arXiv subjects

Jie Wang

Publications and source records attributed to Jie Wang.

At least 307 records · Page 17Linked to original sources

arXiv2024

On Completeness of SDP-Based Barrier Certificate Synthesis over Unbounded Domains

Barrier certificates, serving as differential invariants that witness system safety, play a crucial role in the verification of cyber-physical systems (CPS). Prevailing computational methods for synthesizing barrier certificates are based on semidefinite programming (SDP) by exploiting Putinar Positivstellensatz. Consequently, these approaches are limited by the Archimedean condition, which requires all variables to be bounded, i.e., systems are defined over bounded domains. For systems over unbounded domains, unfortunately, existing methods become incomplete and may fail to identify potential barrier certificates. In this paper, we address this limitation for the unbounded cases. We first give a complete characterization of polynomial barrier certificates by using homogenization, a recent technique in the optimization community to reduce an unbounded optimization problem to a bounded one. Furthermore, motivated by this formulation, we introduce the definition of homogenized systems and propose a complete characterization of a family of non-polynomial barrier certificates with more expressive power. Experimental results demonstrate that our two approaches are more effective while maintaining a comparable level of efficiency.

eess.SY↗

arXiv2024

Estimation of line-of-sight velocities of individual galaxies using neural networks I. Modelling redshift-space distortions at large scales

We present a scheme based on artificial neural networks (ANN) to estimate the line-of-sight velocities of individual galaxies from an observed redshift-space galaxy distribution. We find an estimate of the peculiar velocity at a galaxy based on galaxy counts and barycenters in shells around it. By training the network with environmental characteristics, such as the total mass and mass center within each shell surrounding every galaxy in redshift space, our ANN model can accurately predict the line-of-sight velocity of each individual galaxy. When this velocity is used to eliminate the RSD effect, the two-point correlation function (TPCF) in real space can be recovered with an accuracy better than 1% at $s$ > 8 $h^{-1}\mathrm{Mpc}$, and 4% on all scales compared to ground truth. The real-space power spectrum can be recovered within 3% on $k$< 0.5 $\mathrm{Mpc}^{-1}h$, and less than 5% for all $k$ modes. The quadrupole moment of the TPCF or power spectrum is almost zero down to $s$ = 10 $h^{-1}\mathrm{Mpc}$ or all $k$ modes, indicating an effective correction of the spatial anisotropy caused by the RSD effect. We demonstrate that on large scales, without additional training with new data, our network is adaptable to different galaxy formation models, different cosmological models, and mock galaxy samples at high redshifts and high biases, achieving less than 10% error for scales greater than 15 $h^{-1}\mathrm{Mpc}$. As it is sensitive to large-scale densities, it does not manage to remove Fingers of God in large clusters, but works remarkably well at recovering real-space galaxy positions elsewhere. Our scheme provides a novel way to predict the peculiar velocity of individual galaxies, to eliminate the RSD effect directly in future large galaxy surveys, and to reconstruct the 3-D cosmic velocity field accurately.

astro-ph.CO↗

arXiv2024

Foundations and Frontiers of Graph Learning Theory

Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures. Notably, Graph Neural Networks (GNNs), i.e. neural network architectures designed for learning graph representations, have become a popular paradigm. With these models being usually characterized by intuition-driven design or highly intricate components, placing them within the theoretical analysis framework to distill the core concepts, helps understand the key principles that drive the functionality better and guide further development. Given this surge in interest, this article provides a comprehensive summary of the theoretical foundations and breakthroughs concerning the approximation and learning behaviors intrinsic to prevalent graph learning models. Encompassing discussions on fundamental aspects such as expressiveness power, generalization, optimization, and unique phenomena such as over-smoothing and over-squashing, this piece delves into the theoretical foundations and frontier driving the evolution of graph learning. In addition, this article also presents several challenges and further initiates discussions on possible solutions.

cs.LG↗

arXiv2024

FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge

Speech recognition systems driven by DNNs have revolutionized human-computer interaction through voice interfaces, which significantly facilitate our daily lives. However, the growing popularity of these systems also raises special concerns on their security, particularly regarding backdoor attacks. A backdoor attack inserts one or more hidden backdoors into a DNN model during its training process, such that it does not affect the model's performance on benign inputs, but forces the model to produce an adversary-desired output if a specific trigger is present in the model input. Despite the initial success of current audio backdoor attacks, they suffer from the following limitations: (i) Most of them require sufficient knowledge, which limits their widespread adoption. (ii) They are not stealthy enough, thus easy to be detected by humans. (iii) Most of them cannot attack live speech, reducing their practicality. To address these problems, in this paper, we propose FlowMur, a stealthy and practical audio backdoor attack that can be launched with limited knowledge. FlowMur constructs an auxiliary dataset and a surrogate model to augment adversary knowledge. To achieve dynamicity, it formulates trigger generation as an optimization problem and optimizes the trigger over different attachment positions. To enhance stealthiness, we propose an adaptive data poisoning method according to Signal-to-Noise Ratio (SNR). Furthermore, ambient noise is incorporated into the process of trigger generation and data poisoning to make FlowMur robust to ambient noise and improve its practicality. Extensive experiments conducted on two datasets demonstrate that FlowMur achieves high attack performance in both digital and physical settings while remaining resilient to state-of-the-art defenses. In particular, a human study confirms that triggers generated by FlowMur are not easily detected by participants.

cs.CR↗

arXiv2024

Nonlinear Craig Interpolant Generation over Unbounded Domains by Separating Semialgebraic Sets

Interpolation-based techniques become popular in recent years, as they can improve the scalability of existing verification techniques due to their inherent modularity and local reasoning capabilities. Synthesizing Craig interpolants is the cornerstone of these techniques. In this paper, we investigate nonlinear Craig interpolant synthesis for two polynomial formulas of the general form, essentially corresponding to the underlying mathematical problem to separate two disjoint semialgebraic sets. By combining the homogenization approach with existing techniques, we prove the existence of a novel class of non-polynomial interpolants called semialgebraic interpolants. These semialgebraic interpolants subsume polynomial interpolants as a special case. To the best of our knowledge, this is the first existence result of this kind. Furthermore, we provide complete sum-of-squares characterizations for both polynomial and semialgebraic interpolants, which can be efficiently solved as semidefinite programs. Examples are provided to demonstrate the effectiveness and efficiency of our approach.

cs.LO↗

arXiv2024

DF-SLAM: Dictionary Factors Representation for High-Fidelity Neural Implicit Dense Visual SLAM System

We introduce a high-fidelity neural implicit dense visual Simultaneous Localization and Mapping (SLAM) system, termed DF-SLAM. In our work, we employ dictionary factors for scene representation, encoding the geometry and appearance information of the scene as a combination of basis and coefficient factors. Compared to neural implicit dense visual SLAM methods that directly encode scene information as features, our method exhibits superior scene detail reconstruction capabilities and more efficient memory usage, while our model size is insensitive to the size of the scene map, making our method more suitable for large-scale scenes. Additionally, we employ feature integration rendering to accelerate color rendering speed while ensuring color rendering quality, further enhancing the real-time performance of our neural SLAM method. Extensive experiments on synthetic and real-world datasets demonstrate that our method is competitive with existing state-of-the-art neural implicit SLAM methods in terms of real-time performance, localization accuracy, and scene reconstruction quality. Our source code is available at https://github.com/funcdecl/DF-SLAM.

cs.CV↗

arXiv2024

Revisiting Interpolation Augmentation for Speech-to-Text Generation

Speech-to-text (S2T) generation systems frequently face challenges in low-resource scenarios, primarily due to the lack of extensive labeled datasets. One emerging solution is constructing virtual training samples by interpolating inputs and labels, which has notably enhanced system generalization in other domains. Despite its potential, this technique's application in S2T tasks has remained under-explored. In this paper, we delve into the utility of interpolation augmentation, guided by several pivotal questions. Our findings reveal that employing an appropriate strategy in interpolation augmentation significantly enhances performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.

cs.CL↗

arXiv2024

CodeR: Issue Resolving with Multi-Agent and Task Graphs

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.

cs.CL↗

arXiv2024

A Lightweight Framework for Adaptive Retrieval In Code Completion With Critique Model

Recent advancements in Retrieval-Augmented Generation have significantly enhanced code completion at the repository level. Various RAG-based code completion systems are proposed based on different design choices. For instance, gaining more effectiveness at the cost of repeating the retrieval-generation process multiple times. However, the indiscriminate use of retrieval in current methods reveals issues in both efficiency and effectiveness, as a considerable portion of retrievals are unnecessary and may introduce unhelpful or even harmful suggestions to code language models. To address these challenges, we introduce CARD, a lightweight critique method designed to provide insights into the necessity of retrievals and select the optimal answer from multiple predictions. CARD can seamlessly integrate into any RAG-based code completion system. Our evaluation shows that CARD saves 21% to 46% times of retrieval for Line completion, 14% to 40% times of retrieval for API completion, and 6% to 46.5% times of retrieval for function completion respectively, while improving the accuracy. CARD reduces latency ranging from 16% to 83%. CARD is generalizable to different LMs, retrievers, and programming languages. It is lightweight with training in few seconds and inference in few milliseconds.

cs.SE↗

arXiv2024

FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding

Fine urban change segmentation using multi-temporal remote sensing images is essential for understanding human-environment interactions in urban areas. Although there have been advances in high-quality land cover datasets that reveal the physical features of urban landscapes, the lack of fine-grained land use datasets hinders a deeper understanding of how human activities are distributed across the landscape and the impact of these activities on the environment, thus constraining proper technique development. To address this, we introduce FUSU, the first fine-grained land use change segmentation dataset for Fine-grained Urban Semantic Understanding. FUSU features the most detailed land use classification system to date, with 17 classes and 30 billion pixels of annotations. It includes bi-temporal high-resolution satellite images with 0.2-0.5 m ground sample distance and monthly optical and radar satellite time series, covering 847 km^2 across five urban areas in the southern and northern of China with different geographical features. The fine-grained land use pixel-wise annotations and high spatial-temporal resolution data provide a robust foundation for developing proper deep learning models to provide contextual insights on human activities and urbanization. To fully leverage FUSU, we propose a unified time-series architecture for both change detection and segmentation. We benchmark FUSU on various methods for several tasks. Dataset and code are available at: https://github.com/yuanshuai0914/FUSU.

cs.CV↗

arXiv2024

Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching

Image-text matching (ITM) is a fundamental problem in computer vision. The key issue lies in jointly learning the visual and textual representation to estimate their similarity accurately. Most existing methods focus on feature enhancement within modality or feature interaction across modalities, which, however, neglects the contextual information of the object representation based on the inter-object relationships that match the corresponding sentences with rich contextual semantics. In this paper, we propose a Hybrid-modal Interaction with multiple Relational Enhancements (termed \textit{Hire}) for image-text matching, which correlates the intra- and inter-modal semantics between objects and words with implicit and explicit relationship modelling. In particular, the explicit intra-modal spatial-semantic graph-based reasoning network is designed to improve the contextual representation of visual objects with salient spatial and semantic relational connectivities, guided by the explicit relationships of the objects' spatial positions and their scene graph. We use implicit relationship modelling for potential relationship interactions before explicit modelling to improve the fault tolerance of explicit relationship detection. Then the visual and textual semantic representations are refined jointly via inter-modal interactive attention and cross-modal alignment. To correlate the context of objects with the textual context, we further refine the visual semantic representation via cross-level object-sentence and word-image-based interactive attention. Extensive experiments validate that the proposed hybrid-modal interaction with implicit and explicit modelling is more beneficial for image-text matching. And the proposed \textit{Hire} obtains new state-of-the-art results on MS-COCO and Flickr30K benchmarks.

cs.CV↗

arXiv2024

Lower bound results for conditionally decomposable polytopes

It is possible for a combinatorial type of polytope to have both decomposable and indecomposable realizations; here decomposability is meant with respect to Minkowski addition. Such polytopes are called conditionally decomposable. We show that the minimum number of vertices of a conditionally decomposable $d$-polytope is in the range $[3d-3, 4d-4]$, and that for a polytope having a line segment for a summand, $4d-4$ is sharp. As an application, the exact lower bound of the number of $k$-faces of a decomposable $d$-polytope with $2d+m$ vertices ($2 \le m\le d-4$) is obtained. Concerning the facets, in dimension 4, the minimum number of facets of a conditionally decomposable polytope is 9, and in dimension $d\ge 5$, the minimum is $d+4$.

math.CO↗

arXiv2024

Reliability for Nerve Fiber Layer Reflectance Using Spectral Domain Optical Coherence Tomography

Purpose: Reliability for Nerve Fiber Layer Reflectance Using Spectral Domain Optical Coherence Tomography (OCT) Methods: The study utilized OCT to scan participants with a cubic 6x6 mm disc scan. NFL reflectance were normalized by the average of bands below NFL and summarized. We selected several reference bands, including the pigment epithelium complex (PPEC), the band between NFL and Bruch's membrane (Post-NFL), and the top 50% of pixels with higher values were selected from the Post-NFL band by Post-NFL-Bright. Especially, we also included NFL attenuation coefficient (AC), which was equivalent to NFL reflectance normalized by all pixels below NFL. An experiment was designed to test the NFL reflectance against different levels of attenuation using neutral density filter (NDF). We also evaluated the within-visit and between-visit repeatability using a clinical dataset with normal and glaucoma eyes. Results: The experiment enrolled 20 healthy participants. The clinical dataset selected 22 normal and 55 glaucoma eyes with at least two visits form functional and structural OCT (FSOCT) study. The experiment showed that NFL reflectance normalized PPEC Max and Post-NFL-Bright had lowest dependence, slope=-0.77 and -1.34 dB/optical density on NDF levels, respectively. The clinical data showed that the NFL reflectance metrics normalized by Post-NFL-Bright or Post-NFL-Mean metrics had a trend of better repeatability and reproducibility than others, but the trend was not significant. All metrics demonstrated similar diagnostic accuracy (0.82-0.87), but Post-NFL-Bright provide the best result. Conclusions: The NFL reflectance normalized by the maximum in PPEC had less dependence of the global attenuation followed by Post-NFL-Bright, PPEC/Mean, Post-NFL-Mean and NFL/AC. But NFL reflectance normalized by Post-NFL-Bright had better result in two datasets.

q-bio.QM↗

arXiv2024

ROPO: Robust Preference Optimization for Large Language Models

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data. Recent efforts for this problem either marginally alleviate the impact of noise without the ability to actually reduce its presence, or rely on costly teacher LLMs prone to reward misgeneralization. To address these challenges, we propose the RObust Preference Optimization (ROPO) framework, an iterative alignment approach that integrates noise-tolerance and filtering of noisy samples without the aid of external models. Specifically, ROPO iteratively solves a constrained optimization problem, where we dynamically assign a quality-aware weight for each sample and constrain the sum of the weights to the number of samples we intend to retain. For noise-tolerant training and effective noise identification, we derive a robust loss by suppressing the gradients of samples with high uncertainty. We demonstrate both empirically and theoretically that the derived loss is critical for distinguishing noisy samples from clean ones. Furthermore, inspired by our derived loss, we propose a robustness-guided rejection sampling technique to compensate for the potential important information in discarded queries. Experiments on three widely-used datasets with Mistral-7B and Llama-2-7B demonstrate that ROPO significantly outperforms existing preference alignment methods, with its superiority growing as the noise rate increases.

cs.LG↗

arXiv2024

Length Generalization of Causal Transformers without Position Encoding

Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to overcome the challenge. In this paper, we study the length generalization property of NoPE. We find that although NoPE can extend to longer sequences than the commonly used explicit position encodings, it still has a limited context length. We identify a connection between the failure of NoPE's generalization and the distraction of attention distributions. We propose a parameter-efficient tuning for searching attention heads' best temperature hyper-parameters, which substantially expands NoPE's context size. Experiments on long sequence language modeling, the synthetic passkey retrieval task and real-world long context tasks show that NoPE can achieve competitive performances with state-of-the-art length generalization algorithms. The source code is publicly accessible

cs.CL↗

arXiv2024

Polytopes with low excess degree

We study the existence and structure of $d$-polytopes for which the number $f_1$ of edges is small compared to the number $f_0$ of vertices. Our results are more elegantly expressed in terms of the excess degree of the polytope, defined as $2f_1-df_0$. We show that the excess degree of a $d$-polytope cannot lie in the range $[d+3,2d-7]$, complementing the known result that values in the range $[1,d-3]$ are impossible. In particular, many pairs $(f_0,f_1)$ are not realised by any polytope. For $d$-polytopes with excess degree $d-2$, strong structural results are known; we establish comparable results for excess degrees $d$, $d+2$, and $2d-6$. Frequently, in polytopes with low excess degree, say at most $2d-6$, the nonsimple vertices all have the same degree and they form either a face or a missing face. We show that excess degree $d+1$ is possible only for $d=3,5$, or $7$, complementing the known result that an excess degree $d-1$ is possible only for $d=3$ or $5$.

math.CO↗

arXiv2024

Can Class-Priors Help Single-Positive Multi-Label Learning?

Single-positive multi-label learning (SPMLL) is a typical weakly supervised multi-label learning problem, where each training example is annotated with only one positive label. Existing SPMLL methods typically assign pseudo-labels to unannotated labels with the assumption that prior probabilities of all classes are identical. However, the class-prior of each category may differ significantly in real-world scenarios, which makes the predictive model not perform as well as expected due to the unrealistic assumption on real-world application. To alleviate this issue, a novel framework named {\proposed}, i.e., Class-pRiors Induced Single-Positive multi-label learning, is proposed. Specifically, a class-priors estimator is introduced, which could estimate the class-priors that are theoretically guaranteed to converge to the ground-truth class-priors. In addition, based on the estimated class-priors, an unbiased risk estimator for classification is derived, and the corresponding risk minimizer could be guaranteed to approximately converge to the optimal risk minimizer on fully supervised data. Experimental results on ten MLL benchmark datasets demonstrate the effectiveness and superiority of our method over existing SPMLL approaches.

cs.LG↗

arXiv2024

Theory of Generalized Landau Levels and Implication for non-Abelian States

Quantum geometry is a fundamental concept to characterize the local properties of quantum states. It is recently demonstrated that saturating certain quantum geometric bounds allows a topological Chern band to share many essential features with the lowest Landau level, facilitating fractionalized phases in moiré flat bands. In this work, we systematically extend the consequence and universality of saturated geometric bounds to arbitrary Landau levels by introducing a set of single-particle states, which we term as ``generalized Landau levels''. These generalized Landau levels exhibit exactly quantized values of integrated trace of quantum metric determined by their corresponding Landau level indices, regardless of the nonuniformity of their quantum geometric quantities. We derive all geometric quantities for individual and multiple generalized Landau levels, discuss their relations, and understand them in light of the theory of holomorphic curves and moving frames. We further propose a model by superposing few generalized Landau levels which is supposed to capture a large portion of the single-particle Hilbert space of a generic Chern band analogous to the first Landau level. Using this model, we employ exact diagonalization to identify a single-particle geometric criterion for permitting the non-Abelian Moore-Read phase, which is potentially useful for future engineering of moiré materials and beyond. We use a double twisted bilayer graphene model with only adjacent layer hopping term to show the existence of first generalized Landau level type narrow band and zero-field Moore-Read state at the second magic angle which serves as a promising starting point for more detailed future studies. We expect that generalized Landau levels will serve as a systematic tool for analyzing topological Chern bands and fractionalized phases therein.

cond-mat.mes-hall↗