Bowei Li 李博伟
M.S. Student, Department of Electrical and Computer Engineering
Carnegie Mellon University
I am a Master's student at the Department of Electrical and Computer Engineering, Carnegie Mellon University, advised by Prof. Changliu Liu in the Intelligent Control Lab. My research spans robot learning, scalable robot data generation, long-horizon manipulation, and agentic robot policies.
I received my Bachelor's degree in Telecommunication Engineering jointly from Xidian University and Heriot-Watt University. During my undergraduate studies, I worked at the Digital Governance Engineering Research Center led by Prof. Huailiang Liu on sentiment analysis, and was also remotely advised by Prof. Ran Zhang from UNC Charlotte on reinforcement learning for UAV communications.
Email: boweili [at] andrew [dot] cmu [dot] edu
Publications
* denotes equal contribution. Author names in bold indicate me.
Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks
arXiv preprint, 2025
Deep neural networks have been widely adopted in many vision and robotics applications with visual inputs. It is essential to verify their robustness against semantic transformation perturbations, such as brightness and contrast. However, current certified training and robustness certification methods face the challenge of over-parameterization, which hinders the tightness and scalability due to over-complicated neural networks. To this end, we first analyze stability and variance of layers and neurons against input perturbation, showing that certifiable robustness can be indicated by a fundamental Unbiased and Smooth Neuron metric (USN). Based on USN, we introduce a novel pruning method that removes neurons with low USN and retains those with high USN, preserving model expressiveness without over-parameterization. To further enhance this pruning, we propose a new Wasserstein distance loss to ensure pruned neurons are more concentrated across layers. We validate our approach on robust keypoint detection under realistic brightness and contrast perturbations, demonstrating superior robustness certification performance and efficiency compared to baselines.
@article{hu2025enhancing,
title = {Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks},
author = {Hu, Hanjiang and Li, Bowei and Wang, Ziwei and Wei, Tianhao and Hutchison, Casidhe and Sample, Eric and Liu, Changliu},
journal = {arXiv preprint arXiv:2510.00083},
year = {2025}
}
NeSyPack: A Neuro-Symbolic Framework for Bimanual Logistics Packing
RSS 2025 Workshop on Benchmarking Robot Manipulation · First Prize, WBCD Competition @ ICRA 2025
abstract · bibtex · arXiv · video
This paper presents NeSyPack, a neuro-symbolic framework for bimanual logistics packing. NeSyPack combines data-driven models and symbolic reasoning to build an explainable hierarchical system that is generalizable, data-efficient, and reliable. It decomposes a task into subtasks via hierarchical reasoning, and further into atomic skills managed by a symbolic skill graph. The graph selects skill parameters, robot configurations, and task-specific control strategies for execution. This modular design enables robustness, adaptability, and efficient reuse — outperforming end-to-end models that require large-scale retraining. Using NeSyPack, our team won the First Prize in the What Bimanuals Can Do (WBCD) competition at the 2025 IEEE International Conference on Robotics and Automation.
@article{li2025nesypack,
title = {NeSyPack: A Neuro-Symbolic Framework for Bimanual Logistics Packing},
author = {Li, Bowei and Yu, Peiqi and Tang, Zhenran and Zhou, Han and Sun, Yifan and Liu, Ruixuan and Liu, Changliu},
journal = {arXiv preprint arXiv:2506.06567},
year = {2025}
}
SPARK: A Modular Benchmark for Humanoid Robot Safety
IFAC Symposium on Robotics, 2025
abstract · bibtex · arXiv · code · project page
This paper introduces the Safe Protective and Assistive Robot Kit (SPARK), a comprehensive benchmark designed to ensure safety in humanoid autonomy and teleoperation. Humanoid robots pose significant safety risks due to their physical capabilities of interacting with complex environments, and their structures further add complexity to general safety solutions. SPARK is a toolbox that comes with state-of-the-art safe control algorithms in a modular and composable robot control framework. Users can configure safety criteria and sensitivity levels to optimize the balance between safety and performance. SPARK provides simulation benchmarks comparing safety approaches in a variety of environments, tasks, and robot models, and allows quick deployment of synthesized safe controllers on real robots. For hardware deployment, SPARK supports Apple Vision Pro or a Motion Capture System as external sensors, with interfaces for alternative hardware. We demonstrate SPARK's capability with simulation experiments and case studies on a Unitree G1 humanoid.
@inproceedings{sun2025spark,
title = {SPARK: Safe Protective and Assistive Robot Kit},
author = {Sun, Yifan and Chen, Rui and Yun, Kai S. and Fang, Yikuan and Jung, Sebin and Li, Feihan and Li, Bowei and Zhao, Weiye and Liu, Changliu},
booktitle = {IFAC Symposium on Robotics},
year = {2025}
}
IEEE Transactions on Cognitive Communications and Networking, vol. 12, pp. 175–188, 2025
Distributed management over UAV-based communication networks (UCNs) has attracted increasing research attention. In this work, we study a distributed user connectivity maximization problem in a UCN, featuring a horizontal study over different levels of information exchange and a consideration of dynamics in UAV set and user distribution. The problem is formulated as a time-coupled mixed-integer non-convex optimization. A heuristic two-stage UAV–user association policy is proposed to determine connectivity faster. To tackle the NP-hard problem at scale, DUCM-1 is proposed under the multi-agent deep Q learning (MA-DQL) framework, evaluating how information-exchange levels impact convergence; DUCM-2 then handles arbitrary join-ins and quits of UAVs in a considered horizon.
@article{li2025when,
title = {When Learning Meets Dynamics: Distributed User Connectivity Maximization in UAV-Based Communication Networks},
author = {Li, Bowei and Tripathi, Saugat and Hosain, AKM Salman and Zhang, Ran and Wang, Miao and Xie, Jiang},
journal = {IEEE Transactions on Cognitive Communications and Networking},
volume = {12},
pages = {175--188},
year = {2025}
}
IEEE Communications Magazine, 2025
UAV-based communication networks (UCNs) are a key component in future mobile networking. To handle their dynamic environments, reinforcement learning (RL) has emerged as a promising solution thanks to its strong adaptive decision-making free of environment models. However, most existing RL-based research focuses on control strategies assuming a fixed UAV set, while few works investigate adaptive regulation when the serving UAVs change dynamically. This article discusses RL-based strategy design for adaptive UCN regulation given a dynamic UAV set, addressing both reactive strategies in general UCNs and proactive strategies in solar-powered UCNs, with case studies from our recent works.
@article{zhang2025learning,
title = {Learning with Dynamics: Autonomous Regulation of UAV-Based Communication Networks with Dynamic UAV Crew},
author = {Zhang, Ran and Li, Bowei and Zhang, Liyuan and Xie, Jiang and Wang, Miao},
journal = {IEEE Communications Magazine},
year = {2025}
}
IEEE International Conference on Communications (ICC), pp. 530–535, 2025
Deep reinforcement learning (DRL) has been extensively applied to Multi-UAV networks (MUNs) for real-time adaptation in time-varying environments. However, most existing works assume a stationary or predictably dynamic user distribution (UD), which makes UD-specific strategies insufficient when a MUN is deployed in unknown environments. This paper investigates distributed user connectivity maximization in a MUN with generalization to arbitrary UDs. The problem is formulated as a time-coupled combinatorial nonlinear non-convex optimization. A multi-agent CNN-enhanced deep Q learning (MA-CDQL) algorithm is proposed, integrating a ResNet-based CNN that analyzes the input UD in real time. A heatmap algorithm transforms the raw UD into a continuous density map to improve learning efficiency.
@inproceedings{li2025maximizing,
title = {Maximizing User Connectivity in AI-Enabled Multi-UAV Networks: A Distributed Strategy Generalized to Arbitrary User Distributions},
author = {Li, Bowei and Xu, Yang and Zhang, Ran and Xie, Jiang and Wang, Miao},
booktitle = {IEEE International Conference on Communications (ICC)},
pages = {530--535},
year = {2025}
}
Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM
Scientific Reports, 14(1):5827, 2024
Danmakus are user-generated comments overlaid on videos, enabling real-time interactions between viewers and video content. Their emotional orientation can reflect viewers' attitudes toward video segments, helping platforms optimize recommendation and evaluate users' abnormal emotion levels. We propose a video danmaku sentiment analysis method based on MIBE-RoBERTa-FF-BiLSTM. We construct a Bilibili Must-Watch List and Top Video Danmaku Sentiment Dataset of 10,000 positive/negative danmakus across 18 themes; a new word recognition algorithm based on mutual information and branch entropy discovers 2,610 irregular network words; Maslow's hierarchy of needs guides consistent annotation. The proposed model achieves an F1 of 94.06%.
@article{zhao2024sentiment,
title = {Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM},
author = {Zhao, Jianbo and Liu, Huailiang and Wang, Yakai and Zhang, Weili and Zhang, Xiaojin and Li, Bowei and Sun, Tong and Qi, Yanwei and Zhang, Shanzhuang},
journal = {Scientific Reports},
volume = {14},
number = {1},
pages = {5827},
year = {2024}
}
Research on Domain Ontology Construction Based on the Content Features of Online Rumors
Scientific Reports, 14(1):12134, 2024
Online rumors are widespread and difficult to identify, bringing serious harm to society and individuals. To effectively detect and govern them, in-depth semantic analysis is required. This paper proposes a TFI domain ontology construction method aiming to achieve semantic parsing and reasoning of rumor text content. Starting from the term, frame, and instance layers, and based on top-level ontology reuse, core literature feature extraction, and discovery of new concepts, the method obtains five parent classes and 88 subclasses. OWL is used for encoding, Protégé for visualization, and SWRL rules with a pellet reasoner mine implicit knowledge and judge rumor categories.
@article{zhao2024research,
title = {Research on Domain Ontology Construction Based on the Content Features of Online Rumors},
author = {Zhao, Jianbo and Liu, Huailiang and Zhang, Weili and Sun, Tong and Chen, Qiuyi and Wang, Yuehai and Cheng, Jiale and Zhuang, Yan and Zhang, Xiaojin and Zhang, Shanzhuang and others},
journal = {Scientific Reports},
volume = {14},
number = {1},
pages = {12134},
year = {2024}
}