is applied to a real-life HIV cohort dataset, further validating its applicability in practice.

stat.ME↗

arXiv2025

Event-triggered control and communication for single-master multi-slave teleoperation systems with Try-Once-Discard protocol

Single-master multi-slave (SMMS) teleoperation systems can perform multiple tasks remotely in a shorter time, cover large-scale areas, and adapt more easily to single-point failures, thereby effectively encompassing a broader range of applications. As the number of slave manipulators sharing a communication network increases, the limitation of communication bandwidth becomes critical. To alleviate bandwidth usage, the Try-Once-Discard (TOD) scheduling protocol and event-triggered mechanisms are often employed separately. In this paper, we combine both strategies to optimize network bandwidth and energy consumption for SMMS teleoperation systems. Specifically, we propose event-triggered control and communication schemes for a class of SMMS teleoperation systems using the TOD scheduling protocol. Considering dynamic uncertainties, the unavailability of relative velocities, and time-varying delays, we develop adaptive controllers with virtual observers based on event-triggered schemes to achieve master-slave synchronization. Stability criteria for the SMMS teleoperation systems under these event-triggered control and communication schemes are established, demonstrating that Zeno behavior is excluded. Finally, experiments are conducted to validate the effectiveness of the proposed algorithms.

eess.SY↗

arXiv2025

MoVa: Towards Generalizable Classification of Human Morals and Values

Identifying human morals and values embedded in language is essential to empirical studies of communication. However, researchers often face substantial difficulty navigating the diversity of theoretical frameworks and data available for their analysis. Here, we contribute MoVa, a well-documented suite of resources for generalizable classification of human morals and values, consisting of (1) 16 labeled datasets and benchmarking results from four theoretically-grounded frameworks; (2) a lightweight LLM prompting strategy that outperforms fine-tuned models across multiple domains and frameworks; and (3) a new application that helps evaluate psychological surveys. In practice, we specifically recommend a classification strategy, all@once, that scores all related concepts simultaneously, resembling the well-known multi-label classifier chain. The data and methods in MoVa can facilitate many fine-grained interpretations of human and machine communication, with potential implications for the alignment of machine behavior.

cs.CL↗

arXiv2025

SDC-Net: A Domain Adaptation Framework with Semantic-Dynamic Consistency for Cross-Subject EEG Emotion Recognition

Emotion recognition based on electroencephalography (EEG) holds significant promise for affective brain-computer interfaces (aBCIs). However, its practical deployment faces challenges due to the variability within inter-subject and the scarcity of labeled data in target domains. To overcome these limitations, we propose SDC-Net, a novel Semantic-Dynamic Consistency domain adaptation network for fully label-free cross-subject EEG emotion recognition. First, we introduce a Same-Subject Same-Trial Mixup strategy that generates augmented samples through intra-trial interpolation, enhancing data diversity while explicitly preserving individual identity to mitigate label ambiguity. Second, we construct a dynamic distribution alignment module within the Reproducing Kernel Hilbert Space (RKHS), jointly aligning marginal and conditional distributions through multi-objective kernel mean embedding, and leveraging a confidence-aware pseudo-labeling strategy to ensure stable adaptation. Third, we propose a dual-domain similarity consistency learning mechanism that enforces cross-domain structural constraints based on latent pairwise similarities, facilitating semantic boundary learning without reliance on temporal synchronization or label priors. To validate the effectiveness and robustness of the proposed SDC-Net, extensive experiments are conducted on three widely used EEG benchmark datasets: SEED, SEED-IV, and FACED. Comparative results against existing unsupervised domain adaptation methods demonstrate that SDC-Net achieves state-of-the-art performance in emotion recognition under both cross-subject and cross-session conditions. This advancement significantly improves the accuracy and generalization capability of emotion decoding, laying a solid foundation for real-world applications of personalized aBCIs. The source code is available at: https://github.com/XuanSuTrum/SDC-Net.

cs.HC↗

arXiv2025

AIVA: An AI-based Virtual Companion for Emotion-aware Interaction

Recent advances in Large Language Models (LLMs) have significantly improved natural language understanding and generation, enhancing Human-Computer Interaction (HCI). However, LLMs are limited to unimodal text processing and lack the ability to interpret emotional cues from non-verbal signals, hindering more immersive and empathetic interactions. This work explores integrating multimodal sentiment perception into LLMs to create emotion-aware agents. We propose \ours, an AI-based virtual companion that captures multimodal sentiment cues, enabling emotionally aligned and animated HCI. \ours introduces a Multimodal Sentiment Perception Network (MSPN) using a cross-modal fusion transformer and supervised contrastive learning to provide emotional cues. Additionally, we develop an emotion-aware prompt engineering strategy for generating empathetic responses and integrate a Text-to-Speech (TTS) system and animated avatar module for expressive interactions. \ours provides a framework for emotion-aware agents with applications in companion robotics, social care, mental health, and human-centered AI.

cs.CV↗

arXiv2025

Nav-SCOPE: Swarm Robot Cooperative Perception and Coordinated Navigation

This paper proposes a lightweight systematic solution for multi-robot coordinated navigation with decentralized cooperative perception. An information flow is first created to facilitate real-time observation sharing over unreliable ad-hoc networks. Then, the environmental uncertainties of each robot are reduced by interaction fields that deliver complementary information. Finally, path optimization is achieved, enabling self-organized coordination with effective convergence, divergence, and collision avoidance. Our method is fully interpretable and ready for deployment without gaps. Comprehensive simulations and real-world experiments demonstrate reduced path redundancy, robust performance across various tasks, and minimal demands on computation and communication.

cs.RO↗

arXiv2025

Physics-Constrained Diffusion Reconstruction with Posterior Correction for Quantitative and Fast PET Imaging

Deep learning-based reconstruction of positron emission tomography(PET) data has gained increasing attention in recent years. While these methods achieve fast reconstruction,concerns remain regarding quantitative accuracy and the presence of artifacts,stemming from limited model interpretability,data driven dependence, and overfitting risks.These challenges have hindered clinical adoption.To address them,we propose a conditional diffusion model with posterior physical correction (PET-DPC) for PET image reconstruction. An innovative normalization procedure generates the input Geometric TOF Probabilistic Image (GTP-image),while physical information is incorporated during the diffusion sampling process to perform posterior scatter,attenuation,and random corrections. The model was trained and validated on 300 brain and 50 whole-body PET datasets,a physical phantom,and 20 simulated brain datasets. PET-DPC produced reconstructions closely aligned with fully corrected OSEM images,outperforming end-to-end deep learning models in quantitative metrics and,in some cases, surpassing traditional iterative methods. The model also generalized well to out-of-distribution(OOD) data. Compared to iterative methods,PET-DPC reduced reconstruction time by 50% for brain scans and 85% for whole-body scans. Ablation studies confirmed the critical role of posterior correction in implementing scatter and attenuation corrections,enhancing reconstruction accuracy. Experiments with physical phantoms further demonstrated PET-DPC's ability to preserve background uniformity and accurately reproduce tumor-to-background intensity ratios. Overall,these results highlight PET-DPC as a promising approach for rapid, quantitatively accurate PET reconstruction,with strong potential to improve clinical imaging workflows.

physics.med-ph↗

arXiv2025

QuarkMed Medical Foundation Model Technical Report

Recent advancements in large language models have significantly accelerated their adoption in healthcare applications, including AI-powered medical consultations, diagnostic report assistance, and medical search tools. However, medical tasks often demand highly specialized knowledge, professional accuracy, and customization capabilities, necessitating a robust and reliable foundation model. QuarkMed addresses these needs by leveraging curated medical data processing, medical-content Retrieval-Augmented Generation (RAG), and a large-scale, verifiable reinforcement learning pipeline to develop a high-performance medical foundation model. The model achieved 70% accuracy on the Chinese Medical Licensing Examination, demonstrating strong generalization across diverse medical benchmarks. QuarkMed offers a powerful yet versatile personal medical AI solution, already serving over millions of users at ai.quark.cn.

cs.AI↗

arXiv2025

TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Data

The scarcity of large-scale and high-quality electronic health records (EHRs) remains a major bottleneck in biomedical research, especially as large foundation models become increasingly data-hungry. Synthesizing substantial volumes of de-identified and high-fidelity data from existing datasets has emerged as a promising solution. However, existing methods suffer from a series of limitations: they struggle to model the intrinsic properties of heterogeneous multimodal EHR data (e.g., continuous, discrete, and textual modalities), capture the complex dependencies among them, and robustly handle pervasive data incompleteness. These challenges are particularly acute in Traditional Chinese Medicine (TCM). To this end, we propose TCDiff (Triplex Cascaded Diffusion Network), a novel EHR generation framework that cascades three diffusion networks to learn the features of real-world EHR data, formatting a multi-stage generative process: Reference Modalities Diffusion, Cross-Modal Bridging, and Target Modality Diffusion. Furthermore, to validate our proposed framework, besides two public datasets, we also construct and introduce TCM-SZ1, a novel multimodal EHR dataset for benchmarking. Experimental results show that TCDiff consistently outperforms state-of-the-art baselines by an average of 10% in data fidelity under various missing rate, while maintaining competitive privacy guarantees. This highlights the effectiveness, robustness, and generalizability of our approach in real-world healthcare scenarios.

cs.LG↗

arXiv2025

DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving

Primal heuristics play a critical role in improving the efficiency of mixed integer programming (MILP) solvers. As large language models (LLMs) have demonstrated superior code generation abilities, recent MILP works are devoted to leveraging the evolutionary computation approaches with LLMs to generate effective primal heuristics. Although the generated heuristics have achieved better solving performance than the hand-crafted ones with little adaptability, the advantage of current LLM-based methods is limited to few MILP instances in one problem class, as they fail to capture the instance characteristics in the problem class (the MILP instances generated from the same mathematical model are defined as a problem class). Since MILP instances often differ significantly in structure and feature distribution, the neglect of their characteristics in the evolution process results in poor generalization within the same problem class. To overcome this challenge, we propose a data-algorithm co-evolution framework (DHEvo) that iteratively selects representative instances and evolves corresponding heuristics. With the initial instance distribution, we develop an LLM-based multi-agent system to generate data-code pairs simultaneously. These data-code pairs are iteratively refined based on their fitness scores, leading to the identification of the most effective heuristic over the entire problem class. Extensive experiments across diverse MILP benchmarks demonstrate that our approach significantly outperforms both human-designed heuristics and existing LLM-based methods.

cs.NE↗

arXiv2025

LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning

We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection. Unlike prior methods that treat labels as flat and independent, our approach leverages LLM prompting to automatically generate multi-level semantic taxonomies and introduces a recursive uncertainty projection mechanism that propagates uncertainty across hierarchy levels. This enables spatially diverse, label-aware point selection that respects the inherent semantic structure of 3D scenes. Experiments on S3DIS and ScanNet v2 show that our method achieves up to 4% mIoU improvement under extremely low annotation budgets (e.g., 0.02%), substantially outperforming existing baselines. Our results highlight the untapped potential of LLMs as knowledge priors in 3D vision and establish hierarchical uncertainty modeling as a powerful paradigm for efficient point cloud annotation.

cs.CV↗

arXiv2025

Anomalous properties of spark plasma sintered boron nitride solids

Hexagonal boron nitride (h-BN) is a brittle ceramic with a layered structure, however, recent experiments have suggested that inter-layer structural engineering could be key to new structural and functional properties. Here we report the scalable bulk synthesis of high-density crystalline h-BN solids, by using high-temperature spark plasma sintering (SPS) of h-BN powders, which show high values of mechanical strength, ductility, dielectric constant, thermal conductivity, and exceptional neutron radiation shielding capability. Through exhaustive characterizations we reveal that SPS induces non-basal plane crystallinity, twisting of layers, and facilitates inter-grain fusion with a high degree of in-plane alignment across macroscale dimensions, resulting in near-theoretical density and improved properties. Our findings highlight the importance of material design, via new approaches such as layer twisting and interlayer interconnections, to create novel ceramics with properties that could go beyond their intrinsic limits.

cond-mat.mtrl-sci↗

arXiv2025

Bayesian inference for cluster-randomized trials with multivariate outcomes subject to both truncation by death and missingness

Cluster-randomized trials (CRTs) on fragile populations frequently encounter complex attrition problems where the reasons for missing outcomes can be heterogeneous, with participants who are known alive, known to have died, or with unknown survival status, and with complex and distinct missing data mechanisms for each group. Although existing methods have been developed to address death truncation in CRTs, no existing methods can jointly accommodate participants who drop out for reasons unrelated to mortality or serious illnesses, or those with an unknown survival status. This paper proposes a Bayesian framework for estimating survivor average causal effects in CRTs while accounting for different types of missingness. Our approach uses a multivariate outcome that jointly estimates the causal effects, and in the posterior estimates, we distinguish the individual-level and the cluster-level survivor average causal effect. We perform simulation studies to evaluate the performance of our model and found low bias and high coverage on key parameters across several different scenarios. We use data from a geriatric CRT to illustrate the use of our model. Although our illustration focuses on the case of a bivariate continuous outcome, our model is straightforwardly extended to accommodate more than two endpoints as well as other types of endpoints (e.g., binary). Thus, this work provides a general modeling framework for handling complex missingness in CRTs and can be applied to a wide range of settings with aging and palliative care populations.

stat.ME↗

arXiv2025

Pfaffian solution for dark-dark soliton to the coupled complex modified Korteweg-de Vries equation

In this paper, we study coupled complex modified Korteweg-de Vries (ccmKdV) equation by combining the Hirota's method and the Kadomtsev-Petviashvili (KP) reduction method. First, we show that the bilinear form of the ccmKdV equation under nonzero boundary condition is linked to the discrete BKP hierarchy through Miwa transformation. Based on this finding, we construct the dark-dark soliton solution in the pfaffian form. The dynamical behaviors for one- and two-soliton are analyzed and illustrated.

math-ph↗

arXiv2025

Trust Region Methods For Nonconvex Stochastic Optimization Beyond Lipschitz Smoothness

In many important machine learning applications, the standard assumption of having a globally Lipschitz continuous gradient may fail to hold. This paper delves into a more general $(L_0, L_1)$-smoothness setting, which gains particular significance within the realms of deep neural networks and distributionally robust optimization (DRO). We demonstrate the significant advantage of trust region methods for stochastic nonconvex optimization under such generalized smoothness assumption. We show that first-order trust region methods can recover the normalized and clipped stochastic gradient as special cases and then provide a unified analysis to show their convergence to first-order stationary conditions. Motivated by the important application of DRO, we propose a generalized high-order smoothness condition, under which second-order trust region methods can achieve a complexity of $\mathcal{O}(ε^{-3.5})$ for convergence to second-order stationary points. By incorporating variance reduction, the second-order trust region method obtains an even better complexity of $\mathcal{O}(ε^{-3})$, matching the optimal bound for standard smooth optimization. To our best knowledge, this is the first work to show convergence beyond the first-order stationary condition for generalized smooth optimization. Preliminary experiments show that our proposed algorithms perform favorably compared with existing methods.

math.OC↗

arXiv2025

Highly Efficient Observation Process based on FFT Filtering for Robot Swarm Collaborative Navigation in Unknown Environments

Collaborative path planning for robot swarms in complex, unknown environments without external positioning is a challenging problem. This requires robots to find safe directions based on real-time environmental observations, and to efficiently transfer and fuse these observations within the swarm. This study presents a filtering method based on Fast Fourier Transform (FFT) to address these two issues. We treat sensors' environmental observations as a digital sampling process. Then, we design two different types of filters for safe direction extraction, as well as for the compression and reconstruction of environmental data. The reconstructed data is mapped to probabilistic domain, achieving efficient fusion of swarm observations and planning decision. The computation time is only on the order of microseconds, and the transmission data in communication systems is in bit-level. The performance of our algorithm in sensor data processing was validated in real world experiments, and the effectiveness in swarm path optimization was demonstrated through extensive simulations.

cs.RO↗

arXiv2024

Collaborative Goal Tracking of Multiple Mobile Robots Based on Geometric Graph Neural Network

Multiple mobile robots play a significant role in various spatially distributed tasks.In unfamiliar and non-repetitive scenarios, reconstructing the global map is time-inefficient and sometimes unrealistic. Hence, research has focused on achieving real-time collaborative planning by utilizing sensor data from multiple robots located at different positions, all without relying on a global map.This paper introduces a Multi-Robot collaborative Path Planning method based on Geometric Graph Neural Network (MRPP-GeoGNN). We extract the features of each neighboring robot's sensory data and integrate the relative positions of neighboring robots into each interaction layer to incorporate obstacle information along with location details using geometric feature encoders. After that, a MLP layer is used to map the amalgamated local features to multiple forward directions for the robot's actual movement. We generated expert data in ROS to train the network and carried out both simulations and physical experiments to validate the effectiveness of the proposed method. Simulation results demonstrate an approximate 5% improvement in accuracy compared to the model based solely on CNN on expert datasets. The success rate is enhanced by about 4% compared to CNN, and the flowtime increase is reduced by approximately 18% in the ROS test, surpassing other GNN models. Besides, the proposed method is able to leverage neighbor's information and greatly improves path efficiency in real-world scenarios.

cs.RO↗

arXiv2024

Efficient Collaborative Navigation through Perception Fusion for Multi-Robots in Unknown Environments

For tasks conducted in unknown environments with efficiency requirements, real-time navigation of multi-robot systems remains challenging due to unfamiliarity with surroundings.In this paper, we propose a novel multi-robot collaborative planning method that leverages the perception of different robots to intelligently select search directions and improve planning efficiency. Specifically, a foundational planner is employed to ensure reliable exploration towards targets in unknown environments and we introduce Graph Attention Architecture with Information Gain Weight(GIWT) to synthesizes the information from the target robot and its teammates to facilitate effective navigation around obstacles.In GIWT, after regionally encoding the relative positions of the robots along with their perceptual features, we compute the shared attention scores and incorporate the information gain obtained from neighboring robots as a supplementary weight. We design a corresponding expert data generation scheme to simulate real-world decision-making conditions for network training. Simulation experiments and real robot tests demonstrates that the proposed method significantly improves efficiency and enables collaborative planning for multiple robots. Our method achieves approximately 82% accuracy on the expert dataset and reduces the average path length by about 8% and 6% across two types of tasks compared to the fundamental planner in ROS tests, and a path length reduction of over 6% in real-world experiments.

cs.RO↗