Searcharxiv⌕ Search

arXiv subjects

Hongyang Du

Publications and source records attributed to Hongyang Du.

At least 37 records · Page 2Linked to original sources
arXiv2026

MORES: Mobile Reasoning-as-a-Service via Distributed LLM Inference-Time Scaling

Inference-time scaling has emerged as an effective approach for enhancing the capabilities of Large Language Models (LLMs), addressing the growing demand for stronger reasoning without increasing model size. This novel form of LLM scaling comprises two representative approaches: explicit reasoning, which generates intermediate chain-of-thought tokens during an explicit thinking phase, and implicit reasoning, which iteratively updates hidden states in the latent space without producing explicit outputs. Despite their effectiveness, both paradigms incur substantial computational and memory overhead, raising challenges for deployment on resource-constrained edge devices. To address these issues, we propose a Mobile Reasoning-as-aService (MORES) framework that treats reasoning as a computational service accessible to edge devices over wireless networks. Focusing on implicit reasoning, we leverage its recursive structure to partition hiddenstate updates between edge devices and servers, enabling cooperative inference that allows devices to access additional cloud computation on demand. To optimize long-term performance, we formulate a joint computation and communication scheduling problem and solve it using a semantic Mixture-of-Experts (MoE)-based Deep Reinforcement Learning (DRL) algorithm to address heterogeneity in wireless conditions and task demands. The agent adaptively allocates resources by adjusting the number of recurrent steps and the transmission pruning rate, while a semantic router enables high-speed gating for real-time expert selection. Experimental results show that the proposed method achieves an approximately 18% improvement in system throughput over the baseline Soft Actor-Critic (SAC) algorithm. Our code is available at https://github.com/NICE-HKU/MORES.

cs.NI↗
arXiv2026

Multi-objective Low-altitude IRS-assisted ISAC Optimization via Generative AI-enhanced Deep Reinforcement Learning

Integrated sensing and communication (ISAC) has garnered substantial research interest owing to its pivotal role in advancing the development of next-generation (6G) wireless networks. However, achieving a performance balance between communication and sensing in the dual-function radar communication (DFRC)-based ISAC system remains a significant challenge. In this paper, a low-altitude intelligent reflecting surface (IRS)-assisted ISAC system is explored, where a base station (BS) supports dual-functional operations, enabling both data transmission for multiple users and sensing for a blocked target, with the channel quality enhanced by an IRS mounted on the unmanned aerial vehicle (UAV). Moreover, we formulate an integrated communication, sensing, and energy efficiency multi-objective optimization problem (CSEMOP), which aims to maximize the communication rate of the users and the sensing rate of the target, while minimizing UAV propulsion energy consumption by jointly optimizing the BS beamforming matrix, IRS phase shifts, the flight velocity and angle of the UAV. Considering the non-convexity, trade-off, and dynamic nature of the formulated CSEMOP, we propose a generative diffusion model-based deep deterministic policy gradient (GDMDDPG) algorithm to solve the problem. Specifically, the diffusion model is incorporated into the actor network of DDPG to improve the action quality, with noise perturbation mechanism for better exploration and recent prioritized experience replay (RPER) sampling mechanism for enhanced training efficiency. Simulation results indicate that the GDMDDPG algorithm delivers superior performance compared to the existing methods.

cs.NI↗
arXiv2026

Graph Diffusion-Based AeBS Deployment and Resource Allocation in RSMA-Enabled URLLC Low-Altitude Wireless Networks

As a key component of low-altitude wireless networks, aerial base stations (AeBSs) provide flexible and reliable wireless coverage to support 6G ultra-reliable and low-latency communication (URLLC) services. However, limited spectrum resources and severe co-channel interference pose significant challenges to the deployment and resource allocation of AeBSs. To address these limitations, this paper proposes a novel rate-splitting multiple access (RSMA)-enabled transmission design to manage interference and enhance URLLC services in spectrum-constrained multi-AeBS networks. We formulate a joint optimization problem involving AeBS deployment, user association, and resource allocation to maximize the sum rate and coverage of system. Given the NP-hard nature of the problem, we propose a novel alternating optimization framework based on the generative graph diffusion models. Specifically, we model AeBSs and ground users as graph nodes, then we employ a discrete graph generation process solved via denoising diffusion to explore the combinatorial space of deployment and association strategies. Moreover, the successive convex approximation (SCA) is adopted to optimize AeBS beamforming and RSMA rate allocation under finite blocklength constraints. Extensive simulations demonstrate that the proposed algorithm outperforms existing methods in terms of convergence speed, sum rate, and coverage, while also exhibiting robust performance under varying network densities and interference levels.

cs.NI↗
arXiv2026

CoDeR: Local Constraint-Compatible Retrieval Beyond Semantic Similarity

Information retrieval systems have long treated semantic similarity as a proxy for relevance. For constraint-sensitive queries, this proxy can fail when a document is topically close to the query but supports the opposite constraint direction, such as satisfying an attribute that should be excluded or affirming a relation that should be negated. We study this failure as constraint-violating evidence exposure and propose CoDeR, a local constraint-compatible dense retrieval method that separates topical relevance from constraint compatibility. CoDeR keeps a standard topical encoder for candidate coverage and adds a compatibility scorer, implemented as a bi-encoder, trained with lexical-polarity supervision over contrastive satisfying and violating evidences. The compatibility signal can be used to rescore topical candidates or to retrieve an auxiliary compatibility-oriented candidate set, producing a ranked document list without external Large Language Model~(LLM) calls at inference time. We evaluate CoDeR on controlled diagnostics and public negative-constraint retrieval benchmarks. Across three controlled diagnostic sets targeting antonymy, negation, and exclusion, CoDeR reduces V@2 by 20.59, 23.53, and 5.77 points relative to the strongest non-CoDeR baselines, and improves FVR by pushing the first violating document deeper in the ranking.

cs.IR↗
arXiv2026

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit incentives for geometric coherence. To address this, we introduce VideoGPA (Video Geometric Preference Alignment), a data-efficient self-supervised framework that leverages a geometry foundation model to automatically derive dense preference signals that guide VDMs via Direct Preference Optimization (DPO). This approach effectively steers the generative distribution toward inherent 3D consistency without requiring human annotations. VideoGPA significantly enhances temporal stability, geometric plausibility, and motion coherence using minimal preference pairs, consistently outperforming state-of-the-art baselines in extensive experiments.

cs.CV↗
arXiv2026

Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge

Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its distributed deployment to enable cooperative token generation in a multiuser edge system; its advantage is to effectively balance computational loads between resource-constrained devices and servers. The resulting architecture, termed Multi-access SPIN (Multi-SPIN), utilizes on-device small language models to generate and upload candidate token drafts, while an edge server operates the LLM to verify them in parallel batches. Given the severe heterogeneity in users' computation and communication capabilities, the draft length emerges as a critical control variable that influences node-level computation loads and multi-access latency, thereby governing the sum token goodput. Consequently, considering frequency-division multiple access, we investigate the problem of multi-access draft control, a joint optimization of draft-length control and bandwidth allocation to maximize sum token goodput. We examine two cases: (1) homogeneous draft lengths across users to facilitate server-side batching, and (2) heterogeneous draft lengths to introduce a new dimension for goodput enhancement. By developing decomposition methods, we reduce these complex optimizations into tractable sub-problems, which allow efficient draft control algorithms to be derived in closed form. Our analysis shows that the optimal bandwidth allocation compensates users with weaker computation-and-communication capabilities in the homogeneous case due to the batching synchronization requirements, whereas its heterogeneous-case counterpart rewards users with higher acceptance rates by relaxing such requirements. Experiments using Llama-2 and Qwen3.5 model pairs across diverse tasks demonstrate that Multi-SPIN improves goodput by up to 88% over heterogeneity-agnostic baselines.

cs.DC↗
arXiv2026

A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.

cs.CV↗
arXiv2026

Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage

Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most methods train agents at a single fixed difficulty throughout the entire run. We term this static-difficulty regime environmental meta-stationarity and show that it caps policy generalization and steers learning toward shallow local optima. To break this regime, we propose CL-MARL, a dynamic curriculum learning framework that adapts opponent strength online from win-rate signals, advancing or regressing the task as agents master it. Its scheduler, FlexDiff, fuses momentum-based trend estimation with sliding-window dual-curve monitoring of training and evaluation returns, yielding stable difficulty transitions without manual tuning. Because a moving curriculum amplifies non-stationarity and sparsifies global rewards, we introduce the Counterfactual Group Relative Policy Advantage (CGRPA), which extends GRPO-style group-relative optimization with counterfactual baselines to disentangle each agent's contribution under shifting team dynamics. On the StarCraft Multi-Agent Challenge (SMAC), CL-MARL attains a 40% mean win rate on the super-hard maps with an average episode return of 17.85, exceeding the QMIX, OW-QMIX, DER, EMC, and MARR baselines by +2.94 on average, while reaching its peak win rate roughly 1.28faster on 8m_vs_9m and 1.42 faster on 3s5z_vs_3s6z than the strongest baseline. The implementation is publicly available at https://github.com/NICE-HKU/CL2MARL-SMAC.

cs.AI↗
arXiv2026

Optimizing Split Federated Learning with Unstable Client Participation

To enable training of large artificial intelligence (AI) models at the network edge, split federated learning (SFL) has emerged as a promising approach by distributing computation between edge devices and a server. However, while unstable network environments pose significant challenges to SFL, prior schemes often overlook such an effect by assuming perfect client participation, rendering them impractical for real-world scenarios. In this work, we develop an optimization framework for SFL with unstable client participation. We theoretically derive the first convergence upper bound for SFL with unstable client participation by considering activation uploading failures, gradient downloading failures, and model aggregation failures. Based on the theoretical results, we formulate a joint optimization problem for client sampling and model splitting to minimize the upper bound. We then develop an efficient solution approach to solve the problem optimally. Extensive simulations on EMNIST and CIFAR-10 demonstrate the superiority of our proposed framework compared to existing benchmarks.

cs.NI↗
arXiv2026

Generative Artificial Intelligence Assisted Multi-modal Semantic Extraction for NOMA-based Image Transmissions

In this paper, we investigate a generative artificial intelligence (GAI)-assisted semantic communication framework for non-orthogonal multiple access (NOMA)-based image transmissions. Semantic users (SUs) extract cross-modal semantic features from the raw images, which are then used for image recovery by leveraging a GAI model. The GAI enhances the generalization and recovery of semantic image transmissions, while NOMA efficiently allocates transmission capacities to SUs based on their traffic demands. Thus, the semantic extraction and transmission control jointly affect both semantic recovery performance and transmission overhead. We maximize a weighted performance of transmission latency and semantic recovery accuracy by jointly optimizing the semantic feature selection at the semantic level, as well as the receive beamforming and NOMA decoding order at the transmission level. To reduce potential redundancy in semantic features and improve optimization efficiency, we develop an importance-aware and model-driven proximal policy optimization (IM-PPO) framework. Specifically, we quantify and retain high-importance semantic features to enhance the learning efficiency of PPO, while model-based optimization methods are used to adapt the transmission control variables. Numerical results validate that the joint adjustment of the semantic feature selection and the transmission control significantly improves the semantic recovery accuracy and the transmission latency performance. Moreover, the IM-PPO framework effectively leverages the model information to improve the learning efficiency compared to benchmark methods.

cs.NI↗
arXiv2026

Learning to Optimize Joint Source and RIS-assisted Channel Encoding for Multi-User Semantic Communication Systems

In this paper, we explore a joint source and reconfigurable intelligent surface (RIS)-assisted channel encoding (JSRE) framework for multi-user semantic communications, where a deep neural network (DNN) extracts semantic features for all users and the RIS provides channel orthogonality, enabling a unified semantic encoding-decoding design. We aim to maximize the overall energy efficiency of semantic communications across all users by jointly optimizing the user scheduling, the RIS's phase shifts, and the semantic compression ratio. Although this joint optimization problem can be addressed using conventional deep reinforcement learning (DRL) methods, evaluating semantic similarity typically relies on extensive real environment interactions, which can incur heavy computational overhead during training. To address this challenge, we propose a truncated DRL (T-DRL) framework, where a DNN-based semantic similarity estimator is developed to rapidly estimate the similarity score. Moreover, the user scheduling strategy is tightly coupled with the semantic model configuration. To exploit this relationship, we further propose a semantic model caching mechanism that stores and reuses fine-tuned semantic models corresponding to different scheduling decisions. A Transformer-based actor network is employed within the DRL framework to dynamically generate action space conditioned on the current caching state. This avoids redundant retraining and further accelerates the convergence of the learning process. Numerical results demonstrate that the proposed JSRE framework significantly improves the system energy efficiency compared with the baseline methods. By training fewer semantic models, the proposed T-DRL framework significantly enhances the learning efficiency.

cs.NI↗
arXiv2026

NetSpatial: Spatially Conditional Traffic Generation for Cellular Planning and Operations

Base station (BS) deployment and operation are fundamental to network performance, yet they require accurate demand understanding, which remains difficult for operators. Cellular traffic in dense urban regions is well measured but highly dynamic, which undermines prediction-based management, whereas the scarcity of traffic measurements in emerging regions limits informed deployment decisions. Existing approaches therefore either depend on manual planning heuristics or use autoregressive predictors that fail to capture stochastic traffic variation. We present NetSpatial, a unified system for cellular planning and operation through spatially conditional traffic generation. NetSpatial exploits multimodal urban context, including satellite imagery and point of interest (POI) distributions, to learn how physical environment and functional semantics shape BS demand. It uses a multi-level flow-matching architecture that separates periodic structure from residual dynamics, enabling direct generation of long-horizon traffic sequences. NetSpatial supports two complementary decision scenarios, i.e., what-if analysis for deployment planning, which ranks candidate sites using generated traffic profiles, and what-to-do support for network operation, which uses generated traffic forecasts to guide BS sleep scheduling and load balancing. Experiments on real-world cellular traffic data show that NetSpatial reduces Jensen-Shannon Divergence (JSD) by 29.44% over the strongest baseline, generalizes across cities in zero-shot experiments, and enables up to 16.8% energy savings while maintaining over 80% quality of experience.

cs.CE↗
arXiv2026

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent approaches have demonstrated that LLM agents can self-evolve from scratch with little to no data, VLMs introduce an additional visual modality that typically requires at least some seed data, such as images, to bootstrap the self-evolution process. In this work, we present Multi-model Multimodal Zero (MM-Zero), the first RL-based framework to achieve zero-data self-evolution for VLM reasoning. Moving beyond prior dual-role (Proposer and Solver) setups, MM-Zero introduces a multi-role self-evolving training framework comprising three specialized roles: a Proposer that generates abstract visual concepts and formulates questions; a Coder that translates these concepts into executable code (e.g., Python, SVG) to render visual images; and a Solver that performs multimodal reasoning over the generated visual content. All three roles are initialized from the same base model and trained using Group Relative Policy Optimization (GRPO), with carefully designed reward mechanisms that integrate execution feedback, visual verification, and difficulty balancing. Our experiments show that MM-Zero improves VLM reasoning performance across a wide range of multimodal benchmarks. MM-Zero establishes a scalable path toward self-evolving multi-model systems for multimodal models, extending the frontier of self-improvement beyond the conventional two-model paradigm.

cs.CV↗
arXiv2026

ReaCritic: Reasoning Transformer-based DRL Critic-model Scaling For Wireless Networks

Heterogeneous Networks (HetNets) pose critical challenges for intelligent management due to the diverse user requirements and time-varying wireless conditions. These factors introduce significant decision complexity, which limits the adaptability of existing Deep Reinforcement Learning (DRL) methods. In many DRL algorithms, especially those involving value-based or actor-critic structures, the critic component plays a key role in guiding policy learning by estimating value functions. However, conventional critic models often use shallow architectures that map observations directly to scalar estimates, limiting their ability to handle multi-task complexity. In contrast, recent progress in inference-time scaling of Large Language Models (LLMs) has shown that generating intermediate reasoning steps can significantly improve decision quality. Motivated by this, we propose ReaCritic, a reasoning transformer-based critic-model scaling scheme that brings reasoning-like ability into DRL. ReaCritic performs horizontal reasoning over parallel state-action inputs and vertical reasoning through deep transformer stacks. It is compatible with a broad range of value-based and actor-critic DRL algorithms and enhances generalization in dynamic wireless environments. Extensive experiments demonstrate that ReaCritic improves convergence speed and final performance across various HetNet settings and standard OpenAI Gym control tasks. The code of ReaCritic is available at https://github.com/NICE-HKU/ReaCritic.

cs.LG↗
arXiv2026

StarSD: One-for-Many Speculative Decoding

Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for serving modern Large Language Models (LLMs). We present StarSD, a one-for-many speculative decoding framework that uses a single draft model to serve multiple target models across distributed nodes via a star topology. StarSD decouples drafting and verification, enabling effective sharing of draft computation, and preventing distributed accelerators from remaining idle under bursty workloads. We provide a system-level analysis that characterizes when and why a single draft model can remain fully utilized by multiple verifiers, yielding predictable latency and utilization gains. Extensive experiments in real-world distributed inference settings demonstrate that StarSD simplifies deployment and supports flexible resource allocation across heterogeneous accelerators, while maintaining output quality. These results indicate that StarSD is a practical and scalable framework for bringing speculative decoding to modern cloud and edge inference infrastructures.

eess.SY↗
arXiv2026

Large Language Model (LLM)-enabled Reinforcement Learning for Wireless Network Optimization

Enhancing future wireless networks presents a significant challenge for networking systems due to diverse user demands and the emergence of 6G technology. While reinforcement learning (RL) is a powerful framework, it often encounters difficulties with high-dimensional state spaces and complex environments, leading to substantial computational demands, distributed intelligence, and potentially inconsistent outcomes. Large language models (LLMs), with their extensive pretrained knowledge and advanced reasoning capabilities, offer promising tools to enhance RL in optimizing 6G wireless networks. We explore RL models augmented by LLMs, emphasizing their roles and the potential benefits of their synergy in wireless network optimization. We then examine LLM-enabled RL across various protocol layers: physical, data link, network, transport, and application layers. Additionally, we propose an LLM-assisted state representation and semantic extraction to enhance the multi-agent reinforcement learning (MARL) framework. This approach is applied to service migration and request routing, as well as topology graph generation in unmanned aerial vehicle (UAV)-satellite networks. Through case studies, we demonstrate that our framework effectively performs optimization of wireless network. Finally, we outline prospective research directions for LLM-enabled RL in wireless network optimization.

cs.NI↗
arXiv2026

U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications

Personalized mobile artificial intelligence applications are widely deployed, yet they are expected to infer user behavior from sparse and irregular histories under a continuously evolving spatio-temporal context. This setting induces a fundamental tension among three requirements, i.e., immediacy to adapt to recent behavior, stability to resist transient noise, and generalization to support long-horizon prediction and cold-start users. Most existing approaches satisfy at most two of these requirements, resulting in an inherent impossibility triangle in data-scarce, non-stationary personalization. To address this challenge, we model mobile behavior as a partially observed spatio-temporal tensor and unify short-term adaptation, long-horizon forecasting, and cold-start recommendation as a conditional completion problem, where a user- and task-specific mask specifies which coordinates are treated as evidence. We propose U-MASK, a user-adaptive spatio-temporal masking method that allocates evidence budgets based on user reliability and task sensitivity. To enable mask generation under sparse observations, U-MASK learns a compact, task-agnostic user representation from app and location histories via U-SCOPE, which serves as the sole semantic conditioning signal. A shared diffusion transformer then performs mask-guided generative completion while preserving observed evidence, so personalization and task differentiation are governed entirely by the mask and the user representation. Experiments on real-world mobile datasets demonstrate consistent improvements over state-of-the-art methods across short-term prediction, long-horizon forecasting, and cold-start settings, with the largest gains under severe data sparsity. The code and dataset will be available at https://github.com/NICE-HKU/U-MASK.

cs.LG↗
arXiv2026

Channel Knowledge Map Construction via Guided Flow Matching

The efficient construction of accurate channel knowledge maps (CKMs) is crucial for unleashing the full potential of environment-aware wireless networks, yet it remains a difficult ill-posed problem due to the sparsity of available location-specific channel knowledge data. Although diffusion-based methods such as denoising diffusion probabilistic models (DDPMs) have been exploited for CKM construction, they rely on iterative stochastic sampling, rendering them too slow for real-time wireless applications. To bridge the gap between high fidelity and efficient CKM construction, this letter introduces a novel framework based on linear transport guided flow matching (LT-GFM). Deviating from the noise-removal paradigm of diffusion models, our approach models the CKM generation process as a deterministic ordinary differential equation (ODE) that follows linear optimal transport paths, thereby drastically reducing the number of required inference steps. We propose a unified architecture that is applicable to not only the conventional channel gain map (CGM) construction, but also the more challenging spatial correlation map (SCM) construction. To achieve physics-informed CKM constructions, we integrate environmental semantics (e.g., building masks) for edge recovery and enforce Hermitian symmetry for property of the SCM. Simulation results verify that LT-GFM achieves superior distributional fidelity with significantly lower Fréchet Inception Distance (FID) and accelerates inference speed by a factor of 25 compared to DDPMs.

cs.IT↗