arXiv subjects

Xiaoru Dong

Publications and source records attributed to Xiaoru Dong.

3 recordsLinked to original sources

arXiv2026

Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving

Human driving behavior is inherently diverse, yet most end-to-end autonomous driving (E2E-AD) systems learn a single average driving style, neglecting individual differences. Achieving personalized E2E-AD faces challenges across three levels: limited real-world datasets with individual-level annotations, a lack of quantitative metrics for evaluating personal driving styles, and the absence of algorithms that can learn stylized representations from users' trajectories. To address these gaps, we propose Person2Drive, a comprehensive personalized E2E-AD platform and benchmark. It includes an open-source, flexible data collection system that simulates realistic scenarios to generate scalable, diverse personalized driving datasets; style vector-based evaluation metrics with Maximum Mean Discrepancy and KL divergence to comprehensively quantify individual driving behaviors; and a personalized E2E-AD framework with a style reward model that efficiently adapts E2E models for safe and individualized driving. Crucially, our framework enables plug-and-play personalization by fine-tuning only the trajectory prediction head, preserving the pretrained base model and ensuring safety. Extensive experiments demonstrate that Person2Drive enables fine-grained analysis and effective personalization, while preserving driving performance and success rate even in challenging scenarios.

cs.CV↗

arXiv2025

Penalized Linear Models for Highly Correlated High-Dimensional Immunophenotyping Data

Accurate prediction and identification of variables associated with outcomes or disease states are critical for advancing diagnosis, prognosis, and precision medicine in biomedical research. Regularized regression techniques, such as lasso, are widely employed to enhance interpretability by reducing model complexity and identifying significant variables. However, when applying to biomedical datasets, e.g., immunophenotyping dataset, there are two major challenges that may lead to unsatisfactory results using these methods: 1) high correlation between predictors, which leads to the exclusion of important variables with included predictors in variable selection, and 2) the presence of skewness, which violates key statistical assumptions of these methods. Current approaches that fail to address these issues simultaneously may lead to biased interpretations and unreliable coefficient estimates. To overcome these limitations, we propose a novel two-step approach, the Bootstrap-Enhanced Regularization Method (BERM). BERM outperforms existing two-step approaches and demonstrates consistent performance in terms of variable selection and estimation accuracy across simulated sparsity scenarios. We further demonstrate the effectiveness of BERM by applying it to a human immunophenotyping dataset identifying important immune parameters associated the autoimmune disease, type 1 diabetes.

stat.AP↗

arXiv2020

Optimization-driven Deep Reinforcement Learning for Robust Beamforming in IRS-assisted Wireless Communications

Intelligent reflecting surface (IRS) is a promising technology to assist downlink information transmissions from a multi-antenna access point (AP) to a receiver. In this paper, we minimize the AP's transmit power by a joint optimization of the AP's active beamforming and the IRS's passive beamforming. Due to uncertain channel conditions, we formulate a robust power minimization problem subject to the receiver's signal-to-noise ratio (SNR) requirement and the IRS's power budget constraint. We propose a deep reinforcement learning (DRL) approach that can adapt the beamforming strategies from past experiences. To improve the learning performance, we derive a convex approximation as a lower bound on the robust problem, which is integrated into the DRL framework and thus promoting a novel optimization-driven deep deterministic policy gradient (DDPG) approach. In particular, when the DDPG algorithm generates a part of the action (e.g., passive beamforming), we can use the model-based convex approximation to optimize the other part (e.g., active beamforming) of the action more efficiently. Our simulation results demonstrate that the optimization-driven DDPG algorithm can improve both the learning rate and reward performance significantly compared to the conventional model-free DDPG algorithm.

eess.SP↗