arXiv subjects

Weixuan Chen

Publications and source records attributed to Weixuan Chen.

18 recordsLinked to original sources

arXiv2026

Evolving Token Communication with Parametric Memory Network

Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. However, transmitting full semantic tokens still incurs considerable communication overhead. In this paper, we propose an evolving semantic token communication system with a parametric memory network over MIMO fading channels. Specifically, only an equal-length prefix of each semantic token is transmitted, which reduces transmission cost while preserving a consistent token structure for receiver-side recovery. At the receiver, a parametric memory network is introduced to reconstruct the missing suffix information from the received token prefixes, where semantic memory is stored implicitly in the network parameters. To realize this design, full semantic tokens are first organized into a codebook, and truncated tokens are paired with the codeword labels of their corresponding full tokens. Based on these token-label pairs, kNN-based teacher distributions are constructed to fine-tune a pretrained GPT-2-based recovery module, which learns to infer the codeword distribution of each incomplete token and recover the corresponding complete semantic token. In addition, an online evolution strategy is developed to periodically update the parametric memory network and the entire system using newly observed test samples, thereby improving adaptability under distribution shifts. Experimental results demonstrate that the proposed method consistently outperforms the existing evolving memory benchmark under different channel conditions and channel bandwidth ratios, with up to 1.09 dB PSNR improvement.

cs.IT↗

arXiv2026

OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder

Recent advances in omni-modal large language models have enabled remarkable progress in joint vision-audio understanding. However, prevailing architectures rely on modality-specific encoders with a \emph{video-coarse, audio-dense} design -- sampling visual frames at 1--2 fps while processing audio waveforms at 25 fps -- resulting in systems that perceive video \emph{frame by frame, modality by modality} rather than holistically as humans do. Such a discrepancy leaves models with impoverished cross-modal interaction during encoding and an inability to capture fine-grained visual motion. To bridge this gap, we present \textbf{Omni-Encoder, a unified Transformer backbone designed to co-embed visual and audio signals at a symmetrical 25 fps} within a shared latent space. This architecture leverages three core innovations -- the Omni-Encoder Token Template, Omni-RoPE, and Temporal Window Shifting -- to effectively reconcile the dual challenges of modality disentanglement and computational efficiency. Experiments demonstrate that, compared to the modality-specific baseline Qwen2.5-Omni under the same input token budget to the LLM decoder, Omni-Encoder delivers substantial gains on visual continuous understanding tasks -- such as sign language recognition and fine-grained sports action analysis -- while maintaining competitive performance on established audio-visual benchmarks such as AVQA and Speaker Identification and Localization. These results suggest that unified omnivorous encoding offers a promising direction for building omni-modal models that more closely reflect the integrated nature of human perception.

cs.CV↗

arXiv2025

Secure Digital Semantic Communications: Fundamentals, Challenges, and Opportunities

Semantic communication (SemCom) has emerged as a promising paradigm for future wireless networks by prioritizing task-relevant meaning over raw data delivery, thereby reducing communication overhead and improving efficiency. However, shifting from bit-accurate transmission to task-oriented delivery introduces new security and privacy risks. These include semantic leakage, semantic manipulation, knowledge base vulnerabilities, model-related attacks, and threats to authenticity and availability. Most existing secure SemCom studies focus on analog SemCom, where semantic features are mapped to continuous channel inputs. In contrast, digital SemCom transmits semantic information through discrete bits or symbols within practical transceiver pipelines, offering stronger compatibility with realworld systems while exposing a distinct and underexplored attack surface. In particular, digital SemCom typically represents semantic information over a finite alphabet through explicit digital modulation, following two main routes: probabilistic modulation and deterministic modulation. These discrete mechanisms and practical transmission procedures introduce additional vulnerabilities affecting bit- or symbol-level semantic information, the modulation stage, and packet-based delivery and protocol operations. Motivated by these challenges and the lack of a systematic analysis of secure digital SemCom, this paper provides a structured review of the area. Specifically, we review SemCom fundamentals and clarify the architectural differences between analog and digital SemCom. We then summarize threats shared by both paradigms and organize the threat landscape specific to digital SemCom, followed by a discussion of potential defenses. Finally, we outline open research directions toward secure and deployable digital SemCom systems.

cs.CR↗

arXiv2025

Can Knowledge Improve Security? A Coding-Enhanced Jamming Approach for Semantic Communication

As semantic communication (SemCom) attracts growing attention as a novel communication paradigm, ensuring the security of transmitted semantic information over open wireless channels has become a critical issue. However, traditional encryption methods often introduce significant additional communication overhead to maintain reliability, and conventional learning-based secure SemCom methods typically rely on a channel capacity advantage for the legitimate receiver, which is challenging to guarantee in real-world scenarios. In this paper, we propose a coding-enhanced jamming method that eliminates the need to transmit a secret key by utilizing shared knowledge, which may be part of the training set of the SemCom system, between the legitimate receiver and the transmitter. Specifically, we leverage the shared private knowledge base to generate a set of private digital codebooks in advance using neural network (NN)-based encoders. For each transmission, we encode the transmitted data into a digital sequence Y1 and associate Y1 with a sequence randomly picked from the private codebook, denoted as Y2, through superposition coding. Here, Y1 serves as the outer code and Y2 as the inner code. By optimizing the power allocation between the inner and outer codes, the legitimate receiver can reconstruct the transmitted data using successive decoding based on the shared index of Y2, while the eavesdropper's decoding performance is severely degraded, potentially to the point of random guessing. Experimental results demonstrate that our method achieves security comparable to state-of-the-art approaches while significantly improving the reconstruction performance of the legitimate receiver by more than 1 dB across varying channel signal-to-noise ratios (SNRs) and compression ratios.

cs.IT↗

arXiv2025

A DRL-Empowered Multi-Level Jamming Approach for Secure Semantic Communication

Semantic communication (SemCom) aims to transmit only task-relevant information, thereby improving communication efficiency but also exposing semantic information to potential eavesdropping. In this paper, we propose a deep reinforcement learning (DRL)-empowered multi-level jamming approach to enhance the security of SemCom systems over MIMO fading wiretap channels. This approach combines semantic layer jamming, achieved by encoding task-irrelevant text, and physical layer jamming, achieved by encoding random Gaussian noise. These two-level jamming signals are superposed with task-relevant semantic information to protect the transmitted semantics from eavesdropping. A deep deterministic policy gradient (DDPG) algorithm is further introduced to dynamically design and optimize the precoding matrices for both task-relevant semantic information and multi-level jamming signals, aiming to enhance the legitimate user's image reconstruction while degrading the eavesdropper's performance. To jointly train the SemCom model and the DDPG agent, we propose an alternating optimization strategy where the two modules are updated iteratively. Experimental results demonstrate that, compared with both the encryption-based (ESCS) and encoded jammer-based (EJ) benchmarks, our method achieves comparable security while improving the legitimate user's peak signal-to-noise ratio (PSNR) by up to approximately 0.6 dB.

cs.CR↗

arXiv2025

Privacy-Preserving Semantic Communication over Wiretap Channels with Learnable Differential Privacy

While semantic communication (SemCom) improves transmission efficiency by focusing on task-relevant information, it also raises critical privacy concerns. Many existing secure SemCom approaches rely on restrictive or impractical assumptions, such as favorable channel conditions for the legitimate user or prior knowledge of the eavesdropper's model. To address these limitations, this paper proposes a novel secure SemCom framework for image transmission over wiretap channels, leveraging differential privacy (DP) to provide approximate privacy guarantees. Specifically, our approach first extracts disentangled semantic representations from source images using generative adversarial network (GAN) inversion method, and then selectively perturbs private semantic representations with approximate DP noise. Distinct from conventional DP-based protection methods, we introduce DP noise with learnable pattern, instead of traditional white Gaussian or Laplace noise, achieved through adversarial training of neural networks (NNs). This design mitigates the inherent non-invertibility of DP while effectively protecting private information. Moreover, it enables explicitly controllable security levels by adjusting the privacy budget according to specific security requirements, which is not achieved in most existing secure SemCom approaches. Experimental results demonstrate that, compared with the previous DP-based method and direct transmission, the proposed method significantly degrades the reconstruction quality for the eavesdropper, while introducing only slight degradation in task performance. Under comparable security levels, our approach achieves an LPIPS advantage of 0.06-0.29 and an FPPSR advantage of 0.10-0.86 for the legitimate user compared with the previous DP-based method.

cs.CR↗

arXiv2025

A Superposition Code-Based Semantic Communication Approach with Quantifiable and Controllable Security

This paper addresses the challenge of achieving security in semantic communication (SemCom) over a wiretap channel, where a legitimate receiver coexists with an eavesdropper experiencing a poorer channel condition. Despite previous efforts to secure SemCom against eavesdroppers, guarantee of approximately zero information leakage remains an open issue. In this work, we propose a secure SemCom approach based on superposition code, aiming to provide quantifiable and controllable security for digital SemCom systems. The proposed method employs a double-layered constellation map, where semantic information is associated with satellite constellation points and cloud center constellation points are randomly selected. By carefully allocating power between these two layers of constellation, we ensure that the symbol error probability (SEP) of the eavesdropper when decoding satellite constellation points is nearly equivalent to random guessing, while maintaining a low SEP for the legitimate receiver to successfully decode the semantic information. Simulation results demonstrate that the peak signal-to-noise ratio (PSNR) and mean squared error (MSE) of the eavesdropper's reconstructed data, under the proposed method, can range from decoding Gaussian-distributed random noise to approaching the variance of the data. This validates the effectiveness of our method in nearly achieving the experimental upper bound of security for digital SemCom systems when both eavesdroppers and legitimate users utilize identical decoding schemes. Furthermore, the proposed method consistently outperforms benchmark techniques, showcasing superior data security and robustness against eavesdropping. The implementation code is publicly available at: https://github.com/1weixuanchen/ A-Superposition-Code-Based-Semantic-Communication.

cs.IT↗

arXiv2025

HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context

With the rapid evolution of multimodal large language models, the capacity to deeply understand and interpret human intentions has emerged as a critical capability, which demands detailed and thoughtful reasoning. In recent studies, Reinforcement Learning (RL) has demonstrated potential in enhancing the reasoning capabilities of Large Language Models (LLMs). Nonetheless, the challenges associated with adapting RL to multimodal data and formats remain largely unaddressed. In this paper, we identify two issues in existing multimodal reasoning models: insufficient global context understanding and shortcut problems. Insufficient context understanding can happen when a model misinterprets multimodal context, resulting in incorrect answers. The shortcut problem occurs when the model overlooks crucial clues in multimodal inputs, directly addressing the query without considering the multimodal information. To tackle these issues, we emphasize the necessity for the model to reason with a clear understanding of the global context within multimodal inputs. This global context understanding can effectively prevent the model from overlooking key multimodal cues and ensure a thorough reasoning process. To ensure the accurate interpretation of multimodal context information, we implement a context reward judged by a large language model, alongside format and accuracy rewards. Additionally, to improve complex reasoning capability, we employ the LLM to assess the logical reward, determining whether the reasoning process successfully integrates multimodal information with logical methods. We also introduce a reasoning omni-modal benchmark, IntentBench, aimed at evaluating models in understanding complex human intentions and emotions. Our proposed method demonstrates advanced performance across multiple omni-modal benchmarks compared to other open-source omni-modal models.

cs.CV↗

arXiv2025

Enhancing Privacy in Semantic Communication over Wiretap Channels leveraging Differential Privacy

Semantic communication (SemCom) improves transmission efficiency by focusing on task-relevant information. However, transmitting semantic-rich data over insecure channels introduces privacy risks. This paper proposes a novel SemCom framework that integrates differential privacy (DP) mechanisms to protect sensitive semantic features. This method employs the generative adversarial network (GAN) inversion technique to extract disentangled semantic features and uses neural networks (NNs) to approximate the DP application and removal processes, effectively mitigating the non-invertibility issue of DP. Additionally, an NN-based encryption scheme is introduced to strengthen the security of channel inputs. Simulation results demonstrate that the proposed approach effectively prevents eavesdroppers from reconstructing sensitive information by generating chaotic or fake images, while ensuring high-quality image reconstruction for legitimate users. The system exhibits robust performance across various privacy budgets and channel conditions, achieving an optimal balance between privacy protection and reconstruction fidelity.

cs.CR↗

arXiv2025

Entropy-and-Channel-Aware Adaptive-Rate Semantic Communication with MLLM-Aided Feature Compensation

Despite the transmission efficiency gains of semantic communication (SemCom) over traditional methods, most existing SemCom schemes still operate at a fixed transmission rate regardless of channel conditions and transmitted content, resulting in wasted resources in favorable channels and degraded performance in harsh channels. To address this issue, we propose a novel SemCom framework that incorporates an entropy-and-channel-aware adaptive rate control mechanism over MIMO Rayleigh fading channels. Specifically, we embed a joint representation of the channel state information (CSI) and the signal-to-noise ratio (SNR) into both the semantic encoder and decoder, thereby realizing channel-aware semantic coding and decoding. Moreover, the proposed method jointly exploits the CSI, the SNR, the feature maps, and their 2D entropy via two policy networks to selectively transmit only a subset of feature maps and, within each selected feature map, only a subset of symbols. Thereby, it achieves finer-grained adaptive rate control than existing methods. At the receiver, leveraging the strong visual understanding capability of multimodal large language models (MLLMs), we deploy the lightweight visual encoder (InternViT-300M) of the pre-trained InternVL3.5 model to compensate for discarded feature maps and symbols, and we fine-tune InternViT using low-rank adaptation (LoRA) for parameter-efficient training. Experimental results show that, with a carefully designed channel-aware loss function, our system automatically allocates more communication resources under poor channels to enhance task performance while reducing resource usage under favorable channels and maintaining high task performance.

eess.IV↗

arXiv2024

CASC: Condition-Aware Semantic Communication with Latent Diffusion Models

Diffusion-based semantic communication methods have shown significant advantages in image transmission by harnessing the generative power of diffusion models. However, they still face challenges, including generation randomness that leads to distorted reconstructions and high computational costs. To address these issues, we propose CASC, a condition-aware semantic communication framework that incorporates a latent diffusion model (LDM)-based denoiser. The LDM denoiser at the receiver utilizes the received noisy latent codes as the conditioning signal to reconstruct the latent codes, enabling the decoder to accurately recover the source image. By operating in the latent space, the LDM reduces computational complexity compared to traditional diffusion models (DMs). Additionally, we introduce a condition-aware neural network (CAN) that dynamically adjusts the weights in the hidden layers of the LDM based on the conditioning signal. This enables finer control over the generation process, significantly improving the perceptual quality of the reconstructed images. Experimental results show that CASC significantly outperforms DeepJSCC in both perceptual quality and visual effect. Moreover, CASC reduces inference time by 51.7% compared to existing DM-based semantic communication systems, while maintaining comparable perceptual performance. The ablation studies also validate the effectiveness of the CAN module in improving the image reconstruction quality.

eess.IV↗

arXiv2024

Enhancing Image Privacy in Semantic Communication over Wiretap Channels leveraging Differential Privacy

Semantic communication (SemCom) enhances transmission efficiency by sending only task-relevant information compared to traditional methods. However, transmitting semantic-rich data over insecure or public channels poses security and privacy risks. This paper addresses the privacy problem of transmitting images over wiretap channels and proposes a novel SemCom approach ensuring privacy through a differential privacy (DP)-based image protection and deprotection mechanism. The method utilizes the GAN inversion technique to extract disentangled semantic features and applies a DP mechanism to protect sensitive features within the extracted semantic information. To address the non-invertibility of DP, we introduce two neural networks to approximate the DP application and removal processes, offering a privacy protection level close to that by the original DP process. Simulation results validate the effectiveness of our method in preventing eavesdroppers from obtaining sensitive information while maintaining high-fidelity image reconstruction at the legitimate receiver.

eess.IV↗

arXiv2023

Deep Joint Source-Channel Coding for Wireless Image Transmission with Entropy-Aware Adaptive Rate Control

Adaptive rate control for deep joint source and channel coding (JSCC) is considered as an effective approach to transmit sufficient information in scenarios with limited communication resources. We propose a deep JSCC scheme for wireless image transmission with entropy-aware adaptive rate control, using a single deep neural network to support multiple rates and automatically adjust the rate based on the feature maps of the input image and their entropy, as well as the channel conditions. In particular, we maximize the entropy of the feature maps to increase the average information carried by each transmitted symbol during the training. We further decide which feature maps should be activated based on their entropy, which improves the efficiency of the transmitted symbols. We also propose a pruning module to remove less important pixels in the activated feature maps in order to further improve transmission efficiency. The experimental results demonstrate that our proposed scheme learns an effective rate control strategy that reduces the required channel bandwidth while preserving the quality of the reconstructed images.

eess.IV↗

arXiv2020

Neural Mesh Refiner for 6-DoF Pose Estimation

How can we effectively utilise the 2D monocular image information for recovering the 6D pose (6-DoF) of the visual objects? Deep learning has shown to be effective for robust and real-time monocular pose estimation. Oftentimes, the network learns to regress the 6-DoF pose using a naive loss function. However, due to a lack of geometrical scene understanding from the directly regressed pose estimation, there are misalignments between the rendered mesh from the 3D object and the 2D instance segmentation result, e.g., bounding boxes and masks prediction. This paper bridges the gap between 2D mask generation and 3D location prediction via a differentiable neural mesh renderer. We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation. By leveraging geometry, we demonstrate that our technique significantly improves direct regression performance on the difficult task of translation estimation and achieve the state of the art results on Peking University/Baidu - Autonomous Driving dataset and the ApolloScape 3D Car Instance dataset. The code can be found at \url{https://bit.ly/2IRihfU}.

cs.CV↗

arXiv2018

DeepMag: Source Specific Motion Magnification Using Gradient Ascent

Many important physical phenomena involve subtle signals that are difficult to observe with the unaided eye, yet visualizing them can be very informative. Current motion magnification techniques can reveal these small temporal variations in video, but require precise prior knowledge about the target signal, and cannot deal with interference motions at a similar frequency. We present DeepMag an end-to-end deep neural video-processing framework based on gradient ascent that enables automated magnification of subtle color and motion signals from a specific source, even in the presence of large motions of various velocities. While the approach is generalizable, the advantages of DeepMag are highlighted via the task of video-based physiological visualization. Through systematic quantitative and qualitative evaluation of the approach on videos with different levels of head motion, we compare the magnification of pulse and respiration to existing state-of-the-art methods. Our method produces magnified videos with substantially fewer artifacts and blurring whilst magnifying the physiological changes by a similar degree.

cs.CV↗

arXiv2018

DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks

Non-contact video-based physiological measurement has many applications in health care and human-computer interaction. Practical applications require measurements to be accurate even in the presence of large head rotations. We propose the first end-to-end system for video-based measurement of heart and breathing rate using a deep convolutional network. The system features a new motion representation based on a skin reflection model and a new attention mechanism using appearance information to guide motion estimation, both of which enable robust measurement under heterogeneous lighting and major motions. Our approach significantly outperforms all current state-of-the-art methods on both RGB and infrared video datasets. Furthermore, it allows spatial-temporal distributions of physiological signals to be visualized via the attention mechanism.

cs.CV↗

arXiv2018

Estimating Carotid Pulse and Breathing Rate from Near-infrared Video of the Neck

Objective: Non-contact physiological measurement is a growing research area that allows capturing vital signs such as heart rate (HR) and breathing rate (BR) comfortably and unobtrusively with remote devices. However, most of the approaches work only in bright environments in which subtle photoplethysmographic and ballistocardiographic signals can be easily analyzed and/or require expensive and custom hardware to perform the measurements. Approach: This work introduces a low-cost method to measure subtle motions associated with the carotid pulse and breathing movement from the neck using near-infrared (NIR) video imaging. A skin reflection model of the neck was established to provide a theoretical foundation for the method. In particular, the method relies on template matching for neck detection, Principal Component Analysis for feature extraction, and Hidden Markov Models for data smoothing. Main Results: We compared the estimated HR and BR measures with ones provided by an FDA-cleared device in a 12-participant laboratory study: the estimates achieved a mean absolute error of 0.36 beats per minute and 0.24 breaths per minute under both bright and dark lighting. Significance: This work advances the possibilities of non-contact physiological measurement in real-life conditions in which environmental illumination is limited and in which the face of the person is not readily available or needs to be protected. Due to the increasing availability of NIR imaging devices, the described methods are readily scalable.

cs.CV↗

arXiv2017

Organic Primitives: Synthesis and Design of pH-Reactive Materials using Molecular I/O for Sensing, Actuation, and Interaction

In this paper we present Organic Primitives, an enabling toolbox that expands upon the library of input-output devices in HCI and facilitates the design of interactions with organic, fluid-based systems. We formulated color, odor and shape changing material primitives which act as sensor-actuators that convert pH signals into human-readable outputs. Food-grade organic molecules anthocyanin, vanillin, and chitosan were employed as dopants to synthesize materials which output a spectrum of colors, degrees of shape deformation, and switch between odorous and non-odorous states. We evaluated the individual output properties of our sensor-actuators to assess the rate, range, and reversibility of the changes as a function of pH 2-10. We present a design space with techniques for enhancing the functionality of the material primitives, and offer passive and computational methods for controlling the material interfaces. Finally, we explore applications enabled by Organic Primitives under four contexts: environmental, cosmetic, edible, and interspecies.

cs.HC↗