arXiv subjects

Ming Xu

Publications and source records attributed to Ming Xu.

At least 55 records · Page 3Linked to original sources

arXiv2025

On the Arikan Transformations of Binary-Input Discrete Memoryless Channels

The polar codes introduced by Arikan in 2009 achieve the capacity of binary-input discrete memoryless channels (BIDMCs) with low complexity encoding and decoding. Identifying the unreliable synthetic channels, generated by Arikan transformation during the construction of these polar codes, is crucial. Currently, because of the large size of the output alphabets of synthetic channels, there is no efficient and practical approach to evaluate their reliability in general. To tackle this problem, by converting the generation of synthetic channels in polar code construction into algebraic operations, in this paper we develop a method to characterize the synthetic channels as random switching channels of binary symmetric channels when the underlying channels are symmetric. Moreover, a lower bound for the average number of elements that possess the same likelihood ratio within the output alphabet of any synthetic channel generated in polar codes is also derived.

cs.IT↗

arXiv2025

ITVTON: Virtual Try-On Diffusion Transformer Based on Integrated Image and Text

Virtual try-on, which aims to seamlessly fit garments onto person images, has recently seen significant progress with diffusion-based models. However, existing methods commonly resort to duplicated backbones or additional image encoders to extract garment features, which increases computational overhead and network complexity. In this paper, we propose ITVTON, an efficient framework that leverages the Diffusion Transformer (DiT) as its single generator to improve image fidelity. By concatenating garment and person images along the width dimension and incorporating textual descriptions from both, ITVTON effectively captures garment-person interactions while preserving realism. To further reduce computational cost, we restrict training to the attention parameters within a single Diffusion Transformer (Single-DiT) block. Extensive experiments demonstrate that ITVTON surpasses baseline methods both qualitatively and quantitatively, setting a new standard for virtual try-on. Moreover, experiments on 10,257 image pairs from IGPair confirm its robustness in real-world scenarios.

cs.CV↗

arXiv2025

Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis

The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research Intelligence Assistant), a spec-driven, human-in-the-loop framework for automated and interpretable data analysis. ARIA integrates six interoperable layers, namely Command, Context, Code, Data, Orchestration, and AI Module, within a document-centric workflow that unifies human reasoning and machine execution. Through natural-language specifications, researchers define analytical goals while ARIA autonomously generates executable code, validates computations, and produces transparent documentation. Beyond achieving high predictive accuracy, ARIA can rapidly identify optimal feature sets and select suitable models, minimizing redundant tuning and repetitive experimentation. In the Boston Housing case, ARIA discovered 25 key features and determined XGBoost as the best performing model (R square = 0.93) with minimal overfitting. Evaluations across heterogeneous domains demonstrate ARIA's strong performance, interpretability, and efficiency compared with state-of-the-art systems. By combining AI for research and AI for science principles within a spec-driven architecture, ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery.

cs.AI↗

arXiv2025

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, despite their widespread deployment in inference services such as Midjourney, concerns about the potential leakage of sensitive information in uploaded user prompts have arisen. Existing solutions either lack rigorous privacy guarantees or fail to strike an effective balance between utility and efficiency. To bridge this gap, we propose ObCLIP, a plug-and-play safeguard that enables oblivious cloud-device hybrid generation. By oblivious, each input prompt is transformed into a set of semantically similar candidate prompts that differ only in sensitive attributes (e.g., gender, ethnicity). The cloud server processes all candidate prompts without knowing which one is the real one, thus preventing any prompt leakage. To mitigate server cost, only a small portion of denoising steps is performed upon the large cloud model. The intermediate latents are then sent back to the client, which selects the targeted latent and completes the remaining denoising using a small device model. Additionally, we analyze and incorporate several cache-based accelerations that leverage temporal and batch redundancy, effectively reducing computation cost with minimal utility degradation. Extensive experiments across multiple datasets demonstrate that ObCLIP provides rigorous privacy and comparable utility to cloud models with slightly increased server cost.

cs.CR↗

arXiv2025

New constructions of cyclic constant-dimension subspace codes based on Sidon spaces and subspace polynomials

In this paper, two new constructions of Sidon spaces are given by tactfully adding new parameters and flexibly varying the number of parameters. Under the parameters $ n= (2r+1)k, r \ge2 $ and $p_0=\max \{i\in \mathbb{N}^+: \lfloor \frac{r}{i}\rfloor>\lfloor \frac{r}{i+1} \rfloor \}$, the first construction produces a cyclic CDC in $\mathcal{G}_q(n, k)$ with minimum distance $2k-2$ and size $\frac{\left((r+\sum\limits_{i=2}^{p_0}(\lfloor \frac{r}{i}\rfloor-\lfloor \frac{r}{i+1} \rfloor))(q^k-1)(q-1)+r\right)(q^k-1)^{r-1}(q^n-1)}{q-1}$. Given parameters $n=2rk,r\ge 2$ and if $r=2$, $p_0=1$, otherwise, $p_0=\max\{ i\in \mathbb{N}^+: \lceil\frac{r}{i}\rceil-1>\lfloor \frac{r}{i+1} \rfloor \}$, a cyclic CDC in $\mathcal{G}_q(n, k)$ with minimum distance $2k-2$ and size $\frac{\left((r-1+\sum\limits_{i=2}^{p_0}(\lceil \frac{r}{i}\rceil-\lfloor \frac{r}{i+1} \rfloor-1))(q^k-1)(q-1)+r-1\right)(q^k-1)^{r-2}\lfloor \frac{q^k-2}{2}\rfloor(q^n-1)}{q-1}$ is produced by the second construction. The sizes of our cyclic CDCs are larger than the best known results. In particular, in the case of $n=4k$, when $k$ goes to infinity, the ratio between the size of our cyclic CDC and the Sphere-packing bound (Johnson bound) is approximately equal to $\frac{1}{2}$. Moreover, for a prime power $q$ and positive integers $k,s$ with $1\le s< k-1$, a cyclic CDC in $\mathcal{G}_q(N, k)$ of size $e\frac{q^N-1}{q-1}$ and minimum distance $\ge 2k-2s$ is provided by subspace polynomials, where $N,e$ are positive integers. Our construction generalizes previous results and, under certain parameters, provides cyclic CDCs with larger sizes or more admissible values of $ N $ than constructions based on trinomials.

cs.IT↗

arXiv2025

MoPE: A Mixture of Password Experts for Improving Password Guessing

Textual passwords remain a predominant authentication mechanism in web security. To evaluate their strength, existing research has proposed several data-driven models across various scenarios. However, these models generally treat passwords uniformly, neglecting the structural differences among passwords. This typically results in biased training that favors frequent password structural patterns. To mitigate the biased training, we argue that passwords, as a type of complex short textual data, should be processed in a structure-aware manner by identifying their structural patterns and routing them to specialized models accordingly. In this paper, we propose MoPE, a Mixture of Password Experts framework, specifically designed to leverage the structural patterns in passwords to improveguessing performance. Motivated by the observation that passwords with similar structural patterns (e.g., fixed-length numeric strings) tend to cluster in high-density regions within the latent space, our MoPE introduces: (1) a novel structure-based method for generating specialized expert models; (2) a lightweight gate method to select appropriate expert models to output reliable guesses, better aligned with the high computational frequency of password guessing tasks. Our evaluation shows that MoPE significantly outperforms existing state-of-the-art baselines in both offline and online guessing scenarios, achieving up to 38.80% and 9.27% improvement in cracking rate, respectively, showcasing that MoPE can effectively exploit the capabilities of data-driven models for password guessing. Additionally, we implement a real-time Password Strength Meter (PSM) based on offline MoPE, assisting users in choosing stronger passwords more precisely with millisecond-level response latency.

cs.CR↗

arXiv2025

Efficient lattice field theory simulation using adaptive normalizing flow on a resistive memory-based neural differential equation solver

Lattice field theory (LFT) simulations underpin advances in classical statistical mechanics and quantum field theory, providing a unified computational framework across particle, nuclear, and condensed matter physics. However, the application of these methods to high-dimensional systems remains severely constrained by several challenges, including the prohibitive computational cost and limited parallelizability of conventional sampling algorithms such as hybrid Monte Carlo (HMC), the substantial training expense associated with traditional normalizing flow models, and the inherent energy inefficiency of digital hardware architectures. Here, we introduce a software-hardware co-design that integrates an adaptive normalizing flow (ANF) model with a resistive memory-based neural differential equation solver, enabling efficient generation of LFT configurations. Software-wise, ANF enables efficient parallel generation of statistically independent configurations, thereby reducing computational costs, while low-rank adaptation (LoRA) allows cost-effective fine-tuning across diverse simulation parameters. Hardware-wise, in-memory computing with resistive memory substantially enhances both parallelism and energy efficiency. We validate our approach on the scalar phi4 theory and the effective field theory of graphene wires, using a hybrid analog-digital neural differential equation solver equipped with a 180 nm resistive memory in-memory computing macro. Our co-design enables low-cost computation, achieving approximately 8.2-fold and 13.9-fold reductions in integrated autocorrelation time over HMC, while requiring fine-tuning of less than 8% of the weights via LoRA. Compared to state-of-the-art GPUs, our co-design achieves up to approximately 16.1- and 17.0-fold speedups for the two tasks, as well as 73.7- and 138.0-fold improvements in energy efficiency.

cs.NE↗

arXiv2025

Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving

Embodied outdoor scene understanding forms the foundation for autonomous agents to perceive, analyze, and react to dynamic driving environments. However, existing 3D understanding is predominantly based on 2D Vision-Language Models (VLMs), which collect and process limited scene-aware contexts. In contrast, compared to the 2D planar visual information, point cloud sensors such as LiDAR provide rich depth and fine-grained 3D representations of objects. Even better the emerging 4D millimeter-wave radar detects the motion trend, velocity, and reflection intensity of each object. The integration of these two modalities provides more flexible querying conditions for natural language, thereby supporting more accurate 3D visual grounding. To this end, we propose a novel method called TPCNet, the first outdoor 3D visual grounding model upon the paradigm of prompt-guided point cloud sensor combination, including both LiDAR and radar sensors. To optimally combine the features of these two sensors required by the prompt, we design a multi-fusion paradigm called Two-Stage Heterogeneous Modal Adaptive Fusion. Specifically, this paradigm initially employs Bidirectional Agent Cross-Attention (BACA), which feeds both-sensor features, characterized by global receptive fields, to the text features for querying. Moreover, we design a Dynamic Gated Graph Fusion (DGGF) module to locate the regions of interest identified by the queries. To further enhance accuracy, we devise an C3D-RECHead, based on the nearest object edge to the ego-vehicle. Experimental results demonstrate that our TPCNet, along with its individual modules, achieves the state-of-the-art performance on both the Talk2Radar and Talk2Car datasets. We release the code at https://github.com/GuanRunwei/TPCNet.

cs.CV↗

arXiv2025

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models

Text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images but also raise people's concerns about generating harmful or misleading content. While extensive approaches have been proposed to erase unwanted concepts without requiring retraining from scratch, they inadvertently degrade performance on normal generation tasks. In this work, we propose Interpret then Deactivate (ItD), a novel framework to enable precise concept removal in T2I diffusion models while preserving overall performance. ItD first employs a sparse autoencoder (SAE) to interpret each concept as a combination of multiple features. By permanently deactivating the specific features associated with target concepts, we repurpose SAE as a zero-shot classifier that identifies whether the input prompt includes target concepts, allowing selective concept erasure in diffusion models. Moreover, we demonstrate that ItD can be easily extended to erase multiple concepts without requiring further training. Comprehensive experiments across celebrity identities, artistic styles, and explicit content demonstrate ItD's effectiveness in eliminating targeted concepts without interfering with normal concept generation. Additionally, ItD is also robust against adversarial prompts designed to circumvent content filters. Code is available at: https://github.com/NANSirun/Interpret-then-deactivate.

cs.CV↗

arXiv2025

PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation

Existing monocular 3D pose estimation methods primarily rely on joint positional features, while overlooking intrinsic directional and angular correlations within the skeleton. As a result, they often produce implausible poses under joint occlusions or rapid motion changes. To address these challenges, we propose the PoseGRAF framework. We first construct a dual graph convolutional structure that separately processes joint and bone graphs, effectively capturing their local dependencies. A Cross-Attention module is then introduced to model interdependencies between bone directions and joint features. Building upon this, a dynamic fusion module is designed to adaptively integrate both feature types by leveraging the relational dependencies between joints and bones. An improved Transformer encoder is further incorporated in a residual manner to generate the final output. Experimental results on the Human3.6M and MPI-INF-3DHP datasets show that our method exceeds state-of-the-art approaches. Additional evaluations on in-the-wild videos further validate its generalizability. The code is publicly available at https://github.com/iCityLab/PoseGRAF.

cs.CV↗

arXiv2025

A counter example for the Homogeneity Conjecture

We construct a counter example to show that the Homogeneity Conjecture, first proposed by J.A. Wolf in 1962, is not true. To be precise, we prove that on the Lie group Sp(2), there exists a left invariant Riemannian metric and a cyclic subgroup Γ of order (2n+1), such that the left translation of each element of Γ on Sp(2) is a Clifford-Wolf translation, but the Riemannian quotient Γ\Sp(2) is not homogeneous.

math.DG↗

arXiv2025

Towards Next-Generation Intelligent Maintenance: Collaborative Fusion of Large and Small Models

With the rapid advancement of intelligent technologies, collaborative frameworks integrating large and small models have emerged as a promising approach for enhancing industrial maintenance. However, several challenges persist, including limited domain adaptability, insufficient real-time performance and reliability, high integration complexity, and difficulties in knowledge representation and fusion. To address these issues, an intelligent maintenance framework for industrial scenarios is proposed. This framework adopts a five-layer architecture and integrates the precise computational capabilities of domain-specific small models with the cognitive reasoning, knowledge integration, and interactive functionalities of large language models. The objective is to achieve more accurate, intelligent, and efficient maintenance in industrial applications. Two realistic implementations, involving the maintenance of telecommunication equipment rooms and the intelligent servicing of energy storage power stations, demonstrate that the framework significantly enhances maintenance efficiency.

eess.SY↗

arXiv2025

On the Synthetic Channels in Polar Codes over Binary-Input Discrete Memoryless Channels

Polar codes introduced by Arikan in 2009 are the first code family achieving the capacity of binary-input discrete memoryless channels (BIDMCs) with low-complexity encoding and decoding. Identifying unreliable synthetic channels in polar code construction is crucial. Currently, because of the large size of the output alphabets of synthetic channels, there is no effective approach to evaluate their reliability, except in the case that the underlying channels are binary erasure channels. This paper defines equivalence and symmetry based on the likelihood ratio profile of BIDMCs and characterizes symmetric BIDMCs as random switching channels (RSCs) of binary symmetric channels. By converting the generation of synthetic channels in polar code construction into algebraic operations on underlying channels, some compact representations of RSCs for these synthetic channels are derived. Moreover, a lower bound for the average number of elements that possess the same likelihood ratio within the output alphabet of any synthetic channel generated in polar codes is also derived.

cs.IT↗

arXiv2025

Can We Predict Performance of Large Models across Vision-Language Tasks?

Evaluating large vision-language models (LVLMs) is very expensive, due to high computational cost and the wide variety of tasks. The good news is that if we already have some observed performance scores, we may be able to infer unknown ones. In this study, we propose a new framework for predicting unknown performance scores based on observed ones from other LVLMs or tasks. We first formulate the performance prediction as a matrix completion task. Specifically, we construct a sparse performance matrix $\boldsymbol{R}$, where each entry $R_{mn}$ represents the performance score of the $m$-th model on the $n$-th dataset. By applying probabilistic matrix factorization (PMF) with Markov chain Monte Carlo (MCMC), we can complete the performance matrix, i.e., predict unknown scores. Additionally, we estimate the uncertainty of performance prediction based on MCMC. Practitioners can evaluate their models on untested tasks with higher uncertainty first, which quickly reduces the prediction errors. We further introduce several improvements to enhance PMF for scenarios with sparse observed performance scores. Our experiments demonstrate the accuracy of PMF in predicting unknown scores, the reliability of uncertainty estimates in ordering evaluations, and the effectiveness of our enhancements for handling sparse data.

cs.CV↗

arXiv2025

DiSA: Diffusion Step Annealing in Autoregressive Image Generation

An increasing number of autoregressive models, such as MAR, FlowAR, xAR, and Harmon adopt diffusion sampling to improve the quality of image generation. However, this strategy leads to low inference efficiency, because it usually takes 50 to 100 steps for diffusion to sample a token. This paper explores how to effectively address this issue. Our key motivation is that as more tokens are generated during the autoregressive process, subsequent tokens follow more constrained distributions and are easier to sample. To intuitively explain, if a model has generated part of a dog, the remaining tokens must complete the dog and thus are more constrained. Empirical evidence supports our motivation: at later generation stages, the next tokens can be well predicted by a multilayer perceptron, exhibit low variance, and follow closer-to-straight-line denoising paths from noise to tokens. Based on our finding, we introduce diffusion step annealing (DiSA), a training-free method which gradually uses fewer diffusion steps as more tokens are generated, e.g., using 50 steps at the beginning and gradually decreasing to 5 steps at later stages. Because DiSA is derived from our finding specific to diffusion in autoregressive models, it is complementary to existing acceleration methods designed for diffusion alone. DiSA can be implemented in only a few lines of code on existing models, and albeit simple, achieves $5-10\times$ faster inference for MAR and Harmon and $1.4-2.5\times$ for FlowAR and xAR, while maintaining the generation quality.

cs.CV↗

arXiv2025

On the Account Security Risks Posed by Password Strength Meters

Password strength meters (PSMs) have been widely used by websites to gauge password strength, encouraging users to create stronger passwords. Popular data-driven PSMs, e.g., based on Markov, Probabilistic Context-free Grammar (PCFG) and neural networks, alarm strength based on a model learned from real passwords. Despite their proven effectiveness, the secure utility that arises from the leakage of trained passwords remains largely overlooked. To address this gap, we analyze 11 PSMs and find that 5 data-driven meters are vulnerable to membership inference attacks that expose their trained passwords, and seriously, 3 rule-based meters openly disclose their blocked passwords. We specifically design a PSM privacy leakage evaluation approach, and uncover that a series of general data-driven meters are vulnerable to leaking between 10^4 to 10^5 trained passwords, with the PCFG-based models being more vulnerable than other counterparts; furthermore, we aid in deriving insights that the inherent utility-privacy tradeoff is not as severe as previously thought. To further exploit the risks, we develop novel meter-aware attacks when a clever attacker can filter the used passwords during compromising accounts on websites using the meter, and experimentally show that attackers targeting websites that deployed the popular Zxcvbn meter can compromise an additional 5.84% user accounts within 10 attempts, demonstrating the urgent need for privacy-preserving PSMs that protect the confidentiality of the meter's used passwords. Finally, we sketch some counter-measures to mitigate these threats.

cs.CR↗

arXiv2025

Very standard homogeneous Finsler manifolds with positive flag curvature

In this paper, we consider a homogeneous manifold $G/H$ in which $G$ is a compact connected simply connected simple Lie group and $H$ is a closed connected subgroup of $G$. We define standard and very standard homogeneous Finsler metrics on $G/H$, which generalize the standard homogeneous $(α_1,α_2)$ metric in literature. We classify all these $G/H$ which admit positively curved very standard homogeneous Finsler metrics.

math.DG↗

arXiv2025

Nearby open clusters with tidal features: golden sample selection and 3D structure

Open clusters offer unique opportunities to study stellar dynamics and evolution under the influence of their internal gravity, the Milky Way's gravitational field, and the interactions with encounters. Using the Gaia DR3 data for a catalog of open clusters within 500 parsecs that exhibit tidal features reported by the literature, we apply a novel method based on 3D principal component analysis to select a ``golden sample'' of nearby open clusters with minimal line-of-sight distortions. This approach ensures a systematic comparison of 3D and 2D structural parameters for tidally perturbed clusters. The selected golden sample includes Blanco 1, Melotte 20, Melotte 22, NGC 2632, NGC 7092, NGC 1662, Roslund 6 and Melotte 111. We analyze these clusters by fitting both 2D and 3D King Profiles to their stellar density distributions. Our results reveal systematic discrepancies: most of the golden sample clusters exhibit larger 3D tidal radii compared to their 2D counterparts, demonstrating that the 2D projection effects bias the measured cluster size. Furthermore, the 3D density profiles show stronger deviations from King profiles at the tidal radii ($Δρ_{\rm 3D} > Δρ_{\rm 2D}$), highlighting enhanced sensitivity to tidal disturbances. Additionally, we investigate the spatial distribution of cluster members relative to their bulk motion in the Galactic plane. We find that some clusters exhibit tidal features oriented perpendicular to their direction of motion, which can be attributed to the fact that the current surveys only detect the curved inner regions of the tidal features. In conclusion, this work offers a golden sample of nearby open clusters that are most reliable for 3D structure analysis and underscores the necessity of 3D analysis in characterizing OC morphological asymmetries, determining cluster size, and identifying tidal features.

astro-ph.GA↗