arXiv subjects

Wan Jiang

Publications and source records attributed to Wan Jiang.

14 recordsLinked to original sources

arXiv2026

Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection

Deep learning-based Major Depressive Disorder (MDD) detection using Electroencephalography (EEG) is fundamentally constrained by the "small-sample dilemma." Prevailing generative data augmentation methods not only incur heavy computational overhead but also risk introducing synthetic noise, thereby blurring classification boundaries. To challenge the traditional "data quantity first" convention, we propose a novel framework "Beyond Augmentation": Score-Guided Classification (SGC). SGC does not synthesize pseudo-samples; instead, it utilizes an unsupervised generative network architecture to model the structural and statistical anomaly degrees of samples, serving as the core "Pathological Prior". This prior, after robust normalization, is explicitly fused with deep feature representations, thereby precisely guiding the classifier's decision boundary. Furthermore, to dynamically adapt to varying channel configurations, we propose a Cross-Channel Spatial Adaptation module, utilizing a spatial mapping mechanism to effectively resolve the hardware heterogeneity of mismatched channels in multi-center datasets. Extensive experiments on the Mumtaz2016 and high-density MODMA datasets demonstrate the effectiveness and exceptional generalizability of our method under the challenging "zero data augmentation" setting and at "zero sample synthesis cost". Keywords: Electroencephalography (EEG), Depression Detection, Anomaly Score, Diffusion Models, Few-Shot Learning

cs.LG↗

arXiv2026

CanonSLR: Canonical-View Guided Multi-View Continuous Sign Language Recognition

Continuous Sign Language Recognition (CSLR) has achieved remarkable progress in recent years; however, most existing methods are developed under single-view settings and thus remain insufficiently robust to viewpoint variations in real-world scenarios. To address this limitation, we propose CanonSLR, a canonical-view guided framework for multi-view CSLR. Specifically, we introduce a frontal-view-anchored teacher-student learning strategy, in which a teacher network trained on frontal-view data provides canonical temporal supervision for a student network trained on all viewpoints. To further reduce cross-view semantic discrepancy, we propose Sequence-Level Soft-Target Distillation, which transfers structured temporal knowledge from the frontal view to non-frontal samples, thereby alleviating gloss boundary ambiguity and category confusion caused by occlusion and projection variation. In addition, we introduce Temporal Motion Relational Enhancement to explicitly model motion-aware temporal relations in high-level visual features, strengthening stable dynamic representations while suppressing viewpoint-sensitive appearance disturbances. To support multi-view CSLR research, we further develop a universal multi-view sign language data construction pipeline that transforms original single-view RGB videos into semantically consistent, temporally coherent, and viewpoint-controllable multi-view sign language videos. Based on this pipeline, we extend PHOENIX-2014T and CSL-Daily into two seven-view benchmarks, namely PT14-MV and CSL-MV, providing a new experimental foundation for multi-view CSLR. Extensive experiments on PT14-MV and CSL-MV demonstrate that CanonSLR consistently outperforms existing approaches under multi-view settings and exhibits stronger robustness, especially on challenging non-frontal views.

cs.CV↗

arXiv2026

A C-band microwave rectifier without capacitors for microwave power transmission

A microwave rectifier at 5.8 GHz without any capacitors is presented, which owns a measured MW-to-DC conversion efficiency of 68.1%. A harmonic rejection filter and a DC pass filter, which replace lumped capacitors in conventional microwave rectifiers, are applied to suppressing the harmonics produced by an HSMS-286 Schottky diode during rectifying. At the fundamental frequency, a microstrip impedance transformer which contains a shunt {\lambda}g/8 short-ended microstrip transmission line and two short series microstrip transmission lines are applied to compensating the imaginary impedance of the diode and matching the input impedance of the rectifier. The measured MW-to-DC conversion efficiency agrees well to the simulated results. The novel rectifier without any lumped passive elements may be applied for power transmission system at higher microwave frequencies.

physics.app-ph↗

arXiv2026

Experimental study on an S-band near-field microwave magnetron power transmission system on hundred-watt level

A multi-magnetron microwave source, a metamaterial transmitting antenna, and a large power rectenna array are presented to build a near-field 2.45 GHz microwave power transmission system. The square 1 m2 rectenna array consists of sixteen rectennas with 2048 Schottky diodes for large power microwave rectifying. It receives microwave power and converts them into DC power. The design, structure, and measured performance of a unit rectenna as well as the entail rectenna array are presented in detail. The multi-magnetron microwave power source switches between half and full output power levels, i.e. the half-wave and full-wave modes. The transmission antenna is formed by a double-layer metallic hole array, which is applied to combine the output power of each magnetron. The rectenna array DC output power reaches 67.3 W on a 1.2 ohm DC load at a distance of 5.5 m from the transmission antenna. DC output power is affected by the distance, DC load, and the mode of microwave power source. It shows that conventional low power Schottky diodes can be applied to a microwave power transmission system with simple magnetrons to realise large power microwave rectifying.

physics.app-ph↗

arXiv2025

SEGB: Self-Evolved Generative Bidding with Local Autoregressive Diffusion

In the realm of online advertising, automated bidding has become a pivotal tool, enabling advertisers to efficiently capture impression opportunities in real-time. Recently, generative auto-bidding has shown significant promise, offering innovative solutions for effective ad optimization. However, existing offline-trained generative policies lack the near-term foresight required for dynamic markets and usually depend on simulators or external experts for post-training improvement. To overcome these critical limitations, we propose Self-Evolved Generative Bidding (SEGB), a framework that plans proactively and refines itself entirely offline. SEGB first synthesizes plausible short-horizon future states to guide each bid, providing the agent with crucial, dynamic foresight. Crucially, it then performs value-guided policy refinement to iteratively discover superior strategies without any external intervention. This self-contained approach uniquely enables robust policy improvement from static data alone. Experiments on the AuctionNet benchmark and a large-scale A/B test validate our approach, demonstrating that SEGB significantly outperforms state-of-the-art baselines. In a large-scale online deployment, it delivered substantial business value, achieving a +10.19% increase in target cost, proving the effectiveness of our advanced planning and evolution paradigm.

cs.IR↗

arXiv2025

MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systems

Modern recommender systems face significant computational challenges due to growing model complexity and traffic scale, making efficient computation allocation critical for maximizing business revenue. Existing approaches typically simplify multi-stage computation resource allocation, neglecting inter-stage dependencies, thus limiting global optimality. In this paper, we propose MaRCA, a multi-agent reinforcement learning framework for end-to-end computation resource allocation in large-scale recommender systems. MaRCA models the stages of a recommender system as cooperative agents, using Centralized Training with Decentralized Execution (CTDE) to optimize revenue under computation resource constraints. We introduce an AutoBucket TestBench for accurate computation cost estimation, and a Model Predictive Control (MPC)-based Revenue-Cost Balancer to proactively forecast traffic loads and adjust the revenue-cost trade-off accordingly. Since its end-to-end deployment in the advertising pipeline of a leading global e-commerce platform in November 2024, MaRCA has consistently handled hundreds of billions of ad requests per day and has delivered a 16.67% revenue uplift using existing computation resources.

cs.IR↗

arXiv2025

EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift

Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding: structural edits enhance the reconstruction of real images while degrading that of generated images, creating a distinctive edit-induced reconstruction error shift. This asymmetric shift enhances the separability between real and generated images. Building on this insight, we propose EIRES, a training-free method that leverages structural edits to reveal inherent differences between real and generated images. To explain the discriminative power of this shift, we derive the reconstruction error lower bound under edit perturbations. Since EIRES requires no training, thresholding depends solely on the natural separability of the signal, where a larger margin yields more reliable detection. Extensive experiments show that EIRES is effective across diverse generative models and remains robust on the unbiased subset, even under post-processing operations.

cs.CV↗

arXiv2024

Moderating the Generalization of Score-based Generative Model

Score-based Generative Models (SGMs) have demonstrated remarkable generalization abilities, e.g. generating unseen, but natural data. However, the greater the generalization power, the more likely the unintended generalization, and the more dangerous the abuse. Research on moderated generalization in SGMs remains limited. To fill this gap, we first examine the current 'gold standard' in Machine Unlearning (MU), i.e., re-training the model after removing the undesirable training data, and find it does not work in SGMs. Further analysis of score functions reveals that the MU 'gold standard' does not alter the original score function, which explains its ineffectiveness. Based on this insight, we propose the first Moderated Score-based Generative Model (MSGM), which introduces a novel score adjustment strategy that redirects the score function away from undesirable data during the continuous-time stochastic differential equation process. Extensive experimental results demonstrate that MSGM significantly reduces the likelihood of generating undesirable content while preserving high visual quality for normal image generation. Albeit designed for SGMs, MSGM is a general and flexible MU framework that is compatible with diverse diffusion architectures (SGM and DDPM) and training strategies (re-training and fine-tuning), and enables zero-shot transfer of the pre-trained models to downstream tasks, e.g. image inpainting and reconstruction. The code will be shared upon acceptance.

cs.LG↗

arXiv2024

Cosine Annealing Optimized Denoising Diffusion Error Correction Codes

To address the issue of increased bit error rates during the later stages of linear search in denoising diffusion error correction codes, we propose a novel method that optimizes denoising diffusion error correction codes (ECC) using cosine annealing. In response to the challenge of decoding long codewords, the proposed method employs a variance adjustment strategy during the reverse diffusion process, rather than maintaining a constant variance. By leveraging cosine annealing, this method effectively lowers the bit error rate and enhances decoding effciency. This letter extensively validates the approach through experiments and demonstrates signifcant improvements in bit error rate reduction and iteration effciency compared to existing methods. This advancement offers a promising solution for improving ECC decoding performance, potentially impacting secure digital communication practices.

cs.IT↗

arXiv2023

Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples

Safeguarding data from unauthorized exploitation is vital for privacy and security, especially in recent rampant research in security breach such as adversarial/membership attacks. To this end, \textit{unlearnable examples} (UEs) have been recently proposed as a compelling protection, by adding imperceptible perturbation to data so that models trained on them cannot classify them accurately on original clean distribution. Unfortunately, we find UEs provide a false sense of security, because they cannot stop unauthorized users from utilizing other unprotected data to remove the protection, by turning unlearnable data into learnable again. Motivated by this observation, we formally define a new threat by introducing \textit{learnable unauthorized examples} (LEs) which are UEs with their protection removed. The core of this approach is a novel purification process that projects UEs onto the manifold of LEs. This is realized by a new joint-conditional diffusion model which denoises UEs conditioned on the pixel and perceptual similarity between UEs and LEs. Extensive experiments demonstrate that LE delivers state-of-the-art countering performance against both supervised UEs and unsupervised UEs in various scenarios, which is the first generalizable countermeasure to UEs across supervised learning and unsupervised learning. Our code is available at \url{https://github.com/jiangw-0/LE_JCDP}.

cs.LG↗

arXiv2023

New entanglement-assisted quantum codes from negacyclic codes

The theory of entanglement-assisted quantum error-correcting codes (EAQECCs) is a generalization of the standard stabilizer quantum error-correcting codes, which can be possibly constructed from any classical codes by relaxing the duality condition and utilizing preshared entanglement between the sender and receiver. In this paper, a new family of EAQECCs is constructed from negacyclic codes of length $n=\frac{q^2+1}{a}$, where $q$ is an odd prime power, $a=\frac{m^2+1}{2}$ and $m$ is an odd integer. Some new entanglement-assisted quantum maximum distance separable (EAQMDS) codes are obtained in the sense that their parameters are not covered by the previously known ones.

cs.IT↗

arXiv2022

Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling

Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm.

cs.LG↗

arXiv2020

Cyclic codes and some new entanglement-assisted quantum MDS codes

Entanglement-assisted quantum error correcting codes (EAQECCs) play a significant role in protecting quantum information from decoherence and quantum noise. Recently, constructing entanglement-assisted quantum maximum distance separable (EAQMDS) codes with flexible parameters has received much attention. In this work, four families of EAQMDS codes with a more general length are presented. And the method of selecting defining set is different from others. Compared with all the previously known results, the EAQMDS codes we constructed have larger minimum distance. All of these EAQMDS codes are new in the sense that their parameters are not covered by the quantum codes available in the literature.

cs.IT↗

arXiv2019

New entanglement-assisted quantum MDS codes with length $n=\frac{q^2+1}5$

The entanglement-assisted stabilizer formalism can transform arbitrary classical linear codes into entanglement-assisted quantum error correcting codes (EAQECCs). In this work, we construct some new entanglement-assisted quantum MDS (EAQMDS) codes with length $n=\frac{q^2+1}5$ from cyclic codes. Compared with all the previously known parameters with the same length, all of them have flexible parameters and larger minimum distance.

cs.IT↗