Searcharxiv⌕ Search

arXiv subjects

Li Guo

Publications and source records attributed to Li Guo.

At least 55 records · Page 3Linked to original sources

Braided dynamical groups, the dynamical Yang-Baxter equation and related structures

We introduce the notion of a braided dynamical group which is a matched pair of dynamical groups satisfying extra conditions. It is shown to give a solution of the dynamical Yang-Baxter equation and at the same time a braided groupoid, thereby integrating the approaches of Andruskiewitsch and Matsumoto-Shimizu respectively that use these two notions to produce quiver-theoretical solutions of the Yang-Baxter equation. We pursue this connection further by relative Rota-Baxter operators on dynamical groups, which give rise to matched pairs of dynamical groups. As the derived structures of relative Rota-Baxter operators on dynamical groups, dynamical post-groups are introduced and are shown to be equivalent to braided dynamical groups. Finally, skew-braces are generalized to dynamical skew-braces as another equivalent notion of braided dynamical groups.

math-ph↗

3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering

With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by leveraging the strengths of foundational models. The framework integrates key components, including multi-modal embedding, cross-modal interaction, and a language model decoder, to process natural language instructions and 3D scene data. This approach facilitates enhanced reasoning and response generation in complex 3D environments. Using the ScanNet 3D scene dataset, along with text annotations from ScanQA and ScanRefer, 3D-MoRe generates 62,000 question-answer (QA) pairs and 73,000 object descriptions across 1,513 scenes. We also employ various data augmentation techniques and implement semantic filtering to ensure high-quality data. Experiments on ScanQA demonstrate that 3D-MoRe significantly outperforms state-of-the-art baselines, with the CIDEr score improving by 2.15\%. Similarly, on ScanRefer, our approach achieves a notable increase in CIDEr@0.5 by 1.84\%, highlighting its effectiveness in both tasks. Our code and generated datasets will be publicly released to benefit the community, and both can be accessed on the https://3D-MoRe.github.io.

cs.CV↗

Generalized splitting of algebras with application to a bialgebra structure of Leibniz algebras induced from averaging Lie bialgebras

The classical notion of splitting a binary quadratic operad $\mathcal{P}$ gives the notion of pre-$\mathcal{P}$-algebras characterized by $\mathcal{O}$-operators, with pre-Lie algebras as a well-known example. Pre-$\mathcal{P}$-algebras give a refinement of the structure of $\mathcal{P}$-algebras and is critical in the Manin triple approach to bialgebras for $\mathcal{P}$-algebras. Motivated by the new types of splitting appeared in recent studies, this paper aims to extend the classical notion of splitting, by relaxing the requirement that the adjoint actions of the pre-$\mathcal{P}$-algebra form a representation of the $\mathcal{P}$-algebra, to allow also linear combinations of the adjoint actions to form a representation. This yields a whole family of type-$M$ pre-structures, parameterized by the coefficient matrix $M$ of the linear combinations. Using the duals of the adjoint actions gives another family of splittings. Similar generalizations are given to the $\mathcal{O}$-operator characterization of the splitting, and to certain conditions on bilinear forms. Furthermore, this general framework is applied to determine the bialgebra structure induced from averaging Lie bialgebras, lifting the well-known fact that an averaging Lie algebra induces a Leibniz algebra to the level of bialgebras. This is achieved by interpreting the desired bialgebra structure for the Leibniz algebra as the one for a special type-$M$ pre-Leibniz algebra for a suitably chosen matrix $M$ in the above family.

math.QA↗

Induced structures of averaging commutative and cocommutative infinitesimal bialgebras via a new splitting of perm algebras

It is well-known that an averaging operator on a commutative associative algebra gives rise to a perm algebra. This paper lifts this process to the level of bialgebras. For this purpose, we first give an infinitesimal bialgebra structure for averaging commutative associative algebras and characterize it by double constructions of averaging Frobenius commutative algebras. To find the bialgebra counterpart of perm algebras that is induced by such averaging bialgebras, we need a new two-part splitting of the multiplication in a perm algebra, which differs from the usual splitting of the perm algebra (into the pre-perm algebra) by the characterized representation. This gives rise to the notion of an averaging-pre-perm algebra, or simply an apre-perm algebra. Furthermore, the notion of special apre-perm algebras which are apre-perm algebras with the second multiplications being commutative is introduced as the underlying algebra structure of perm algebras with nondegenerate symmetric left-invariant bilinear forms. The latter are also the induced structures of symmetric Frobenius commutative algebras with averaging operators. Consequently, a double construction of averaging Frobenius commutative algebra gives rise to a Manin triple of special apre-perm algebras. In terms of bialgebra structures, this means that an averaging commutative and cocommutative infinitesimal bialgebra gives rise to a special apre-perm bialgebra.

math.RA↗

SE and EE Tradeoff in Active STAR-RIS Assisted Systems With Hardware Impairments

This paper investigates the problem of resource efficiency maximization in an active simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted communication system under practical transceiver hardware impairments (HWIs). We aim to obtain an optimal tradeoff between system spectral efficiency (SE) and energy efficiency (EE), by jointly optimizing the base station (BS) transmit beamforming and the active STAR-RIS beamforming. To tackle the challenges in the fractional objective function, we begin by applying the quadratic transformation method to simplify it into a manageable form. An alternating optimization-based algorithm is then developed to iteratively update the BS and STAR-RIS beamforming coefficients. Simulation results demonstrate that the proposed scheme performs better than other baseline schemes in the presence of HWIs. Moreover, the variation of the achievable SE-EE region with different transmit power budgets is analyzed.

eess.SP↗

Joint News, Attention Spillover,and Stock Returns

Analyzing a comprehensive news dataset, we document that joint news coverage triggers attention contagion, causing temporarily inflated valuations for affected stocks. Tracing SEC EDGAR visits from unique IPs, we provide direct evidence of attention spillovers between stocks. Stocks with greater joint news coverage exhibit increased Google search activity, higher contemporaneous returns, and subsequent reversals. Notably, aggregated joint news coverage strongly and negatively predicts future market returns. This relationship holds out-of-sample, persists after controlling for existing predictors and fundamental linkages, and intensifies during periods of heightened uncertainty or significant market frictions. Our findings indicate that attention contagion contributes to marketwide overvaluations.

q-fin.ST↗

Hopf algebras for the shuffle algebra and fractions from multiple zeta values

The algebra of multiple zeta values (MZVs) is encoded as a stuffle (quasi-shuffle) algebra and a shuffle algebra. The MZV stuffle algebra has a natural Hopf algebra structure. This paper equips a Hopf algebra structure to the MZV shuffle algebra. The needed coproduct is defined by a recursion through a family of weight-increasing linear operators. To verify the Hopf algebra axioms, we make use of a family of fractions, called Chen fractions, that have been used to study MZVs and also serve as the function model for the MZV shuffle algebra. Applying natural derivations on functions and working in the context of locality, a locality Hopf algebra structure is established on the linear span of Chen fractions. This locality Hopf algebra is then shown to descend to a Hopf algebra on the MZV shuffle algebra, whose coproduct satisfies the same recursion as the first-defined coproduct. Thus the two coproducts coincide, establishing the needed Hopf algebra axioms on the MZV shuffle algebra.

math.NT↗

Extended Shuffle Product for Multiple Zeta Values

The shuffle algebra on positive integers encodes the usual multiple zeta values (MZVs) (with positive arguments) thanks to the representations of MZVs by iterated Chen integrals of Kontsevich. Together with the quasi-shuffle (stuffle) algebra, it provides the algebraic framework to study relations among MZVs. This paper enlarges the shuffle algebra uniquely to what we call the extended shuffle algebra that encodes convergent multiple zeta series with arbitrary integer arguments, not just the positive ones in the usual case. To achieved this goal, we first replace the Rota-Baxter operator of weight zero (the integral operator) that characterizes the shuffle product by the differential operator which extends the shuffle product to the larger space. We then show that the subspace corresponding to the convergent MZVs with integer arguments becomes a subalgebra under this extended shuffle product. Furthermore, by lifting the extended shuffle algebra to the locality algebra of Chen symbols, we prove that taking summations of fractions from Chen symbols defines an algebra homomorphism from the above subalgebra to the subalgebra of real numbers spanned by convergent multiple zeta series.

math.NT↗

Cross Entropy versus Label Smoothing: A Neural Collapse Perspective

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical framework which characterizes model behavior during the terminal phase of training. We first show empirically that models trained with label smoothing converge faster to neural collapse solutions and attain a stronger level of neural collapse. Additionally, we show that at the same level of NC1, models under label smoothing loss exhibit intensified NC2. These findings provide valuable insights into the performance benefits and enhanced model calibration under label smoothing loss. We then leverage the unconstrained feature model to derive closed-form solutions for the global minimizers for both loss functions and further demonstrate that models under label smoothing have a lower conditioning number and, therefore, theoretically converge faster. Our study, combining empirical evidence and theoretical results, not only provides nuanced insights into the differences between label smoothing and cross-entropy losses, but also serves as an example of how the powerful neural collapse framework can be used to improve our understanding of DNNs.

cs.LG↗

Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations

Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelated to the topology, which can hardly ensure topological features. In this paper, we formulates message passing as a system of hyperbolic partial differential equations (hyperbolic PDEs), constituting a dynamical system that explicitly maps node representations into a particular solution space. This solution space is spanned by a set of eigenvectors describing the topological structure of graphs. Within this system, for any moment in time, a node features can be decomposed into a superposition of the basis of eigenvectors. This not only enhances the interpretability of message passing but also enables the explicit extraction of fundamental characteristics about the topological structure. Furthermore, by solving this system of hyperbolic partial differential equations, we establish a connection with spectral graph neural networks (spectral GNNs), serving as a message passing enhancement paradigm for spectral GNNs.We further introduce polynomials to approximate arbitrary filter functions. Extensive experiments demonstrate that the paradigm of hyperbolic PDEs not only exhibits strong flexibility but also significantly enhances the performance of various spectral GNNs across diverse graph tasks.

cs.LG↗

Graph Wave Networks

Dynamics modeling has been introduced as a novel paradigm in message passing (MP) of graph neural networks (GNNs). Existing methods consider MP between nodes as a heat diffusion process, and leverage heat equation to model the temporal evolution of nodes in the embedding space. However, heat equation can hardly depict the wave nature of graph signals in graph signal processing. Besides, heat equation is essentially a partial differential equation (PDE) involving a first partial derivative of time, whose numerical solution usually has low stability, and leads to inefficient model training. In this paper, we would like to depict more wave details in MP, since graph signals are essentially wave signals that can be seen as a superposition of a series of waves in the form of eigenvector. This motivates us to consider MP as a wave propagation process to capture the temporal evolution of wave signals in the space. Based on wave equation in physics, we innovatively develop a graph wave equation to leverage the wave propagation on graphs. In details, we demonstrate that the graph wave equation can be connected to traditional spectral GNNs, facilitating the design of graph wave networks based on various Laplacians and enhancing the performance of the spectral GNNs. Besides, the graph wave equation is particularly a PDE involving a second partial derivative of time, which has stronger stability on graphs than the heat equation that involves a first partial derivative of time. Additionally, we theoretically prove that the numerical solution derived from the graph wave equation are constantly stable, enabling to significantly enhance model efficiency while ensuring its performance. Extensive experiments show that GWNs achieve SOTA and efficient performance on benchmark datasets, and exhibit outstanding performance in addressing challenging graph problems, such as over-smoothing and heterophily.

cs.LG↗

Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing

Visual Speech Recognition (VSR) transcribes speech by analyzing lip movements. Recently, Large Language Models (LLMs) have been integrated into VSR systems, leading to notable performance improvements. However, the potential of LLMs has not been extensively studied, and how to effectively utilize LLMs in VSR tasks remains unexplored. This paper systematically explores how to better leverage LLMs for VSR tasks and provides three key contributions: (1) Scaling Test: We study how the LLM size affects VSR performance, confirming a scaling law in the VSR task. (2) Context-Aware Decoding: We add contextual text to guide the LLM decoding, improving recognition accuracy. (3) Iterative Polishing: We propose iteratively refining LLM outputs, progressively reducing recognition errors. Extensive experiments demonstrate that by these designs, the great potential of LLMs can be largely harnessed, leading to significant VSR performance improvement.

cs.CV↗

Movable-Element STARS-Assisted Near-Field Wideband Communications

A novel movable-element simultaneously transmitting and reflecting surface (ME-STARS)-assisted near-field wideband communication framework is proposed. In particular, the position of each STARS element can be adjusted to combat the significant wideband beam squint issue in the near field instead of using costly true-time delay components. Four practical ME-STARS element movement modes are proposed, namely region-based (RB), horizontal-based (HB), vertical-based (VB), and diagonal-based (DB) modes. Based on this, a near-field wideband multi-user downlink communication scenario is considered, where a sum rate maximization problem is formulated by jointly optimizing the base station (BS) precoding, ME-STARS beamforming, and element positions. To solve this intractable problem, a two-layer algorithm is developed. For the inner layer, the block coordinate descent optimization framework is utilized to solve the BS precoding and ME-STARS beamforming in an iterative manner. For the outer layer, the particle swarm optimization-based heuristic search method is employed to determine the desired element positions. Numerical results show that:1) the ME-STARSs can effectively address the beam squint for near-field wideband communications compared to conventional STARSs with fixed element positions; 2) the RB mode achieves the most efficient beam squint effect mitigation, while the DB mode achieves the best trade-off between performance gain and hardware overhead; and 3) an increase in the number of ME-STARS elements or BS subcarriers substantially improves the system performance.

eess.SP↗

FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely heavily on task-specific hard labels, limiting their generalization to unseen categories. Recent popular distillation-based prompt learning methods improve generalization by exploiting larger teacher VLMs and unsupervised knowledge transfer, yet their repetitive teacher model online inference sacrifices the inherent training efficiency advantage of prompt learning. In this paper, we propose {\large {\textbf{F}}}aster {\large {\textbf{D}}}istillation-{\large {\textbf{B}}}ased {\large {\textbf{P}}}rompt {\large {\textbf{L}}}earning (\textbf{FDBPL}), which addresses these issues by sharing soft supervision contexts across multiple training stages and implementing accelerated I/O. Furthermore, FDBPL introduces a region-aware prompt learning paradigm with dual positive-negative prompt spaces to fully exploit randomly cropped regions that containing multi-level information. We propose a positive-negative space mutual learning mechanism based on similarity-difference learning, enabling student CLIP models to recognize correct semantics while learning to reject weakly related concepts, thereby improving zero-shot performance. Unlike existing distillation-based prompt learning methods that sacrifice parameter efficiency for generalization, FDBPL maintains dual advantages of parameter efficiency and strong downstream generalization. Comprehensive evaluations across 11 datasets demonstrate superior performance in base-to-new generalization, cross-dataset transfer, and robustness tests, achieving $2.2\times$ faster training speed.

cs.CV↗

Pinching-Antenna Systems (PASS)-enabled Secure Wireless Communications

A novel pinching-antenna systems (PASS)-enabled secure wireless communication framework is proposed. By dynamically adjusting the positions of dielectric particles, namely pinching antennas (PAs), along the waveguides, PASS introduces a novel concept of pinching beamforming to enhance the performance of physical layer security. A fundamental PASS-enabled secure communication system is considered with one legitimate user and one eavesdropper. Both single-waveguide and multiple-waveguide scenarios are studied. 1) For the single-waveguide scenario, the secrecy rate (SR) maximization is formulated to optimize the pinching beamforming. A PA-wise successive tuning (PAST) algorithm is proposed, which ensures constructive signal superposition at the legitimate user while inducing a destructive legitimate signal at the eavesdropper. 2) For the multiple-waveguide scenario, artificial noise (AN) is employed to further improve secrecy performance. A pair of practical transmission architectures are developed: waveguide division (WD) and waveguide multiplexing (WM). The key difference lies in whether each waveguide carries a single type of signal or a mixture of signals with baseband beamforming. For the SR maximization problem under the WD case, a two-stage algorithm is developed, where the pinching beamforming is designed with the PAST algorithm and the baseband power allocation among AN and legitimate signals is solved using successive convex approximation (SCA). For the WM case, an alternating optimization algorithm is developed, where the baseband beamforming is optimized with SCA and the pinching beamforming is designed employing particle swarm optimization.

eess.SP↗

CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation

Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image recognition performance on associated datasets, often neglecting the crucial aspect of the transferability of learned representations. In this paper, we propose Category-Aware Embedding Data-Free Knowledge Distillation (CAE-DFKD), which addresses at the embedding level the limitations of previous rely on image-level methods to improve model generalization but fail when directly applied to DFKD. The superiority and flexibility of CAE-DFKD are extensively evaluated, including: \textit{\textbf{i.)}} Significant efficiency advantages resulting from altering the generator training paradigm; \textit{\textbf{ii.)}} Competitive performance with existing DFKD state-of-the-art methods on image recognition tasks; \textit{\textbf{iii.)}} Remarkable transferability of data-free learned representations demonstrated in downstream tasks.

cs.CV↗

Advances in Embodied Navigation Using Large Language Models: A Survey

In recent years, the rapid advancement of Large Language Models (LLMs) such as the Generative Pre-trained Transformer (GPT) has attracted increasing attention due to their potential in a variety of practical applications. The application of LLMs with Embodied Intelligence has emerged as a significant area of focus. Among the myriad applications of LLMs, navigation tasks are particularly noteworthy because they demand a deep understanding of the environment and quick, accurate decision-making. LLMs can augment embodied intelligence systems with sophisticated environmental perception and decision-making support, leveraging their robust language and image-processing capabilities. This article offers an exhaustive summary of the symbiosis between LLMs and embodied intelligence with a focus on navigation. It reviews state-of-the-art models, research methodologies, and assesses the advantages and disadvantages of existing embodied navigation models and datasets. Finally, the article elucidates the role of LLMs in embodied intelligence, based on current research, and forecasts future directions in the field. A comprehensive list of studies in this survey is available at https://github.com/Rongtao-Xu/Awesome-LLM-EN.

cs.AI↗

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. Code and models are available at https://github.com/chenshunpeng/FoL

cs.CV↗