Bowen Gu

Bowen Gu

Auto-generated profile, based on publicly available information

Bowen Gu

Xinjiang University, Urumqi, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 November 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YHYating He
Yating He
ZHZhenzhen He
Zhenzhen He
TGTiquan Gu
Tiquan Gu
BGBowen Gu
Bowen Gu
YWYaling Wan
Yaling Wan
MLMin Li
Min Li
Due to their extensive common-sense knowledge and linguistic understanding, large language models (LLMs) have demonstrated remarkable capabilities in text comprehension and logical reasoning for natural language processing tasks. Traditional prompt-based learning methods, which rely on contextual pattern matching, have proven to be effective in extracting knowledge from LLMs. However, these approaches are constrained by training data pattern matching, overlook reasoning processes, and consequently suffer from suboptimal prompt performance and limited interpretability. Moreover, considering that the intermediate steps generated by single-chain reasoning may not effectively assist LLMs in identifying the sentiment polarity of aspect terms, and that multiple reasoning paths often exist for complex reasoning tasks to reach correct conclusions, this paper proposes a Multi-Chain Thought Prompt Learning framework (MT-CPL). Starting from fundamental concepts, this method simulates human multi-path reasoning patterns to progressively construct comprehensive thought processes and deeply explore sentiment cues. Based on syntactic structures and the semantic logic of text, the framework incorporates four distinct perspectives of text comprehension: hierarchical reading, experiential reading, keyword-based reading, and analogical reading. It establishes a multi-chain prompt template and employs voting mechanisms to select correct reasoning path outcomes. The MT-CPL approach aims to guide LLMs in mining multi-dimensional textual information from different perspectives, gradually uncovering hidden contextual sentiment clues, while mitigating issues caused by irrelevant sentiment cues in intermediate reasoning steps. By decomposing main tasks incrementally, the method achieves progressive reasoning, effectively reduces the difficulty of direct analysis, and further enhances model interpretability through the integration of inherent common-sense knowledge.

6 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
XYXianhua Yu
Xianhua Yu
Dong LiDong Li
Dong Li
BGBowen Gu
Bowen Gu
LYLiuqing Yang
Liuqing Yang
SSSumei Sun
Sumei Sun
George K. KaragiannidisGeorge K. Karagiannidis
George K. Karagiannidis
Intelligent reflecting surfaces (IRSs) have become a vital technology for improving the spectrum and energy efficiency of forthcoming wireless networks. Nevertheless, practical implementation is obstructed by the excessive overhead associated with the frequent transmission of phase shift information (PSI) over bandwidth-constrained control lines. Current deep learning-based compression methods mitigate this problem but are constrained by elevated decoder complexity, inadequate flexibility to dynamic channels, and static compression ratios. This research presents a prompt-conditioned PSI compression system that integrates prompt learning inspired by large models into the PSI compression process to address these difficulties. A hybrid prompt technique that integrates soft prompt concatenation with feature-wise linear modulation (FiLM) facilitates adaptive encoding across diverse signal-to-noise ratios (SNRs), fading kinds, and compression ratios. Furthermore, a variable rate technique incorporates the compression ratio into the prompt embeddings through latent masking, enabling a singular model to adeptly balance reconstruction accuracy. Additionally, a lightweight depthwise convolutional gating (DWCG) decoder facilitates precise feature reconstruction with minimal complexity. Comprehensive simulations indicate that the proposed framework significantly reduces NMSE compared to traditional autoencoder baselines, while ensuring robustness across various channel circumstances and accommodating variable compression ratios within a single model. These findings underscore the framework's promise as a scalable and efficient solution for real-time IRS control in next-generation wireless networks.

4 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
HQHaohao Qin
Haohao Qin
BGBowen Gu
Bowen Gu
Dong LiDong Li
Dong Li
XYXianhua Yu
Xianhua Yu
LWLiejun Wang
Liejun Wang
SSSumei Sun
Sumei Sun
In this paper, cooperative energy recycling (CER) is investigated in wireless-powered mobile edge computing systems. Unlike conventional architectures that rely solely on a dedicated power source, wireless sensors are additionally enabled to recycle energy from peer transmissions. To evaluate system performance, a joint computation optimization problem is formulated that integrates local computing and computation offloading, under an alpha-fairness objective that balances total computable data and user fairness while satisfying energy, latency, and task size constraints. Due to the inherent non-convexity introduced by coupled resource variables and fairness regularization, a variable-substitution technique is employed to transform the problem into a convex structure, which is then efficiently solved using Lagrangian duality and alternating optimization. To characterize the fairness-efficiency tradeoff, closed-form solutions are derived for three representative regimes: zero fairness, common fairness, and max-min fairness, each offering distinct system-level insights. Numerical results validate the effectiveness of the proposed CER-enabled framework, demonstrating significant gains in throughput and adaptability over benchmark schemes. The tunable alpha fairness mechanism provides flexible control over performance-fairness trade-offs across diverse scenarios.

25 August 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
GLGong Li
Gong Li
HGHuiqiang Guo
Huiqiang Guo
MLMengdi Liu
Mengdi Liu
ZWZiyin Wei
Ziyin Wei
BGBowen Gu
Bowen Gu
AMAnd Dan Ma
And Dan Ma
Multimodal Emotion Recognition in Conversation (MERC) aims to infer speakers’ affective states from heterogeneous cues within evolving dialogue contexts. Although graph-based methods have shown strong potential in modeling conversational structures, they often introduce history through dense or predefined connections and obtain unified multimodal representations before prediction. This paradigm may propagate irrelevant contextual information, overlook the different roles of same-speaker and cross-speaker dependencies, and underexploit useful corrective cues carried by inconsistent modalities. To address these limitations, we propose HiRoC, a multimodal emotion recognition framework that selectively routes emotion-relevant history and calibrates predictions using cross-modal disagreement. Specifically, a Historical Relevance Filter (HRF) scores how relevant each past utterance is to the current one and suppresses weakly related context before propagation. Guided by the resulting dependency prior, a Speaker-Typed Routing Graph (STRG) keeps intra- and inter-speaker dependencies apart and propagates the retained history along sparse, temporally directed paths. In parallel, the filtered modality-specific representations feed a hypergraph backbone for high-order utterance- and modality-level interactions, which the routing branch complements with speaker-aware temporal dependencies. A Cross-Modal Residual Correction (CMRC) module then uses modal disagreement to adjust the main prediction at the decision level, so that conflicting cues are not averaged away. On IEMOCAP and MELD, HiRoC outperforms representative state-of-the-art methods.

28 July 2026 in Advanced Information and Communication
Verified
Journal Article
Closed access
PDF file
ZHZishan Huang
Zishan Huang
Yongjun XuYongjun Xu
Yongjun Xu
BGBowen Gu
Bowen Gu
HZHaibo Zhang
Haibo Zhang
Resource management in sixth-generation (6G) space-air–ground integrated network (SAGINs) is becoming increasingly challenging due to cross-tier heterogeneity, multi-timescale dynamics, and distributed decision making under partial and delayed information. These characteristics expose the limitations of conventional optimization-based and learning-based approaches, whose effectiveness often depends on accurate modeling, large amounts of task-specific data, or opaque policy adaptation. This article revisits the evolution of SAGIN resource management from optimization and learning to reasoning-centric, large language model (LLM)-enabled agentic intelligence. A unified taxonomy of existing paradigms is first presented, clarifying their respective strengths and limitations. The operational foundations of LLM-enabled agents (LEAs) are then introduced, including perception, memory, thought, execution, and tool-grounded decision making, followed by a discussion of emerging multi-agent frameworks for distributed orchestration. Building on this foundation, LEAs are shown to support proactive spectrum control, autonomous cross-tier routing, multi-service scheduling, and dynamic network slicing. Finally, key open challenges are identified, and future directions toward practical, trustworthy, and scalable agentic resource management in 6G SAGINs are outlined.

4 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
HQHaohao Qin
Haohao Qin
BGBowen Gu
Bowen Gu
XYXianhua Yu
Xianhua Yu
HXHao Xie
Hao Xie
YXYongjun Xu
Yongjun Xu
LWLiejun Wang
Liejun Wang
Cooperative energy recycling (CER) offers a new way to boost energy utilization in wireless-powered multi-access edge computing (MEC) networks, yet its integration with computation-communication co-design remains underexplored. This paper proposes a CER-enabled MEC framework that maximizes the minimum computable data among users under energy causality, latency, and power constraints. The intractable problem is reformulated into a convex form through relaxation, maximum ratio combining, and variable substitution, and closed-form solutions are derived via Lagrangian duality and alternating optimization, offering analytical insights. Simulation results verify that the proposed CER mechanism markedly increases total computable data while maintaining equitable performance across heterogeneous users.