arXiv subjects

Ruonan Zhang

Publications and source records attributed to Ruonan Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Towards Accurate and Fast Clinical Body Composition: A Resource-Efficient Hierarchical Segmentation Framework for Multi-Source CT

Background: Automated 3D segmentation of muscles and adipose tissue from CT is vital for body composition analysis, but multi-source data heterogeneity and high CPU memory demands hinder clinical deployment. Methods: We propose a coarse-to-fine hierarchical framework to segment ten tissue structures. Efficiency is optimized using Dynamic Spacing and Anisotropic Patching, a Group Inference mechanism for low-memory sliding-window processing, and Topology-Aware Asymmetric Resampling for fast post-processing. Results: The framework was trained on 1,558 CT volumes from seven public and two private datasets, and evaluated on an independent test cohort (N=105), per-structure Dice coefficients ranged from 0.924 to 0.982. Eight major structures met the +-10% relative error clinical acceptance limit. On a 12-core CPU workstation, the GPU-free pipeline averaged 44.5 seconds per volume with 4.73 GB peak memory. Conclusion: This framework balances accuracy and efficiency, enabling robust, large-scale body composition analysis on standard CPU workstations.

eess.IV↗

arXiv2026

Time-Slotted Multi-Cluster UAV AirComp with Energy-Awareness: A Pointer Network-Assisted Soft Actor-Critic Learning Framework

Over-the-air computation (AirComp) has emerged as a promising approach for massive data aggregation, which is yet challenged by the channel variations, task distributions, and inherent energy limitation of the computation nodes. In this paper, we propose an unmanned aerial vehicle (UAV)-assisted Aircomp system to serve multi-cluster computation tasks over time, where the UAV mobility-facilitated spatial and time diversity is exploited for efficient and accurate data computation. Specifically, we aim for the minimization of AirComp aggregation error and the energy consumption by jointly optimizing the transceiver beamforming, normalizing factors, sensor scheduling, and UAV trajectory. To solve the formulated problem, we decompose it into two layers where the inner layer addresses the optimization-based AirComp transceiver design, and the outer layer focuses on the deep reinforcement learning (DRL)-based scheduling and trajectory design. In particular, a pointer network actor-critic learning is developed to tackle the binary scheduling problem, and a soft actor-critic DRL algorithm is employed to determine the UAV trajectory. Simulation results validate the convergence of the proposed hierarchical learning framework and demonstrate its significant performance gains in terms of AirComp aggregation error and energy consumption as compared with baseline schemes.

eess.SP↗

arXiv2026

Distributionally Robust Game for Proof-of-Work Blockchain Mining Under Resource Uncertainties

Blockchain plays a crucial role in ensuring the security and integrity of decentralized systems, with the proof-of-work (PoW) mechanism being fundamental for achieving distributed consensus. As PoW blockchains see broader adoption, an increasingly diverse set of miners with varying computing capabilities participate in the network. In this paper, we consider the PoW blockchain mining, where the miners are associated with resource uncertainties. To characterize the uncertainty computing resources at different mining participants, we establish an ambiguous set representing uncertainty of resource distributions. Then, the networked mining is formulated as a non-cooperative game, where distributionally robust performance is calculated for each individual miner to tackle the resource uncertainties. We prove the existence of the equilibrium of the distributionally robust mining game. To derive the equilibrium, we propose the conditional value-at-risk (CVaR)-based reinterpretation of the best response of each miner. We then solve the individual strategy with alternating optimization, which facilitates the iteration among miners towards the game equilibrium. Furthermore, we consider the case that the ambiguity of resource distribution reduces to Gaussian distribution and the case that another uncertainties vanish, and then characterize the properties of the equilibrium therein along with a distributed algorithm to achieve the equilibrium. Simulation results show that the proposed approaches effectively converge to the equilibrium, and effectively tackle the uncertainties in blockchain mining to achieve a robust performance guarantee.

eess.SY↗

arXiv2025

Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling

Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation of this LLM-based paradigm is the discretization of the continuous speech waveform into a sequence of discrete tokens by neural audio codec. However, single codebook modeling is well suited to text LLMs, but suffers from significant information loss; hierarchical acoustic tokens, typically generated via Residual Vector Quantization (RVQ), often lack explicit semantic structure, placing a heavy learning burden on the model. Furthermore, the autoregressive process is inherently susceptible to error accumulation, which can degrade generation stability. To address these limitations, we propose CaT-TTS, a novel framework for robust and semantically-grounded zero-shot synthesis. First, we introduce S3Codec, a split RVQ codec that injects explicit linguistic features into its primary codebook via semantic distillation from a state-of-the-art ASR model, providing a structured representation that simplifies the learning task. Second, we propose an ``Understand-then-Generate'' dual-Transformer architecture that decouples comprehension from rendering. An initial ``Understanding'' Transformer models the cross-modal relationship between text and the audio's semantic tokens to form a high-level utterance plan. A subsequent ``Generation'' Transformer then executes this plan, autoregressively synthesizing hierarchical acoustic tokens. Finally, to enhance generation stability, we introduce Masked Audio Parallel Inference (MAPI), a nearly parameter-free inference strategy that dynamically guides the decoding process to mitigate local errors.

cs.SD↗

arXiv2025

MBCodec:Thorough disentangle for high-fidelity audio compression

High-fidelity neural audio codecs in Text-to-speech (TTS) aim to compress speech signals into discrete representations for faithful reconstruction. However, prior approaches faced challenges in effectively disentangling acoustic and semantic information within tokens, leading to a lack of fine-grained details in synthesized speech. In this study, we propose MBCodec, a novel multi-codebook audio codec based on Residual Vector Quantization (RVQ) that learns a hierarchically structured representation. MBCodec leverages self-supervised semantic tokenization and audio subband features from the raw signals to construct a functionally-disentangled latent space. In order to encourage comprehensive learning across various layers of the codec embedding space, we introduce adaptive dropout depths to differentially train codebooks across layers, and employ a multi-channel pseudo-quadrature mirror filter (PQMF) during training. By thoroughly decoupling semantic and acoustic features, our method not only achieves near-lossless speech reconstruction but also enables a remarkable 170x compression of 24 kHz audio, resulting in a low bit rate of just 2.2 kbps. Experimental evaluations confirm its consistent and substantial outperformance of baselines across all evaluations.

cs.SD↗

arXiv2025

Bridging the gap between training and inference in LM-based TTS models

Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training, TTS models use ground-truth (GT) tokens as prefixes to predict the next token, while in inference these tokens are not available, a gap between training and inference that is often neglected. In this study, we propose a prompt-guided hybrid training scheme to mitigate exposure bias in popular LM-based TTS systems. Our core idea is to adopt a hybrid training paradigm that combines teacher forcing with free running, thereby introducing self-generated tokens into the training process. This makes the training mode more consistent with inference, reducing the training-inference gap. In addition, we incorporate an EOS prediction mechanism during training to detect incorrect sequence termination and adaptively control the free running process. Experimental results provide a comprehensive evaluation of the impact of exposure bias on LM-based TTS, and demonstrate that our method effectively narrows the training-inference gap, thereby improving the quality of synthesized long-form speech.

cs.SD↗

arXiv2025

Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations

Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with post-hoc refinement techniques such as flow matching, these methods fail to recover fine-grained details (e.g., prosodic nuances, speaker-specific timbres), especially in challenging scenarios like singing voice or music synthesis. We propose QTTS, a novel TTS framework built upon our new audio codec, QDAC. The core innovation of QDAC lies in its end-to-end training of an ASR-based auto-regressive network with a GAN, which achieves superior semantic feature disentanglement for scalable, near-lossless compression. QTTS models these discrete codes using two innovative strategies: the Hierarchical Parallel architecture, which uses a dual-AR structure to model inter-codebook dependencies for higher-quality synthesis, and the Delay Multihead approach, which employs parallelized prediction with a fixed delay to accelerate inference speed. Our experiments demonstrate that the proposed framework achieves higher synthesis quality and better preserves expressive content compared to baseline. This suggests that scaling up compression via multi-codebook modeling is a promising direction for high-fidelity, general-purpose speech and audio generation.

cs.SD↗

arXiv2025

UAV-Assisted Integrated Communication and Over-the-Air Computation with Interference Awareness

Over the air computation (AirComp) is a promising technique that addresses big data collection and fast wireless data aggregation. However, in a network where wireless communication and AirComp coexist, mutual interference becomes a critical challenge. In this paper, we propose to employ an unmanned aerial vehicle (UAV) to enable integrated communication and AirComp, where we capitalize on UAV mobility with alleviated interference for performance enhancement. Particularly, we aim to maximize the sum of user transmission rate with the guaranteed AirComp accuracy requirement, where we jointly optimize the transmission strategy, signal normalizing factor, scheduling strategy, and UAV trajectory. We decouple the formulated problem into two layers where the outer layer is for UAV trajectory and scheduling, and the inner layer is for transmission and computation. Then, we solve the inner layer problem through alternating optimization, and the outer layer is solved through soft actor critic based deep reinforcement learning. Simulation results show the convergence of the proposed learning process and also demonstrate the performance superiority of our proposal as compared with the baselines in various situations.

eess.SP↗

arXiv2025

Energy-Efficient Integrated Communication and Computation via Non-Terrestrial Networks with Uncertainty Awareness

Non-terrestrial network (NTN)-based integrated communication and computation empowers various emerging applications with global coverage. Yet this vision is severely challenged by the energy issue given the limited energy supply of NTN nodes and the energy-consuming nature of communication and computation. In this paper, we investigate the energy-efficient integrated communication and computation for the ground node data through a NTN, incorporating an unmanned aerial vehicle (UAV) and a satellite. We jointly consider ground data offloading to the UAV, edge processing on the UAV, and the forwarding of results from UAV to satellite, where we particularly address the uncertainties of the UAV-satellite links due to the large distance and high dynamics therein. Accordingly, we propose to minimize the weighted energy consumption due to data offloading, UAV computation, UAV transmission, and UAV propulsion, in the presence of angular uncertainties under Gaussian distribution within the UAV-satellite channels. The formulated problem with probabilistic constraints due to uncertainties is converted into a deterministic form by exploiting the Bernstein-type inequality, which is then solved using a block coordinate descent framework with algorithm design. Simulation results are provided to demonstrate the performance superiority of our proposal in terms of energy sustainability, along with the robustness against uncertain non-terrestrial environments.

eess.SP↗

arXiv2025

FLAP: Fully-controllable Audio-driven Portrait Video Generation through 3D head conditioned diffusion model

Diffusion-based video generation techniques have significantly improved zero-shot talking-head avatar generation, enhancing the naturalness of both head motion and facial expressions. However, existing methods suffer from poor controllability, making them less applicable to real-world scenarios such as filmmaking and live streaming for e-commerce. To address this limitation, we propose FLAP, a novel approach that integrates explicit 3D intermediate parameters (head poses and facial expressions) into the diffusion model for end-to-end generation of realistic portrait videos. The proposed architecture allows the model to generate vivid portrait videos from audio while simultaneously incorporating additional control signals, such as head rotation angles and eye-blinking frequency. Furthermore, the decoupling of head pose and facial expression allows for independent control of each, offering precise manipulation of both the avatar's pose and facial expressions. We also demonstrate its flexibility in integrating with existing 3D head generation methods, bridging the gap between 3D model-based approaches and end-to-end diffusion techniques. Extensive experiments show that our method outperforms recent audio-driven portrait video models in both naturalness and controllability.

cs.GR↗

arXiv2023

Robust Trajectory and Offloading for Energy-Efficient UAV Edge Computing in Industrial Internet of Things

Efficient data processing and computation are essential for the industrial Internet of things (IIoT) to empower various applications, which yet can be significantly bottlenecked by the limited energy capacity and computation capability of the IIoT nodes. In this paper, we employ an unmanned aerial vehicle (UAV) as an edge server to assist IIoT data processing, while considering the practical issue of UAV jittering. Specifically, we propose a joint design on trajectory and offloading strategies to minimize energy consumption due to local and edge computation, as well as data transmission. We particularly address the UAV jittering that induces Gaussian-distributed uncertainties associated with flying waypoints, resulting in probabilistic-form flying speed and data offloading constraints. We exploit the Bernstein-type inequality to reformulate the constraints in deterministic forms and decompose the energy minimization to solve for trajectory and offloading separately within an alternating optimization framework. The subproblems are then tackled with the successive convex approximation technique. Simulation results show that our proposal strictly guarantees robustness under uncertainties and effectively reduces energy consumption as compared with the baselines.

eess.SP↗

arXiv2023

Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue. We show two drawbacks of the raw triplet loss in MDE and demonstrate our problem-driven redesigns. First, we present a min. operator based strategy applied to all negative samples, to prevent well-performing negatives sheltering the error of edge-fattening negatives. Second, we split the anchor-positive distance and anchor-negative distance from within the original triplet, which directly optimizes the positives without any mutual effect with the negatives. Extensive experiments show the combination of these two small redesigns can achieve unprecedented results: Our powerful and versatile triplet loss not only makes our model outperform all previous SoTA by a large margin, but also provides substantial performance boosts to a large number of existing models, while introducing no extra inference computation at all.

cs.CV↗

arXiv2022

Frequency-Aware Self-Supervised Monocular Depth Estimation

We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models. The high generalizability of our methods is achieved by solving the fundamental and ubiquitous problems in photometric loss function. In particular, from the perspective of spatial frequency, we first propose Ambiguity-Masking to suppress the incorrect supervision under photometric loss at specific object boundaries, the cause of which could be traced to pixel-level ambiguity. Second, we present a novel frequency-adaptive Gaussian low-pass filter, designed to robustify the photometric loss in high-frequency regions. We are the first to propose blurring images to improve depth estimators with an interpretable analysis. Both modules are lightweight, adding no parameters and no need to manually change the network structures. Experiments show that our methods provide performance boosts to a large number of existing models, including those who claimed state-of-the-art, while introducing no extra inference computation at all.

cs.CV↗

arXiv2021

A Personalized Diagnostic Generation Framework Based on Multi-source Heterogeneous Data

Personalized diagnoses have not been possible due to sear amount of data pathologists have to bear during the day-to-day routine. This lead to the current generalized standards that are being continuously updated as new findings are reported. It is noticeable that these effective standards are developed based on a multi-source heterogeneous data, including whole-slide images and pathology and clinical reports. In this study, we propose a framework that combines pathological images and medical reports to generate a personalized diagnosis result for individual patient. We use nuclei-level image feature similarity and content-based deep learning method to search for a personalized group of population with similar pathological characteristics, extract structured prognostic information from descriptive pathology reports of the similar patient population, and assign importance of different prognostic factors to generate a personalized pathological diagnosis result. We use multi-source heterogeneous data from TCGA (The Cancer Genome Atlas) database. The result demonstrate that our framework matches the performance of pathologists in the diagnosis of renal cell carcinoma. This framework is designed to be generic, thus could be applied for other types of cancer. The weights could provide insights to the known prognostic factors and further guide more precise clinical treatment protocols.

cs.CV↗

arXiv2020

Performance Analysis for the CMSA/CA Protocol in UAV-based IoT network

UAV-based base station (UBS) has played an important role in the air-ground integration network due to its high flexibility and nice air-ground wireless channels. Especially in Internet of Things (IoT) services, UBS can provide an efficient way for data collection from the IoT devices. However, due to the continuous mobility of UBS, the communication durations of devices in different locations with the UBS are not only time-limited, but also vary from each other. Therefore, it is a challenging task to analyze the throughput performance of the UAV-based IoT network. Accordingly, in this paper, we consider an air-ground network in which UAV flies straightly to collect information from the IoT devices based on CSMA/CA protocol. An analytical model analyzing the performance of this protocol in the network is proposed. In detail, we set up the system model for the network, and propose a new concept called quitting probability. Then, a modified Markov chain model integrating the quitting probability is introduced to describe the transmission state transition process and an accurately theoretical analysis of saturation throughput is given. In addition, the effects of the network parameters are discussed in the simulation section.

cs.IT↗

arXiv2020

Joint Placement Optimization and RNC in UAV-based Wireless Multicast Networks

Random network coding (RNC) is an efficient coding scheme to improve the performance of the broadband networks, especially for multimedia applications which are popular in 5G network. However, it is a challenging work to transmit the real time media data because of the time limitation and wide band requirement. Moreover, the topology of the network changes due to users' movement, causing huge channel heterogeneity in large wireless network area. In this case, the fixed macro base station (BS) or access point may not fit the real-time user distributions. Accordingly, the UAV-based BS with high mobility can provide flexible service by adjusting it position according to users' locations to fit the dynamic topology of the network. Therefore, in this paper, we propose a UAV-based adaptive RNC (UARNC) scheme that jointly optimizes the UAV's location and RNC packet scheduling to maximize the throughput in a multicast network while guaranteeing the service quality of the bottleneck users. This problem is formulated as an optimization problem, and the greedy scheduling techniques and particle swarm optimization (PSO) algorithm are adopted to solve it. Finally, the simulation results prove the effectiveness of the proposed scheme.

cs.IT↗

arXiv2020

Performance Analysis and Optimization for the MAC Protocol in UAV-based IoT Network

Unmanned aerial vehicles (UAVs) have played an important role in air-ground integration network. Especially in Internet of Things (IoT) services, UAV equipped with communication equipments is widely adopted as a mobile base station (BS) for data collection from IoT devices on the ground. In this paper, we consider an air-ground network in which the UAV flies straightly to collect information from the IoT devices in a 2-D plane based on the CSMA/CA protocol. Due to UAV's continuous mobility, the communication durations of devices in different locations with UAV are not only time-limited, but also vary from each other. To analyze the throughput performance of uplink multiple access control (MAC) protocol, we propose a new analysis model to deal with the communications heterogeneity in the network. Firstly, we divide the devices in the coverage into different clusters according to their communication durations. Then, a quitting probability indicating the probability that a device quits the UAV's coverage at each time slot is clarified. A modified three-dimensional Markov chain model adopting the quitting probability and cluster division is developed for the performance analysis. Besides, we also propose a modified CSMA/CA protocol which fully considers the heterogeneity of the access time and adaptively allocates the time resource among the devices in different clusters. Finally, the effects of retry limit, initial contention window size, the density of the devices, UAVs speed and coverage area are discussed in the simulation section.

cs.IT↗

arXiv2019

StructureFlow: Image Inpainting via Structure-aware Appearance Flow

Image inpainting techniques have shown significant improvements by using deep neural networks recently. However, most of them may either fail to reconstruct reasonable structures or restore fine-grained textures. In order to solve this problem, in this paper, we propose a two-stage model which splits the inpainting task into two parts: structure reconstruction and texture generation. In the first stage, edge-preserved smooth images are employed to train a structure reconstructor which completes the missing structures of the inputs. In the second stage, based on the reconstructed structures, a texture generator using appearance flow is designed to yield image details. Experiments on multiple publicly available datasets show the superior performance of the proposed network.

cs.CV↗