arXiv subjects

Yonghui Li

Publications and source records attributed to Yonghui Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Hybrid Centralized Distributed Control for Lifelong MAPF over Wireless Connections

In lifelong multi-agent path finding (MAPF) with many robots, unreliable wireless links and stochastic executions are the norm. Existing approaches typically either rely on centralized planning under idealized communication, or run fully distributed local controllers with fixed communication patterns; they rarely couple communication scheduling with policy learning, and thus struggle when bandwidth is scarce or packets are frequently dropped. We address this joint control--communication problem and propose a hybrid centralized--distributed scheme: a centralized cloud policy sends small residual corrections only when selected, while a lightweight on-board Gated recurrent unit (GRU) policy provides a safe default fallback when wireless connection is not available.

eess.SY↗

arXiv2025

Medical Referring Image Segmentation via Next-Token Mask Prediction

Medical Referring Image Segmentation (MRIS) involves segmenting target regions in medical images based on natural language descriptions. While achieving promising results, recent approaches usually involve complex design of multimodal fusion or multi-stage decoders. In this work, we propose NTP-MRISeg, a novel framework that reformulates MRIS as an autoregressive next-token prediction task over a unified multimodal sequence of tokenized image, text, and mask representations. This formulation streamlines model design by eliminating the need for modality-specific fusion and external segmentation models, supports a unified architecture for end-to-end training. It also enables the use of pretrained tokenizers from emerging large-scale multimodal models, enhancing generalization and adaptability. More importantly, to address challenges under this formulation-such as exposure bias, long-tail token distributions, and fine-grained lesion edges-we propose three novel strategies: (1) a Next-k Token Prediction (NkTP) scheme to reduce cumulative prediction errors, (2) Token-level Contrastive Learning (TCL) to enhance boundary sensitivity and mitigate long-tail distribution effects, and (3) a memory-based Hard Error Token (HET) optimization strategy that emphasizes difficult tokens during training. Extensive experiments on the QaTa-COV19 and MosMedData+ datasets demonstrate that NTP-MRISeg achieves new state-of-the-art performance, offering a streamlined and effective alternative to traditional MRIS pipelines.

cs.CV↗

arXiv2025

Hybrid-Task Meta-Learning: A GNN Approach for Scalable and Transferable Bandwidth Allocation

In this paper, we develop a deep learning-based bandwidth allocation policy that is: 1) scalable with the number of users and 2) transferable to different communication scenarios, such as non-stationary wireless channels, different quality-of-service (QoS) requirements, and dynamically available resources. To support scalability, the bandwidth allocation policy is represented by a graph neural network (GNN), with which the number of training parameters does not change with the number of users. To enable the generalization of the GNN, we develop a hybrid-task meta-learning (HML) algorithm that trains the initial parameters of the GNN with different communication scenarios during meta-training. Next, during meta-testing, a few samples are used to fine-tune the GNN with unseen communication scenarios. Simulation results demonstrate that our HML approach can improve the initial performance by 8.79%, and sample efficiency by 73%, compared with existing benchmarks. After fine-tuning, our near-optimal GNN-based policy can achieve close to the same reward with much lower inference complexity compared to the optimal policy obtained using iterative optimization. Numerical results validate that our HML can reduce the computation time by approximately 200 to 2000 times than the optimal iterative algorithm.

cs.NI↗

arXiv2025

Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial

The rapid advancement toward sixth-generation (6G) wireless networks has significantly intensified the complexity and scale of optimization problems, including resource allocation and trajectory design, often formulated as combinatorial problems in large discrete decision spaces. However, traditional optimization methods, such as heuristics and deep reinforcement learning (DRL), struggle to meet the demanding requirements of real-time adaptability, scalability, and dynamic handling of user intents in increasingly heterogeneous and resource-constrained network environments. Large language models (LLMs) present a transformative paradigm by enabling natural language-driven problem formulation, context-aware reasoning, and adaptive solution refinement through advanced semantic understanding and structured reasoning capabilities. This paper provides a systematic and comprehensive survey of LLM-enabled optimization frameworks tailored for wireless networks. We first introduce foundational design concepts and distinguish LLM-enabled methods from conventional optimization paradigms. Subsequently, we critically analyze key enabling methodologies, including natural language modeling, solver collaboration, and solution verification processes. Moreover, we explore representative case studies to demonstrate LLMs' transformative potential in practical scenarios such as optimization formulation, low-altitude economy networking, and intent networking. Finally, we discuss current research challenges, examine prominent open-source frameworks and datasets, and identify promising future directions to facilitate robust, scalable, and trustworthy LLM-enabled optimization solutions for next-generation wireless networks.

cs.NI↗

arXiv2025

Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions

The rapid expansion of sixth-generation (6G) wireless networks and the Internet of Things (IoT) has catalyzed the evolution from centralized cloud intelligence towards decentralized edge general intelligence. However, traditional edge intelligence methods, characterized by static models and limited cognitive autonomy, fail to address the dynamic, heterogeneous, and resource-constrained scenarios inherent to emerging edge networks. Agentic artificial intelligence (Agentic AI) emerges as a transformative solution, enabling edge systems to autonomously perceive multimodal environments, reason contextually, and adapt proactively through continuous perception-reasoning-action loops. In this context, the agentification of edge intelligence serves as a key paradigm shift, where distributed entities evolve into autonomous agents capable of collaboration and continual adaptation. This paper presents a comprehensive survey dedicated to Agentic AI and agentification frameworks tailored explicitly for edge general intelligence. First, we systematically introduce foundational concepts and clarify distinctions from traditional edge intelligence paradigms. Second, we analyze important enabling technologies, including compact model compression, energy-aware computing strategies, robust connectivity frameworks, and advanced knowledge representation and reasoning mechanisms. Third, we provide representative case studies demonstrating Agentic AI's capabilities in low-altitude economy networks, intent-driven networking, vehicular networks, and human-centric service provisioning, supported by numerical evaluations. Furthermore, we identify current research challenges, review emerging open-source platforms, and highlight promising future research directions to guide robust, scalable, and trustworthy Agentic AI deployments for next-generation edge environments.

cs.NI↗

arXiv2025

Distributed satellite information networks: Architecture, enabling technologies, and trends

Driven by the vision of ubiquitous connectivity and wireless intelligence, the evolution of ultra-dense constellation-based satellite-integrated Internet is underway, now taking preliminary shape. Nevertheless, the entrenched institutional silos and limited, nonrenewable heterogeneous network resources leave current satellite systems struggling to accommodate the escalating demands of next-generation intelligent applications. In this context, the distributed satellite information networks (DSIN), exemplified by the cohesive clustered satellites system, have emerged as an innovative architecture, bridging information gaps across diverse satellite systems, such as communication, navigation, and remote sensing, and establishing a unified, open information network paradigm to support resilient space information services. This survey first provides a profound discussion about innovative network architectures of DSIN, encompassing distributed regenerative satellite network architecture, distributed satellite computing network architecture, and reconfigurable satellite formation flying, to enable flexible and scalable communication, computing and control. The DSIN faces challenges from network heterogeneity, unpredictable channel dynamics, sparse resources, and decentralized collaboration frameworks. To address these issues, a series of enabling technologies is identified, including channel modeling and estimation, cloud-native distributed MIMO cooperation, grant-free massive access, network routing, and the proper combination of all these diversity techniques. Furthermore, to heighten the overall resource efficiency, the cross-layer optimization techniques are further developed to meet upper-layer deterministic, adaptive and secure information services requirements. In addition, emerging research directions and new opportunities are highlighted on the way to achieving the DSIN vision.

cs.IT↗

arXiv2025

Deep Reinforcement Learning for Wireless Scheduling in Distributed Networked Control

We consider a joint uplink and downlink scheduling problem of a fully distributed wireless networked control system (WNCS) with a limited number of frequency channels. Using elements of stochastic systems theory, we derive a sufficient stability condition of the WNCS, which is stated in terms of both the control and communication system parameters. Once the condition is satisfied, there exists a stationary and deterministic scheduling policy that can stabilize all plants of the WNCS. By analyzing and representing the per-step cost function of the WNCS in terms of a finite-length countable vector state, we formulate the optimal transmission scheduling problem into a Markov decision process and develop a deep reinforcement learning (DRL) based framework for solving it. To tackle the challenges of a large action space in DRL, we propose novel action space reduction and action embedding methods for the DRL framework that can be applied to various algorithms, including Deep Q-Network (DQN), Deep Deterministic Policy Gradient (DDPG), and Twin Delayed Deep Deterministic Policy Gradient (TD3). Numerical results show that the proposed algorithm significantly outperforms benchmark policies.

eess.SY↗

arXiv2025

Short Wins Long: Short Codes with Language Model Semantic Correction Outperform Long Codes

This paper presents a novel semantic-enhanced decoding scheme for transmitting natural language sentences with multiple short block codes over noisy wireless channels. After ASCII source coding, the natural language sentence message is divided into segments, where each is encoded with short block channel codes independently before transmission. At the receiver, each short block of codewords is decoded in parallel, followed by a semantic error correction (SEC) model to reconstruct corrupted segments semantically. We design and train the SEC model based on Bidirectional and Auto-Regressive Transformers (BART). Simulations demonstrate that the proposed scheme can significantly outperform encoding the sentence with one conventional long LDPC code, in terms of block error rate (BLER), semantic metrics, and decoding latency. Finally, we proposed a semantic hybrid automatic repeat request (HARQ) scheme to further enhance the error performance, which selectively requests retransmission depends on semantic uncertainty.

eess.SP↗

arXiv2025

Half a Century of Distributed Byzantine Fault-Tolerant Consensus: Design Principles and Evolutionary Pathways

The concept of distributed consensus originated in the 1970s and gained widespread attention following Leslie Lamport's influential publication on the Byzantine Generals Problem in the 1980s. Over the past five decades, distributed consensus has become an extensively researched field. Practical Byzantine Fault Tolerance (PBFT) has emerged as a prominent and widely adopted solution due to its conceptual clarity, effectiveness, and resilience to arbitrary failures. However, PBFT does not universally address all scenarios, highlighting the necessity of developing a comprehensive understanding of the history, evolution, and foundational principles of distributed consensus. This article systematically reviews the historical evolution and foundational principles of distributed consensus, examining pivotal advancements including fault-tolerant state machine replication (SMR), consensus protocols in partially synchronous and asynchronous networks, and recent innovations in Directed Acyclic Graph (DAG)-based consensus mechanisms. We further analyse the core design rationales, essential components, and underlying primitives across various distributed fault-tolerant protocols. The relationship between BFT consensus mechanisms and their applications in environments requiring robust resilience against adversarial faults is also explored. Finally, we discuss emerging research areas and challenges, such as consensus for wireless and blockchain scenarios, highlighting potential future developments. This comprehensive overview offers valuable insights to inform the design, optimisation, and implementation of distributed consensus systems across multiple application scenarios.

cs.DC↗

arXiv2025

Covert Prompt Transmission for Secure Large Language Model Services

This paper investigates covert prompt transmission for secure and efficient large language model (LLM) services over wireless networks. We formulate a latency minimization problem under fidelity and detectability constraints to ensure confidential and covert communication by jointly optimizing the transmit power and prompt compression ratio. To solve this problem, we first propose a prompt compression and encryption (PCAE) framework, performing surprisal-guided compression followed by lightweight permutation-based encryption. Specifically, PCAE employs a locally deployed small language model (SLM) to estimate token-level surprisal scores, selectively retaining semantically critical tokens while discarding redundant ones. This significantly reduces computational overhead and transmission duration. To further enhance covert wireless transmission, we then develop a group-based proximal policy optimization (GPPO) method that samples multiple candidate actions for each state, selecting the optimal one within each group and incorporating a Kullback-Leibler (KL) divergence penalty to improve policy stability and exploration. Simulation results show that PCAE achieves comparable LLM response fidelity to baseline methods while reducing preprocessing latency by over five orders of magnitude, enabling real-time edge deployment. We further validate PCAE effectiveness across diverse LLM backbones, including DeepSeek-32B, Qwen-32B, and their smaller variants. Moreover, GPPO reduces covert transmission latency by up to 38.6\% compared to existing reinforcement learning strategies, with further analysis showing that increased transmit power provides additional latency benefits.

cs.NI↗

arXiv2025

Optimal Linear MAP Decoding of Convolutional Codes

In this paper, we propose a linear representation of BCJR maximum a posteriori probability (MAP) decoding of a rate 1/2 convolutional code (CC), referred to as the linear MAP decoding (LMAP). We discover that the MAP forward and backward decoding can be implemented by the corresponding dual soft input and soft output (SISO) encoders using shift registers. The bidrectional MAP decoding output can be obtained by combining the contents of respective forward and backward dual encoders. Represented using simple shift-registers, LMAP decoder maps naturally to hardware registers and thus can be easily implemented. Simulation results demonstrate that the LMAP decoding achieves the same performance as the BCJR MAP decoding, but has a significantly reduced decoding delay. For the block length 64, the CC of the memory length 14 with LMAP decoding surpasses the random coding union (RCU) bound by approximately 0.5 dB at a BLER of $10^{-3}$, and closely approaches both the normal approximation (NA) and meta-converse (MC) bounds.

cs.IT↗

arXiv2025

A Method to Decipher "Genome" from Interatomic Cohesion in the Exploration for a "Central Dogma" Replacement in Material Science

In the ball-stick model, interatomic cohesions are considered "sticks". But enormous details and features of the "sticks" are usually oversimplified as indexed quantities or equivocated as geometry characteristics. These indexed quantities or geometry characteristics not only limit the explanatory capability to a few chemical/physical aspects but also eliminate generativity for expected resemblance. And these limitations can be related to the information loss during the conversion. Herein, inspired by the central dogma, a framework is introduced to compact interatomic cohesions into a detailed residue-by-residue "genome" with matched encoding/decoding tools. The framework fuses the quantum mechanical aspects, auto feature extraction, nanostructures and/or simulations, and generative models. As a proof of concept, the realization introduced in this work adopted bosonic/fermionic features, an autoencoder with image recognition processes, Density Functional Theory simulations, and a thiolate-protected gold nanocluster dataset. After repetitive modeling, validating, and analysis based on 26,528 simulated interatomic images, the interatomic cohesion can be almost losslessly encoded into an 8-value-genome, and the genome encoder-decoder pair is also obtained. The model is then automatically extended into a generative model which converts any arbitrary 8-value-genome to a bond image.

cond-mat.mes-hall↗

arXiv2025

Vehicular Multi-Tier Distributed Computing with Hybrid THz-RF Transmission in Satellite-Terrestrial Integrated Networks

In this paper, we propose a Satellite-Terrestrial Integrated Network (STIN) assisted vehicular multi-tier distributed computing (VMDC) system leveraging hybrid terahertz (THz) and radio frequency (RF) communication technologies. Task offloading for satellite edge computing is enabled by THz communication using the orthogonal frequency division multiple access (OFDMA) technique. For terrestrial edge computing, we employ non-orthogonal multiple access (NOMA) and vehicle clustering to realize task offloading. We formulate a non-convex optimization problem aimed at maximizing computation efficiency by jointly optimizing bandwidth allocation, task allocation, subchannel-vehicle matching and power allocation. To address this non-convex optimization problem, we decompose the original problem into four sub-problems and solve them using an alternating iterative optimization approach. For the subproblem of task allocation, we solve it by linear programming. To solve the subproblem of sub-channel allocation, we exploit many-to-one matching theory to obtain the result. The subproblem of bandwidth allocation of OFDMA and the subproblem of power allocation of NOMA are solved by quadratic transformation method. Finally, the simulation results show that our proposed scheme significantly enhances the computation efficiency of the STIN-based VMDC system compared with the benchmark schemes.

eess.SP↗

arXiv2025

GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection

Geometry plays a significant role in monocular 3D object detection. It can be used to estimate object depth by using the perspective projection between object's physical size and 2D projection in the image plane, which can introduce mathematical priors into deep models. However, this projection process also introduces error amplification, where the error of the estimated height is amplified and reflected into the projected depth. It leads to unreliable depth inferences and also impairs training stability. To tackle this problem, we propose a novel Geometry Uncertainty Propagation Network (GUPNet++) by modeling geometry projection in a probabilistic manner. This ensures depth predictions are well-bounded and associated with a reasonable uncertainty. The significance of introducing such geometric uncertainty is two-fold: (1). It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning. (2). It can be derived to a highly reliable confidence to indicate the quality of the 3D detection result, enabling more reliable detection inference. Experiments show that the proposed approach not only obtains (state-of-the-art) SOTA performance in image-based monocular 3D detection but also demonstrates superiority in efficacy with a simplified framework.

cs.CV↗

arXiv2024

The Guesswork of Ordered Statistics Decoding: Guesswork Complexity and Decoder Design

This paper investigates guesswork over ordered statistics and formulates the achievable guesswork complexity of ordered statistics decoding (OSD) in binary additive white Gaussian noise (AWGN) channels. The achievable guesswork complexity is defined as the number of test error patterns (TEPs) processed by OSD immediately upon finding the correct codeword estimate. The paper first develops a new upper bound for guesswork over independent sequences by partitioning them into Hamming shells and applying Hölder's inequality. This upper bound is then extended to ordered statistics, by constructing the conditionally independent sequences within the ordered statistics sequences. Next, we apply these bounds to characterize the statistical moments of the OSD guesswork complexity. We show that the achievable guesswork complexity of OSD at maximum decoding order can be accurately approximated by the modified Bessel function, which increases exponentially with code dimension. We also identify a guesswork complexity saturation threshold, where increasing the OSD decoding order beyond this threshold improves error performance without further raising the achievable guesswork complexity. Finally, the paper presents insights on applying these findings to enhance the design of OSD decoders.

cs.IT↗

arXiv2024

Distributed Massive MIMO-Aided Task Offloading in Satellite-Terrestrial Integrated Multi-Tier VEC Networks

This paper proposes a distributed massive multiple input multiple-output (DM-MIMO) aided multi-tier vehicular edge computing (VEC) system. In particular, each vehicle terminal (VT) offloads its computational task to the roadside unit (RSU) by orthogonal frequency division multiple access (OFDMA), which can be computed locally at the RSU and offloaded to the central processing unit (CPU) via massive satellite access points (SAPs) for remote computation. By considering the partial task offloading model, we consider the joint optimization of the task offloading, subchannel allocation and precoding optimization to minimize the total cost in terms of total delay and energy consumption. To solve this non-convex problem, we transform the original problem into three sub-problems and use the alternate optimization algorithm to solve it. First, we transform the subcarrier allocation problem of discrete variables into convex optimization problem of continuous variables. Then, we use multiple quadratic transformations and Lagrange multiplier method to transform the non-convex subproblem of optimizing precoding vectors into a convex problem, while the task offloading subproblem is a convex problem. Given the subcarrier and the task allocation and precoding result, we finally find the joint optimized results by iterative optimization algorithm. Simulation results show that our proposed algorithm is superior to other benchmarks.

cs.DC↗

arXiv2024

GNN-based Auto-Encoder for Short Linear Block Codes: A DRL Approach

This paper presents a novel auto-encoder based end-to-end channel encoding and decoding. It integrates deep reinforcement learning (DRL) and graph neural networks (GNN) in code design by modeling the generation of code parity-check matrices as a Markov Decision Process (MDP), to optimize key coding performance metrics such as error-rates and code algebraic properties. An edge-weighted GNN (EW-GNN) decoder is proposed, which operates on the Tanner graph with an iterative message-passing structure. Once trained on a single linear block code, the EW-GNN decoder can be directly used to decode other linear block codes of different code lengths and code rates. An iterative joint training of the DRL-based code designer and the EW-GNN decoder is performed to optimize the end-end encoding and decoding process. Simulation results show the proposed auto-encoder significantly surpasses several traditional coding schemes at short block lengths, including low-density parity-check (LDPC) codes with the belief propagation (BP) decoding and the maximum-likelihood decoding (MLD), and BCH with BP decoding, offering superior error-correction capabilities while maintaining low decoding complexity.

cs.LG↗

arXiv2024

Toward Democratized Generative AI in Next-Generation Mobile Edge Networks

The rapid development of generative AI technologies, including large language models (LLMs), has brought transformative changes to various fields. However, deploying such advanced models on mobile and edge devices remains challenging due to their high computational, memory, communication, and energy requirements. To address these challenges, we propose a model-centric framework for democratizing generative AI deployment on mobile and edge networks. First, we comprehensively review key compact model strategies, such as quantization, model pruning, and knowledge distillation, and present key performance metrics to optimize generative AI for mobile deployment. Next, we provide a focused review of mobile and edge networks, emphasizing the specific challenges and requirements of these environments. We further conduct a case study demonstrating the effectiveness of these strategies by deploying LLMs on real mobile edge devices. Experimental results highlight the practicality of democratized LLMs, with significant improvements in generalization accuracy, hallucination rate, accessibility, and resource consumption. Finally, we discuss potential research directions to further advance the deployment of generative AI in resource-constrained environments.

cs.NI↗