Author name cluster

Bowen Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

IROS Conference 2025 Conference Paper

High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

Ziqing Zou
Cong Wang
Yue Hu
Xiao Liu
Bowen Xu
Rong Xiong
Changjie Fan
Yingfeng Chen

The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such applications due to their inability to effectively handle these nonlinearities, while commonly used learning-based methods require extensive interactions with the environment, leading to inefficiency. To address these issues, we introduce EfficientTrack, a trajectory tracking method that integrates model-based learning to manage nonlinear dynamics and leverages closed-loop dynamics to improve learning efficiency, ultimately minimizing tracking errors. We validate our method through comprehensive experiments both in simulation and on a real-world excavator. Comparative experiments in simulation demonstrate that our method outperforms existing learning-based approaches, achieving the highest tracking precision and smoothness with the fewest interactions. Real-world experiments further show that our method remains effective under load conditions and possesses the ability for continual learning, highlighting its practical applicability. For implementation details and source code, please refer to https://github.com/ZiqingZou/EfficientTrack.

Details

ICML Conference 2025 Conference Paper

La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation

Kai Liu
Bowen Xu
Shaoyu Wu
Xin Chen
Hao Zhou
Yongliang Tao
Lulu Hu

Activation sparsity can reduce the computational overhead and memory transfers during the forward pass of Large Language Model (LLM) inference. Existing methods face limitations, either demanding time-consuming recovery training that hinders real-world adoption, or relying on empirical magnitude-based pruning, which causes fluctuating sparsity and unstable inference speed-up. This paper introduces LaRoSA ( La yerwise Ro tated S parse A ctivation), a novel method for activation sparsification designed to improve LLM efficiency without requiring additional training or magnitude-based pruning. We leverage layerwise orthogonal rotations to transform input activations into rotated forms that are more suitable for sparsification. By employing a Top-K selection approach within the rotated activations, we achieve consistent model-level sparsity and reliable wall-clock time speed-up. LaRoSA is effective across various sizes and types of LLMs, demonstrating minimal performance degradation and robust inference acceleration. Specifically, for LLaMA2-7B at 40% sparsity, LaRoSA achieves a mere 0. 17 perplexity gap with a consistent 1. 30$\times$ wall-clock time speed-up, and reduces the accuracy gap in zero-shot tasks compared to the dense model to just 0. 54%, while surpassing TEAL by 1. 77% and CATS by 17. 14%.

Details

JBHI Journal 2025 Journal Article

XFM: An Explainable Knowledge-Fused Vision Foundation Model for Improving Clinical Diagnosis of Low-Prevalence Retinal Diseases

Hongyang Jiang
Mengdi Gao
Bowen Xu
Bowen Liu
Peilun Shi
Yibing Wang
Dajun Liu
Wu Yuan

Foundation models in ophthalmology, often pre-trained on extensive datasets, exhibit exceptional generalization and emergent capabilities that are absent in smaller-scale specialized models. This study first investigated the adaptation of ophthalmic foundation models to detect low-prevalence retinal diseases in real-world clinical settings with low-data regimes. We then bridged the gap in exploring the use of fine-grained prior-knowledge infusion and SAM-guided cycle constraint regularization to enhance the explainability of the foundation models from both qualitative and quantitative perspectives. Evaluated on two newly constructed public datasets (FundusData-FS and OTFID), our foundation model-based solution demonstrates effective transfer learning and few-shot learning fine-tuning performance for multiple low-prevalence retinal diseases. Our experiments demonstrate that prior-knowledge infusion and SAM-guided regularization enhance both the performance and the explainability of the foundation model. For example, our method achieves over 9% accuracy improvement and superior AUC performance (an 8% gain over RETFound) in GradCAM-positive perturbation testing, with statistically significant improvements (p <0. 05) in the FundusData-FS dataset. These findings highlight the potential of explainable ophthalmic foundation models for trustworthy AI in clinical practice.

Details DOI

NeurIPS Conference 2024 Conference Paper

Covariate Shift Corrected Conditional Randomization Test

Bowen Xu
Yiwen Huang
Chuan Hong
Shuangning Li
Molei Liu

Conditional independence tests are crucial across various disciplines in determining the independence of an outcome variable $Y$ from a treatment variable $X$, conditioning on a set of confounders $Z$. The Conditional Randomization Test (CRT) offers a powerful framework for such testing by assuming known distributions of $X \mid Z$; it controls the Type-I error exactly, allowing for the use of flexible, black-box test statistics. In practice, testing for conditional independence often involves using data from a source population to draw conclusions about a target population. This can be challenging due to covariate shift---differences in the distribution of $X$, $Z$, and surrogate variables, which can affect the conditional distribution of $Y \mid X, Z$---rendering traditional CRT approaches invalid. To address this issue, we propose a novel Covariate Shift Corrected Pearson Chi-squared Conditional Randomization (csPCR) test. This test adapts to covariate shifts by integrating importance weights and employing the control variates method to reduce variance in the test statistics and thus enhance power. Theoretically, we establish that the csPCR test controls the Type-I error asymptotically. Empirically, through simulation studies, we demonstrate that our method not only maintains control over Type-I errors but also exhibits superior power, confirming its efficacy and practical utility in real-world scenarios where covariate shifts are prevalent. Finally, we apply our methodology to a real-world dataset to assess the impact of a COVID-19 treatment on the 90-day mortality rate among patients.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Patched Line Segment Learning for Vector Road Mapping

Jiakun Xu
Bowen Xu
Gui-Song Xia
Liang Dong
Nan Xue

This paper presents a novel approach to computing vector road maps from satellite remotely sensed images, building upon a well-defined Patched Line Segment (PaLiS) representation for road graphs that holds geometric significance. Unlike prevailing methods that derive road vector representations from satellite images using binary masks or keypoints, our method employs line segments. These segments not only convey road locations but also capture their orientations, making them a robust choice for representation. More precisely, given an input image, we divide it into non-overlapping patches and predict a suitable line segment within each patch. This strategy enables us to capture spatial and structural cues from these patch-based line segments, simplifying the process of constructing the road network graph without the necessity of additional neural networks for connectivity. In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture. Furthermore, our method achieves state-of-the-art performance with just 6 GPU hours of training, leading to a substantial 32-fold reduction in training costs in terms of GPU hours.

PDF Details DOI

TCS Journal 2023 Journal Article

Numerical spiking neural P systems with production functions on synapses

Suxia Jiang
Bowen Xu
Tao Liang
Xiaoliang Zhu
Tingfang Wu

Numerical spiking neural (NSN) P systems are a class of distributed parallel neural computing devices, where the values of numerical variables are used to encode the information, the programs that process the variables are expressed by continuous production functions. In this work, numerical spiking neural P systems with functions on synapses (NSNFS P systems), as a variant of numerical spike neural P systems, are proposed. In NSNFS P systems, continuous production functions are considered at synapses of neurons and used to transmit information between two neurons connected by a synapse. The computation power of NSNFS P systems as a kind of digital generating devices and digital accepting devices is investigated respectively, when the continuous production functions on each synapse are linear and only one numerical variable is involved in each neuron. The results show that numerical spiking neural P systems with production functions on synapses are still universal.

Details DOI

ICRA Conference 2023 Conference Paper

The SLAM Hive Benchmarking Suite

Yuan-Yuan Yang
Bowen Xu
Yinjie Li
Sören Schwertfeger

Benchmarking Simultaneous Localization and Mapping (SLAM) algorithms is important to scientists and users of robotic systems alike. But through their many configuration options in hardware and software, SLAM systems feature a vast parameter space that scientists up to now were not able to explore. The proposed SLAM Hive Benchmarking Suite is able to analyze SLAM algorithms in 1000's of mapping runs, through its utilization of container technology and deployment in a cluster. This paper presents the architecture and open source implementation of SLAM Hive and compares it to existing efforts on SLAM evaluation. Furthermore, we highlight the function of SLAM Hive by exploring some open source algorithms on public datasets in terms of accuracy. We compare the algorithms against each other and evaluate how parameters effect not only accuracy but also CPU and memory usage. Through this we show that SLAM Hive can become an essential tool for proper comparisons and evaluations of SLAM algorithms and thus drive the scientific development in the research on SLAM.

Details