arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 307 records · Page 17Linked to original sources

arXiv2025

Can We Verify Step by Step for Incorrect Answer Detection?

Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing end-task performance. In addition, there has been research on assessing the quality of reasoning chains in CoT. This raises an intriguing question: Is it possible to predict the accuracy of LLM outputs by scrutinizing the reasoning chains they generate? To answer this research question, we introduce a benchmark, R2PE, designed specifically to explore the relationship between reasoning chains and performance in various reasoning tasks spanning five different domains. This benchmark aims to measure the falsehood of the final output of LLMs based on the reasoning steps. To make full use of information in multiple reasoning chains, we propose the process discernibility score (PDS) framework that beats the answer-checking baseline by a large margin. Concretely, this resulted in an average of $5.1\%$ increase in the F1 score and $2.97\%$ improvement in AUC-PR across all 45 subsets within R2PE. We further demonstrate our PDS's efficacy in advancing open-domain QA accuracy.

cs.CL↗

arXiv2025

Security Analysis of Mode-Pairing Quantum Key Distribution with Flexible Pairing Strategy

Mode-pairing quantum key distribution (MP-QKD) is advantageous for long-distance secure communication, leveraging its simple implementation and quadratic scaling capacity. The post-measurement pairing in MP-QKD alleviates the photon-coincidence demands, which is essential for surpassing the fundamental limit to the key-rate transmission. In this work, we propose an improved decoy-state MP-QKD protocol featuring a flexible and efficient pairing strategy. We prove the security of the proposed scheme by presenting an entanglement model for decoy-state MP-QKD. The simulation results show that the secret key rate (SKR) can be enhanced among all distances. Notably, compared with the original scheme [Nature Communication 13, 3903 (2022)], the improvement of SKR is greater than 65\% within 375 km in the asymptotic case and greater than 50\% within 400 km in the finite case. And the achievable distance can be extended in the finite case, especially with a small block length. The simulation results demonstrate the high efficiency of the proposed scheme, which is expected to promote the practical applicability of MP-QKD. Furthermore, the entanglement model could provide a theoretical framework for further security and performance analysis of decoy-state MP-QKD.

quant-ph↗

arXiv2025

Experimental Frequency-Comb-Based Mode-Pairing Quantum Key Distribution Beyond the Rate-Loss Limit

Mode-pairing quantum key distribution (MP-QKD) offers significant potential for long-distance secure communication, benefiting from its quadratic scaling capacity and phase compensation-free characteristic. However, MP-QKD still requires stringent wavelength consistency between remote lasers, which is impractical with commercial lasers without locking. In this work, we develop a simple optical-frequency-comb-based MP-QKD system to simultaneously establish coherence and distribute keys with free-running commercial lasers. We implement the experiment over standard single-mode fiber with a loss coefficient of 0.2 dB/km. The system achieves finite-size secret key rates (SKRs) of 561.26, 113.59, and 10.20 bits per second over 303.37, 354.62, and 404.25 km, which are 1.0267, 2.5230, and 2.1033 times of the rate-loss limit. Besides, the SKR over 202.31 km is 8695.34 bits per second, which is sufficient to support practical cryptographic applications. These results validate the practicality and robustness of our method, offering a simplified yet high-performance framework for long-distance secure communication.

quant-ph↗

arXiv2025

Entanglement Model for Mode-Pairing Quantum Key Distribution

Mode-pairing (MP) quantum key distribution (QKD) eliminates the requirements of phase locking and phase tracking compared with twin-field (TF) QKD while still surpassing the fundamental rate-distance limit of QKD. The complexity of the experimental implementation is reduced while the efficiency can still be guaranteed. In MP-QKD, two communication parties need to pair two effective rounds according to the announced results by the third party. Therefore, it is not intuitive how to provide an entanglement protocol equivalent to the prepare-and-measure protocol for proving security. At present, the security of MP-QKD is rigorously proven by examining the consistency of the states detailly between MP-QKD and the fixed-pairing scheme under all of Eve's possible interference to obtain the equivalence, and verifying the security of the latter. Here, we directly present an entanglement model for MP-QKD by proposing a free-pairing entanglement scheme that is equivalent to MP-QKD. This entanglement model simplifies the security proof and provides a clearer insight into the foundation of MP-QKD. Besides, it could provide a theoretical framework for the comprehensive analysis of MP-QKD, such as facilitating practical security analysis. Additionally, we propose an optimized pairing strategy based on the entanglement model. The simulation results show an enhancement of 163\% in pairing efficiency with a reasonable pairing interval $2 \times 10^5$.

quant-ph↗

arXiv2025

PIDiff: Image Customization for Personalized Identities with Diffusion Models

Text-to-image generation for personalized identities aims at incorporating the specific identity into images using a text prompt and an identity image. Based on the powerful generative capabilities of DDPMs, many previous works adopt additional prompts, such as text embeddings and CLIP image embeddings, to represent the identity information, while they fail to disentangle the identity information and background information. As a result, the generated images not only lose key identity characteristics but also suffer from significantly reduced diversity. To address this issue, previous works have combined the W+ space from StyleGAN with diffusion models, leveraging this space to provide a more accurate and comprehensive representation of identity features through multi-level feature extraction. However, the entanglement of identity and background information in in-the-wild images during training prevents accurate identity localization, resulting in severe semantic interference between identity and background. In this paper, we propose a novel fine-tuning-based diffusion model for personalized identities text-to-image generation, named PIDiff, which leverages the W+ space and an identity-tailored fine-tuning strategy to avoid semantic entanglement and achieves accurate feature extraction and localization. Style editing can also be achieved by PIDiff through preserving the characteristics of identity features in the W+ space, which vary from coarse to fine. Through the combination of the proposed cross-attention block and parameter optimization strategy, PIDiff preserves the identity information and maintains the generation capability for in-the-wild images of the pre-trained model during inference. Our experimental results validate the effectiveness of our method in this task.

cs.CV↗

arXiv2025

MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models

Multi-object editing aims to modify multiple objects or regions in complex scenes while preserving structural coherence. This task faces significant challenges in scenarios involving overlapping or interacting objects: (1) Inaccurate localization of target objects due to attention misalignment, leading to incomplete or misplaced edits; (2) Attribute-object mismatch, where color or texture changes fail to align with intended regions due to cross-attention leakage, creating semantic conflicts (\textit{e.g.}, color bleeding into non-target areas). Existing methods struggle with these challenges: approaches relying on global cross-attention mechanisms suffer from attention dilution and spatial interference between objects, while mask-based methods fail to bind attributes to geometrically accurate regions due to feature entanglement in multi-object scenarios. To address these limitations, we propose a training-free, inference-stage optimization approach that enables precise localized image manipulation in complex multi-object scenes, named MDE-Edit. MDE-Edit optimizes the noise latent feature in diffusion models via two key losses: Object Alignment Loss (OAL) aligns multi-layer cross-attention with segmentation masks for precise object positioning, and Color Consistency Loss (CCL) amplifies target attribute attention within masks while suppressing leakage to adjacent regions. This dual-loss design ensures localized and coherent multi-object edits. Extensive experiments demonstrate that MDE-Edit outperforms state-of-the-art methods in editing accuracy and visual quality, offering a robust solution for complex multi-object image manipulation tasks.

cs.CV↗

arXiv2025

User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data

With the widespread application of large language models (LLMs), user privacy protection has become a significant research topic. Existing privacy preference modeling methods often rely on large-scale user data, making effective privacy preference analysis challenging in data-limited environments. This study explores how LLMs can analyze user behavior related to privacy protection in scenarios with limited data and proposes a method that integrates Few-shot Learning and Privacy Computing to model user privacy preferences. The research utilizes anonymized user privacy settings data, survey responses, and simulated data, comparing the performance of traditional modeling approaches with LLM-based methods. Experimental results demonstrate that, even with limited data, LLMs significantly improve the accuracy of privacy preference modeling. Additionally, incorporating Differential Privacy and Federated Learning further reduces the risk of user data exposure. The findings provide new insights into the application of LLMs in privacy protection and offer theoretical support for advancing privacy computing and user behavior analysis.

cs.CR↗

arXiv2025

Soft causal learning for generalized molecule property prediction: An environment perspective

Learning on molecule graphs has become an increasingly important topic in AI for science, which takes full advantage of AI to facilitate scientific discovery. Existing solutions on modeling molecules utilize Graph Neural Networks (GNNs) to achieve representations but they mostly fail to adapt models to out-of-distribution (OOD) samples. Although recent advances on OOD-oriented graph learning have discovered the invariant rationale on graphs, they still ignore three important issues, i.e., 1) the expanding atom patterns regarding environments on graphs lead to failures of invariant rationale based models, 2) the associations between discovered molecular subgraphs and corresponding properties are complex where causal substructures cannot fully interpret the labels. 3) the interactions between environments and invariances can influence with each other thus are challenging to be modeled. To this end, we propose a soft causal learning framework, to tackle the unresolved OOD challenge in molecular science, from the perspective of fully modeling the molecule environments and bypassing the invariant subgraphs. Specifically, we first incorporate chemistry theories into our graph growth generator to imitate expaned environments, and then devise an GIB-based objective to disentangle environment from whole graphs and finally introduce a cross-attention based soft causal interaction, which allows dynamic interactions between environments and invariances. We perform experiments on seven datasets by imitating different kinds of OOD generalization scenarios. Extensive comparison, ablation experiments as well as visualized case studies demonstrate well generalization ability of our proposal.

cs.LG↗

arXiv2025

Intelligent Task Scheduling for Microservices via A3C-Based Reinforcement Learning

To address the challenges of high resource dynamism and intensive task concurrency in microservice systems, this paper proposes an adaptive resource scheduling method based on the A3C reinforcement learning algorithm. The scheduling problem is modeled as a Markov Decision Process, where policy and value networks are jointly optimized to enable fine-grained resource allocation under varying load conditions. The method incorporates an asynchronous multi-threaded learning mechanism, allowing multiple agents to perform parallel sampling and synchronize updates to the global network parameters. This design improves both policy convergence efficiency and model stability. In the experimental section, a real-world dataset is used to construct a scheduling scenario. The proposed method is compared with several typical approaches across multiple evaluation metrics, including task delay, scheduling success rate, resource utilization, and convergence speed. The results show that the proposed method delivers high scheduling performance and system stability in multi-task concurrent environments. It effectively alleviates the resource allocation bottlenecks faced by traditional methods under heavy load, demonstrating its practical value for intelligent scheduling in microservice systems.

cs.DC↗

arXiv2025

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of LLMs through BitMoD, an algorithm-hardware co-design solution that enables efficient LLM acceleration at low weight precision. On the algorithm side, BitMoD introduces fine-grained data type adaptation that uses a different numerical data type to quantize a group of (e.g., 128) weights. Through the careful design of these new data types, BitMoD is able to quantize LLM weights to very low precision (e.g., 4 bits and 3 bits) while maintaining high accuracy. On the hardware side, BitMoD employs a bit-serial processing element to easily support multiple numerical precisions and data types; our hardware design includes two key innovations: First, it employs a unified representation to process different weight data types, thus reducing the hardware cost. Second, it adopts a bit-serial dequantization unit to rescale the per-group partial sum with minimal hardware overhead. Our evaluation on six representative LLMs demonstrates that BitMoD significantly outperforms state-of-the-art LLM quantization and acceleration methods. For discriminative tasks, BitMoD can quantize LLM weights to 4-bit with $<\!0.5\%$ accuracy loss on average. For generative tasks, BitMoD is able to quantize LLM weights to 3-bit while achieving better perplexity than prior LLM quantization scheme. Combining the superior model performance with an efficient accelerator design, BitMoD achieves an average of $1.69\times$ and $1.48\times$ speedups compared to prior LLM accelerators ANT and OliVe, respectively.

cs.LG↗

arXiv2025

Towards Generalizable Deepfake Detection with Spatial-Frequency Collaborative Learning and Hierarchical Cross-Modal Fusion

The rapid evolution of deep generative models poses a critical challenge to deepfake detection, as detectors trained on forgery-specific artifacts often suffer significant performance degradation when encountering unseen forgeries. While existing methods predominantly rely on spatial domain analysis, frequency domain operations are primarily limited to feature-level augmentation, leaving frequency-native artifacts and spatial-frequency interactions insufficiently exploited. To address this limitation, we propose a novel detection framework that integrates multi-scale spatial-frequency analysis for universal deepfake detection. Our framework comprises three key components: (1) a local spectral feature extraction pipeline that combines block-wise discrete cosine transform with cascaded multi-scale convolutions to capture subtle spectral artifacts; (2) a global spectral feature extraction pipeline utilizing scale-invariant differential accumulation to identify holistic forgery distribution patterns; and (3) a multi-stage cross-modal fusion mechanism that incorporates shallow-layer attention enhancement and deep-layer dynamic modulation to model spatial-frequency interactions. Extensive evaluations on widely adopted benchmarks demonstrate that our method outperforms state-of-the-art deepfake detection methods in both accuracy and generalizability.

cs.CV↗

arXiv2025

Contrastive Learning for Continuous Touch-Based Authentication

Smart mobile devices have become indispensable in modern daily life, where sensitive information is frequently processed, stored, and transmitted-posing critical demands for robust security controls. Given that touchscreens are the primary medium for human-device interaction, continuous user authentication based on touch behavior presents a natural and seamless security solution. While existing methods predominantly adopt binary classification under single-modal learning settings, we propose a unified contrastive learning framework for continuous authentication in a non-disruptive manner. Specifically, the proposed method leverages a Temporal Masked Autoencoder to extract temporal patterns from raw multi-sensor data streams, capturing continuous motion and gesture dynamics. The pre-trained TMAE is subsequently integrated into a Siamese Temporal-Attentive Convolutional Network within a contrastive learning paradigm to model both sequential and cross-modal patterns. To further enhance performance, we incorporate multi-head attention and channel attention mechanisms to capture long-range dependencies and optimize inter-channel feature integration. Extensive experiments on public benchmarks and a self-collected dataset demonstrate that our approach outperforms state-of-the-art methods, offering a reliable and effective solution for user authentication on mobile devices.

cs.CR↗

arXiv2025

LLM-Driven Optimization of HTML Structure to Support Screen Reader Navigation

Online interactions and e-commerce are commonplace among BLV users. Despite the implementation of web accessibility standards, many e-commerce platforms continue to present challenges to screen reader users, particularly in areas like webpage navigation and information retrieval. We investigate the difficulties encountered by screen reader users during online shopping experiences. We conducted a formative study with BLV users and designed a web browser plugin that uses GenAI to restructure webpage content in real time. Our approach improved the header hierarchy and provided correct labeling for essential information. We evaluated the effectiveness of this solution using an automated accessibility tool and through user interviews. Our results show that the revised webpages generated by our system offer significant improvements over the original webpages regarding screen reader navigation experience. Based on our findings, we discuss its potential usage as both a user and developer tool that can significantly enhance screen reader accessibility of webpages.

cs.HC↗

arXiv2025

Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective

The Transformer model is widely used in various application areas of machine learning, such as natural language processing. This paper investigates the approximation of the Hölder continuous function class $\mathcal{H}_{Q}^β\left([0,1]^{d\times n},\mathbb{R}^{d\times n}\right)$ by Transformers and constructs several Transformers that can overcome the curse of dimensionality. These Transformers consist of one self-attention layer with one head and the softmax function as the activation function, along with several feedforward layers. For example, to achieve an approximation accuracy of $ε$, if the activation functions of the feedforward layers in the Transformer are ReLU and floor, only $\mathcal{O}\left(\log\frac{1}ε\right)$ layers of feedforward layers are needed, with widths of these layers not exceeding $\mathcal{O}\left(\frac{1}{ε^{2/β}}\log\frac{1}ε\right)$. If other activation functions are allowed in the feedforward layers, the width of the feedforward layers can be further reduced to a constant. These results demonstrate that Transformers have a strong expressive capability. The construction in this paper is based on the Kolmogorov-Arnold Representation Theorem and does not require the concept of contextual mapping, hence our proof is more intuitively clear compared to previous Transformer approximation works. Additionally, the translation technique proposed in this paper helps to apply the previous approximation results of feedforward neural networks to Transformer research.

cs.LG↗

arXiv2025

Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching

Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions. We propose FS-RVOS, a Transformer-based model with two key components: a cross-modal affinity module and an instance sequence matching strategy, which extends FS-RVOS to multi-object segmentation (FS-RVMOS). Experiments show FS-RVOS and FS-RVMOS outperform state-of-the-art methods across diverse benchmarks, demonstrating superior robustness and accuracy.

cs.CV↗

arXiv2025

Approximation Bounds for Transformer Networks with Application to Regression

We explore the approximation capabilities of Transformer networks for Hölder and Sobolev functions, and apply these results to address nonparametric regression estimation with dependent observations. First, we establish novel upper bounds for standard Transformer networks approximating sequence-to-sequence mappings whose component functions are Hölder continuous with smoothness index $γ\in (0,1]$. To achieve an approximation error $\varepsilon$ under the $L^p$-norm for $p \in [1, \infty]$, it suffices to use a fixed-depth Transformer network whose total number of parameters scales as $\varepsilon^{-d_x n / γ}$. This result not only extends existing findings to include the case $p = \infty$, but also matches the best known upper bounds on number of parameters previously obtained for fixed-depth FNNs and RNNs. Similar bounds are also derived for Sobolev functions. Second, we derive explicit convergence rates for the nonparametric regression problem under various $β$-mixing data assumptions, which allow the dependence between observations to weaken over time. Our bounds on the sample complexity impose no constraints on weight magnitudes. Lastly, we propose a novel proof strategy to establish approximation bounds, inspired by the Kolmogorov-Arnold representation theorem. We show that if the self-attention layer in a Transformer can perform column averaging, the network can approximate sequence-to-sequence Hölder functions, offering new insights into the interpretability of self-attention mechanisms.

stat.ML↗

arXiv2025

NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results

This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal of the challenge is to design an event-based method that achieves high-quality image deblurring, with performance quantitatively assessed using Peak Signal-to-Noise Ratio (PSNR). Notably, there are no restrictions on computational complexity or model size. The task focuses on leveraging both events and images as inputs for single-image deblurring. A total of 199 participants registered, among whom 15 teams successfully submitted valid results, offering valuable insights into the current state of event-based image deblurring. We anticipate that this challenge will drive further advancements in event-based vision research.

cs.CV↗

arXiv2025

The Jade Gateway to Trust: Exploring How Socio-Cultural Perspectives Shape Trust Within Chinese NFT Communities

Today's world is witnessing an unparalleled rate of technological transformation. The emergence of non-fungible tokens (NFTs) has transformed how we handle digital assets and value. Despite their initial popularity, NFTs face declining adoption influenced not only by cryptocurrency volatility but also by trust dynamics within communities. From a social computing perspective, understanding these trust dynamics offers valuable insights for the development of both the NFT ecosystem and the broader digital economy. China presents a compelling context for examining these dynamics, offering a unique intersection of technological innovation and traditional cultural values. Through a content analysis of eight Chinese NFT-focused WeChat groups and 21 semi-structured interviews, we examine how socio-cultural factors influence trust formation and development. We found that trust in Chinese NFT communities is significantly molded by local cultural values. To be precise, Confucian virtues, such as benevolence, propriety, and integrity, play a crucial role in shaping these trust relationships. Our research identifies three critical trust dimensions in China's NFT market: (1) technological, (2) institutional, and (3) social. We examined the challenges in cultivating each dimension. Based on these insights, we developed tailored trust-building guidelines for Chinese NFT stakeholders. These guidelines address trust issues that factor into NFT's declining popularity and could offer valuable strategies for CSCW researchers, developers, and designers aiming to enhance trust in global NFT communities. Our research urges CSCW scholars to take into account the unique socio-cultural contexts when developing trust-enhancing strategies for digital innovations and online interactions.

cs.CY↗