arXiv subjects

Wen Wu

Publications and source records attributed to Wen Wu.

At least 73 records · Page 4Linked to original sources

arXiv2025

UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

Audio generation, including speech, music and sound effects, has advanced rapidly in recent years. These tasks can be divided into two categories: time-aligned (TA) tasks, where each input unit corresponds to a specific segment of the output audio (e.g., phonemes aligned with frames in speech synthesis); and non-time-aligned (NTA) tasks, where such alignment is not available. Since modeling paradigms for the two types are typically different, research on different audio generation tasks has traditionally followed separate trajectories. However, audio is not inherently divided into such categories, making a unified model a natural and necessary goal for general audio generation. Previous unified audio generation works have adopted autoregressive architectures, while unified non-autoregressive approaches remain largely unexplored. In this work, we propose UniFlow-Audio, a universal audio generation framework based on flow matching. We propose a dual-fusion mechanism that temporally aligns audio latents with TA features and integrates NTA features via cross-attention in each model block. Task-balanced data sampling is employed to maintain strong performance across both TA and NTA tasks. UniFlow-Audio supports omni-modalities, including text, audio, and video. By leveraging the advantage of multi-task learning and the generative modeling capabilities of flow matching, UniFlow-Audio achieves strong results across 7 tasks using fewer than 8K hours of public training data and under 1B trainable parameters. Even the small variant with only ~200M trainable parameters shows competitive performance, highlighting UniFlow-Audio as a potential non-auto-regressive foundation model for audio generation. Code and models will be available at https://wsntxxn.github.io/uniflow_audio.

cs.SD↗

arXiv2025

WiLLM: an Open Framework for LLM Services over Wireless Systems

Large Language Model (LLM) services fundamentally differ from traditional Deep Neural Network (DNN) applications in wireless networks. We identify three critical distinctions: (1) unlike traditional DNNs with unidirectional data flows, LLM's multimodal interactions create bidirectional heavy loads with contrasting bottlenecks, requiring direction-aware resource scheduling; (2) while traditional DNNs exhibit fixed computational patterns, LLM's highly variable inference times interact complexly with network slicing, causing dynamic bottleneck migration; and (3) in contrast to predictable DNN traffic, LLM's token streams demonstrate unprecedented burstiness and state dependencies. These insights motivate WiLLM, the first open-source framework, implemented as a wireless platform, for LLM service research. Built on OpenAirInterface, WiLLM introduces several technical innovations: dynamic slice compatibility, universal UE compatibility through application-layer tunneling, multi-UE multi-slice scheduling, dual-mode resource allocation, and cross-layer APIs. In addition, WiLLM eliminates the need for specialized wireless expertise, enabling researchers and developers to experiment with LLM services over realistic cellular networks. We demonstrate the platform's capabilities through a smart glasses case study and provide a comprehensive dataset of \~1.6 million synchronized measurements. The complete system, dataset, and appendix are available at https://openwillm.github.io.

cs.NI↗

arXiv2025

Efficient Channel Estimation for Rotatable Antenna-Enabled Wireless Communication

Non-fixed flexible antenna architectures, such as fluid antenna system (FAS), movable antenna (MA), and pinching antenna, have garnered significant interest in recent years. Among them, rotatable antenna (RA) is a promising antenna architecture that exploits additional spatial degrees of freedom (DoFs) to enhance the communication performance. To fully obtain the performance gain provided by RAs, accurate channel state information (CSI) is essential for adjusting the orientation/boresight of each antenna. In this letter, we propose an efficient channel estimation scheme for RA communication systems, where the base station (BS) can sequentially and adaptively adjust the orientations of RAs to enrich the environmental observations from diverse angular perspectives, thereby enhancing the channel estimation accuracy. The proposed scheme includes two main procedures that are conducted alternately during each channel training period. Specifically, the first procedure is to estimate the CSI with given RAs' orientations, involving the angle-of-arrivals (AoAs) information and path gains. Then, based on the estimated CSI, the second procedure adjusts the RAs' orientations to maximize the effective channel gain. Simulation results demonstrate that the proposed channel estimation method outperforms other benchmark schemes.

cs.IT↗

arXiv2025

LLM-Empowered IoT for 6G Networks: Architecture, Challenges, and Solutions

The Internet of Things (IoT) in the sixth generation (6G) era is envisioned to evolve towards intelligence, ubiquity, and self-optimization. Large language models (LLMs) have demonstrated remarkable generalization capabilities across diverse domains, including natural language processing (NLP), computer vision (CV), and beyond. In this article, we propose an LLM-empowered IoT architecture for 6G networks to achieve intelligent autonomy while supporting advanced IoT applications. LLMs are pushed to the edge of the 6G network to support the synergy of LLMs and IoT. LLM solutions are tailored to both IoT application requirements and IoT management needs, i.e., LLM for IoT. On the other hand, edge inference and edge fine-tuning are discussed to support the deployment of LLMs, i.e., LLM on IoT. Furthermore, we propose a memory-efficient split federated learning (SFL) framework for LLM fine-tuning on heterogeneous IoT devices that alleviates memory pressures on both IoT devices and the edge server while achieving comparable performance and convergence time. Finally, a case study is presented, followed by a discussion about open issues of LLM-empowered IoT for 6G networks.

cs.ET↗

arXiv2025

Intelligent Rotatable Antenna for Integrated Sensing, Communication, and Computation: Challenges and Opportunities

Integrated sensing, communication, and computation (ISCC) has emerged as a promising paradigm for enabling intelligent services in future sixth-generation (6G) networks. However, existing ISCC systems based on fixed-antenna architectures inherently lack spatial adaptability to cope with the signal degradation and dynamic environmental conditions. Recently, non-fixed flexible antenna architectures, such as fluid antenna system (FAS), movable antenna (MA), and pinching antenna, have garnered significant interest. Among them, intelligent rotatable antenna (IRA) is an emerging technology that offers significant potential to better support the comprehensive services of target sensing, data transmission, and edge computing. This article investigates a novel IRA-enabled ISCC framework to enhance received signal strength, wider coverage, and spatial adaptability to dynamic wireless environments by flexibly adjusting the boresight of directional antennas. Building upon this, we introduce the fundamentals of IRA technology and explore IRA's benefits for improving system performance while providing potential task-oriented applications. Then, we discuss the main design issues and provide solutions for implementing IRA-based ISCC systems. Finally, experimental results are provided to demonstrate the great potential of IRA-enabled ISCC system, thus paving the way for more robust and efficient future wireless networks.

cs.IT↗

arXiv2025

Memory-Efficient Split Federated Learning for LLM Fine-Tuning on Heterogeneous Mobile Devices

In this paper, we propose an edge-assisted split federated learning framework to facilitate large language model (LLM) fine-tuning on heterogeneous mobile devices while alleviating memory pressures on both mobile devices and the edge server. Specifically, mobile devices perform low-rank adaptation (LoRA) fine-tuning on only a subset of lower layers of the pre-trained LLM, tailored to their individual capacities. On the server, a full LLM is maintained, and the corresponding LoRA modules are selectively fine-tuned in a sequential manner for each device. To further enhance training efficiency, we propose a server-side training scheduling method that optimizes the processing order of devices for accelerating fine-tuning. Extensive experiments demonstrate that compared to the baselines, our scheme can reduce 79\% memory footprint and 6\% training time while achieving comparable performance.

cs.DC↗

arXiv2025

Attached Decelerating Turbulent Boundary Layers over Riblets

Turbulent boundary layers over riblets subjected to adverse pressure gradients (APGs) are investigated by direct numerical simulation. Multiple APG strengths and riblet sizes are examined, permitting evaluation of drag modification by riblets, and associated physical mechanisms, in various regimes established for zero-pressure-gradient (ZPG) riblet flows. The APG strengths are selected such that the flow remains attached. It is found that during APGs, riblets reduce drag beyond what has been achieved in ZPG flows. In extreme cases, an upstream force (i.e., negative drag) is attained. The significant drag reduction is found to be a product of Kelvin-Helmholtz roller vortices forming near the riblet crest, which are augmented in size, strength, and frequency during the APG. The preliminary results reported here indicate the need to modify existing metrics to predict drag reduction and the onset of KH rollers by riblets when the pressure gradient is non-negligible. Further analysis will be documented in the final paper.

physics.flu-dyn↗

arXiv2025

Laminar boundary layer separation over a fully porous bump

This study investigates laminar boundary layer separation over a fully porous Gaussian bump using pore-resolved direct numerical simulations. The bump is formed by randomly packed spheres. Compared to a solid bump, the porous surface significantly alters the flow by enabling cross-bump mass flux. Near-wall fluid is drawn into the bump by favorable pressure gradients on the windward side and exits near the crest and leeward side due to adverse pressure gradients. This pore flow weakens the reverse flow and reduces mean shear in the separated region, delaying reattachment and extending the separation zone. The findings highlight the role of porous structures in modulating boundary layer separation.

physics.flu-dyn↗

arXiv2025

The 1st SpeechWellness Challenge: Detecting Suicide Risk Among Adolescents

The 1st SpeechWellness Challenge (SW1) aims to advance methods for detecting current suicide risk in adolescents using speech analysis techniques. Suicide among adolescents is a critical public health issue globally. Early detection of suicidal tendencies can lead to timely intervention and potentially save lives. Traditional methods of assessment often rely on self-reporting or clinical interviews, which may not always be accessible. The SW1 challenge addresses this gap by exploring speech as a non-invasive and readily available indicator of mental health. We release the SW1 dataset which contains speech recordings from 600 adolescents aged 10-18 years. By focusing on speech generated from natural tasks, the challenge seeks to uncover patterns and markers that correlate with current suicide risk.

eess.AS↗

arXiv2025

Task-Core Memory Management and Consolidation for Long-term Continual Learning

In this paper, we focus on a long-term continual learning (CL) task, where a model learns sequentially from a stream of vast tasks over time, acquiring new knowledge while retaining previously learned information in a manner akin to human learning. Unlike traditional CL settings, long-term CL involves handling a significantly larger number of tasks, which exacerbates the issue of catastrophic forgetting. Our work seeks to address two critical questions: 1) How do existing CL methods perform in the context of long-term CL? and 2) How can we mitigate the catastrophic forgetting that arises from prolonged sequential updates? To tackle these challenges, we propose a novel framework inspired by human memory mechanisms for long-term continual learning (Long-CL). Specifically, we introduce a task-core memory management strategy to efficiently index crucial memories and adaptively update them as learning progresses. Additionally, we develop a long-term memory consolidation mechanism that selectively retains hard and discriminative samples, ensuring robust knowledge retention. To facilitate research in this area, we construct and release two multi-modal and textual benchmarks, MMLongCL-Bench and TextLongCL-Bench, providing a valuable resource for evaluating long-term CL approaches. Experimental results show that Long-CL outperforms the previous state-of-the-art by 7.4\% and 6.5\% AP on the two benchmarks, respectively, demonstrating the effectiveness of our approach.

cs.LG↗

arXiv2025

Meta-Learning Driven Lightweight Phase Shift Compression for IRS-Assisted Wireless Systems

The phase shift information (PSI) overhead poses a critical challenge to enabling real-time intelligent reflecting surface (IRS)-assisted wireless systems, particularly under dynamic and resource-constrained conditions. In this paper, we propose a lightweight PSI compression framework, termed meta-learning-driven compression and reconstruction network (MCRNet). By leveraging a few-shot adaptation strategy via model-agnostic meta-learning (MAML), MCRNet enables rapid generalization across diverse IRS configurations with minimal retraining overhead. Furthermore, a novel depthwise convolutional gating (DWCG) module is incorporated into the decoder to achieve adaptive local feature modulation with low computational cost, significantly improving decoding efficiency. Extensive simulations demonstrate that MCRNet achieves competitive normalized mean square error performance compared to state-of-the-art baselines across various compression ratios, while substantially reducing model size and inference latency. These results validate the effectiveness of the proposed asymmetric architecture and highlight the practical scalability and real-time applicability of MCRNet for dynamic IRS-assisted wireless deployments.

eess.SP↗

arXiv2025

Adaptive Split Learning over Energy-Constrained Wireless Edge Networks

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the device heterogeneity and variation of channel conditions, this way is not optimal in training delay and energy consumption. In this paper, we design an adaptive split learning (ASL) scheme which can dynamically select split points for devices and allocate computing resource for the server in wireless edge networks. We formulate an optimization problem to minimize the average training latency subject to long-term energy consumption constraint. The difficulties in solving this problem are the lack of future information and mixed integer programming (MIP). To solve it, we propose an online algorithm leveraging the Lyapunov theory, named OPEN, which decomposes it into a new MIP problem only with the current information. Then, a two-layer optimization method is proposed to solve the MIP problem. Extensive simulation results demonstrate that the ASL scheme can reduce the average training delay and energy consumption by 53.7% and 22.1%, respectively, as compared to the existing SL schemes.

cs.LG↗

arXiv2025

Bayesian WeakS-to-Strong from Text Classification to Generation

Advances in large language models raise the question of how alignment techniques will adapt as models become increasingly complex and humans will only be able to supervise them weakly. Weak-to-Strong mimics such a scenario where weak model supervision attempts to harness the full capabilities of a much stronger model. This work extends Weak-to-Strong to WeakS-to-Strong by exploring an ensemble of weak models which simulate the variability in human opinions. Confidence scores are estimated using a Bayesian approach to guide the WeakS-to-Strong generalization. Furthermore, we extend the application of WeakS-to-Strong from text classification tasks to text generation tasks where more advanced strategies are investigated for supervision. Moreover, direct preference optimization is applied to advance the student model's preference learning, beyond the basic learning framework of teacher forcing. Results demonstrate the effectiveness of the proposed approach for the reliability of a strong student model, showing potential for superalignment.

cs.CL↗

arXiv2025

RingAda: Pipelining Large Model Fine-Tuning on Edge Devices with Scheduled Layer Unfreezing

To enable large model (LM) based edge intelligent service provisioning, on-device fine-tuning with locally personalized data allows for continuous and privacy-preserving LM customization. In this paper, we propose RingAda, a collaborative training framework designed for fine-tuning transformer-based LMs on edge devices. Particularly, RingAda performs parameter-efficient adapter fine-tuning across a set of interconnected edge devices, forming a ring topology for per-batch training by sequentially placing frozen transformer blocks and their trainable adapter modules on the devices. RingAda follows a novel pipeline-parallel training mechanism with top-down adapter unfreezing, allowing for early-stopping of backpropagation at the lowest unfrozen adapter layer, thereby accelerating the fine-tuning process. Extensive experimental results demonstrate that RingAda significantly reduces fine-tuning time and memory costs while maintaining competitive model performance compared to its peer designs.

cs.DC↗

arXiv2025

MobiLLM: Enabling LLM Fine-Tuning on the Mobile Device via Server Assisted Side Tuning

Large Language Model (LLM) at mobile devices and its potential applications never fail to fascinate. However, on-device LLM fine-tuning poses great challenges due to extremely high memory requirements and slow training speeds. Even with parameter-efficient fine-tuning (PEFT) methods that update only a small subset of parameters, resource-constrained mobile devices cannot afford them. In this paper, we propose MobiLLM to enable memory-efficient transformer LLM fine-tuning on a mobile device via server-assisted side-tuning. Particularly, MobiLLM allows the resource-constrained mobile device to retain merely a frozen backbone model, while offloading the memory and computation-intensive backpropagation of a trainable side-network to a high-performance server. Unlike existing fine-tuning methods that keep trainable parameters inside the frozen backbone, MobiLLM separates a set of parallel adapters from the backbone to create a backpropagation bypass, involving only one-way activation transfers from the mobile device to the server with low-width quantization during forward propagation. In this way, the data never leaves the mobile device while the device can remove backpropagation through the local backbone model and its forward propagation can be paralyzed with the server-side execution. Thus, MobiLLM preserves data privacy while significantly reducing the memory and computational burdens for LLM fine-tuning. Through extensive experiments, we demonstrate that MobiLLM can enable a resource-constrained mobile device, even a CPU-only one, to fine-tune LLMs and significantly reduce convergence time and memory usage.

cs.LG↗

arXiv2025

Terahertz Integrated Sensing and Communication-Empowered UAVs in 6G: A Transceiver Design Perspective

Due to their high maneuverability, flexible deployment, and low cost, unmanned aerial vehicles (UAVs) are expected to play a pivotal role in not only communication, but also sensing. Especially by exploiting the ultra-wide bandwidth of terahertz (THz) bands, integrated sensing and communication (ISAC)-empowered UAV has been a promising technology of 6G space-air-ground integrated networks. In this article, we systematically investigate the key techniques and essential obstacles for THz-ISAC-empowered UAV from a transceiver design perspective, with the highlight of its major challenges and key technologies. Specifically, we discuss the THz-ISAC-UAV wireless propagation environment, based on which several channel characteristics for communication and sensing are revealed. We point out the transceiver payload design peculiarities for THz-ISAC-UAV from the perspective of antenna design, radio frequency front-end, and baseband signal processing. To deal with the specificities faced by the payload, we shed light on three key technologies, i.e., hybrid beamforming for ultra-massive MIMO-ISAC, power-efficient THz-ISAC waveform design, as well as communication and sensing channel state information acquisition, and extensively elaborate their concepts and key issues. More importantly, future research directions and associated open problems are presented, which may unleash the full potential of THz-ISAC-UAV for 6G wireless networks.

eess.SP↗

arXiv2025

SplitLLM: Hierarchical Split Learning for Large Language Model over Wireless Network

Fine-tuning a large language model (LLM) using the local data of edge users can enable personalized services and applications. For privacy protection, the prevalent solution adopts distributed learning for fine-tuning and integrates low-rank adaptation (LoRA) to reduce users' computational load. However, as the number of users increases, numerous users simultaneously communicate with the server, and multiple server-side models concurrently execute on the server, leading to significant communication congestion and memory pressure. In this paper, we propose a split learning (SL) scheme for fine-tuning LLM in wireless networks, which involves one cloud server, a small number of edge servers, and multiple users. Specifically, the pre-trained model and LoRA adapters are divided into three parts and deployed across the cloud, edge, and user sides. The training process follows the sequence of user, edge, and cloud, with forward and backward propagation achieved by transmitting activation and gradient. In each round, all edge servers and an equivalent number of users train in parallel, and only the LoRA adapters are updated. At the end of each round, all edge-side and user-side LoRA adapters are uploaded to the cloud for aggregation. Extensive simulation demonstrates that the proposed scheme can reduce peak memory usage up to 74% compared to the state-of-the-art benchmarks.

cs.DC↗

arXiv2025

Disentangled Modeling of Preferences and Social Influence for Group Recommendation

The group recommendation (GR) aims to suggest items for a group of users in social networks. Existing work typically considers individual preferences as the sole factor in aggregating group preferences. Actually, social influence is also an important factor in modeling users' contributions to the final group decision. However, existing methods either neglect the social influence of individual members or bundle preferences and social influence together as a unified representation. As a result, these models emphasize the preferences of the majority within the group rather than the actual interaction items, which we refer to as the preference bias issue in GR. Moreover, the self-supervised learning (SSL) strategies they designed to address the issue of group data sparsity fail to account for users' contextual social weights when regulating group representations, leading to suboptimal results. To tackle these issues, we propose a novel model based on Disentangled Modeling of Preferences and Social Influence for Group Recommendation (DisRec). Concretely, we first design a user-level disentangling network to disentangle the preferences and social influence of group members with separate embedding propagation schemes based on (hyper)graph convolution networks. We then introduce a socialbased contrastive learning strategy, selectively excluding user nodes based on their social importance to enhance group representations and alleviate the group-level data sparsity issue. The experimental results demonstrate that our model significantly outperforms state-of-the-art methods on two realworld datasets.

cs.IR↗