arXiv subjects

Si Li

Publications and source records attributed to Si Li.

At least 55 records · Page 3Linked to original sources

arXiv2024

L-C4: Language-Based Video Colorization for Creative and Consistent Color

Automatic video colorization is inherently an ill-posed problem because each monochrome frame has multiple optional color candidates. Previous exemplar-based video colorization methods restrict the user's imagination due to the elaborate retrieval process. Alternatively, conditional image colorization methods combined with post-processing algorithms still struggle to maintain temporal consistency. To address these issues, we present Language-based video Colorization for Creative and Consistent Colors (L-C4) to guide the colorization process using user-provided language descriptions. Our model is built upon a pre-trained cross-modality generative model, leveraging its comprehensive language understanding and robust color representation abilities. We introduce the cross-modality pre-fusion module to generate instance-aware text embeddings, enabling the application of creative colors. Additionally, we propose temporally deformable attention to prevent flickering or color shifts, and cross-clip fusion to maintain long-term color consistency. Extensive experimental results demonstrate that L-C4 outperforms relevant methods, achieving semantically accurate colors, unrestricted creative correspondence, and temporally robust consistency.

cs.CV↗

arXiv2024

Smart Audit System Empowered by LLM

Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and reliant on human expertise, posing challenges in maintaining transparency, accountability, and continuous improvement across complex global supply chains. To address these challenges, we propose a smart audit system empowered by large language models (LLMs). Our approach introduces three innovations: a dynamic risk assessment model that streamlines audit procedures and optimizes resource allocation; a manufacturing compliance copilot that enhances data processing, retrieval, and evaluation for a self-evolving manufacturing knowledge base; and a Re-act framework commonality analysis agent that provides real-time, customized analysis to empower engineers with insights for supplier improvement. These enhancements elevate audit efficiency and effectiveness, with testing scenarios demonstrating an improvement of over 24%.

cs.CL↗

arXiv2024

Frequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction

Sparse-view tomographic reconstruction is a pivotal direction for reducing radiation dose and augmenting clinical applicability. While many research works have proposed the reconstruction of tomographic images from sparse 2D projections, existing models tend to excessively focus on high-frequency information while overlooking low-frequency components within the sparse input images. This bias towards high-frequency information often leads to overfitting, particularly intense at edges and boundaries in the reconstructed slices. In this paper, we introduce the Frequency Regularized Neural Attenuation/Activity Field (Freq-NAF) for self-supervised sparse-view tomographic reconstruction. Freq-NAF mitigates overfitting by incorporating frequency regularization, directly controlling the visible frequency bands in the neural network input. This approach effectively balances high-frequency and low-frequency information. We conducted numerical experiments on CBCT and SPECT datasets, and our method demonstrates state-of-the-art accuracy.

eess.IV↗

arXiv2024

On the Hilbert Space of the Chern-Simons Matrix Model, Deformed Double Current Algebra Action, and the Conformal Limit

A Chern-Simons matrix model was proposed by Dorey, Tong, and Turner to describe non-Abelian fractional quantum Hall effect. In this paper we study the Hilbert space of the Chern-Simons matrix model from a geometric quantization point of view. We show that the Hilbert space of the Chern-Simons matrix model can be identified with the space of sections of a line bundle on the quiver variety associated to a framed Jordan quiver. We compute the character of the Hilbert space using localization technique. Using a natural isomorphism between vortex moduli space and a Beilinson-Drinfeld Schubert variety, we prove that the ground states wave functions are flat sections of a bundle of conformal blocks associated to a WZW model. In particular they solve a Knizhnik-Zamolodchikov equation. We show that there exists a natural action of the deformed double current algebra (DDCA) on the Hilbert space, moreover the action is irreducible. We define and study the conformal limit of the Chern-Simons matrix model. We show that the conformal limit of the Hilbert space is an irreducible integrable module of $\widehat{\mathfrak{gl}}(n)$ with level identified with the matrix model level. Moreover, we prove that $\widehat{\mathfrak{gl}}(n)$ generators can be obtained from scaling limits of matrix model operators, which settles a conjecture of Dorey-Tong-Turner. The key to the proof is the construction of a Yangian $Y(\mathfrak{gl}_n)$ action on the conformal limit of the Hilbert space, which we expect to be equivalent to the $Y(\mathfrak{gl}_n)$ action on the integrable $\widehat{\mathfrak{gl}}(n)$ modules constructed by Uglov. We also characterize eigenvectors and eigenvalues of the matrix model Hilbert space with respect to a maximal commutative subalgebra of Yangian.

math-ph↗

arXiv2024

Quantum Algebra of Chern-Simons Matrix Model and Large $N$ Limit

In this paper we study the algebra of quantum observables of the Chern-Simons matrix model which was originally proposed by Susskind and Polychronakos to describe electrons in fractional quantum Hall effects. We establish the commutation relations for its generators and study the large $N$ limit of its representation. We show that the large $N$ limit algebra is isomorphic to the uniform in $N$ algebra studied by Costello, which is isomorphic to the deformed double current algebra studied by Guay. Under appropriate scaling limit, we show that the large $N$ limit algebra degenerates to a Lie algebra which admits a surjective map to the affine Lie algebra of $\mathfrak{u}(p)$. This leads to a complete proof of the large $N$ emergence of the $\mathfrak{u}(p)$ current algebra as proposed by Dorey, Tong and Turner. This also suggests a rigorous derivation of edge excitation of a fractional quantum Hall droplet.

math.QA↗

arXiv2024

TOP:A New Target-Audience Oriented Content Paraphrase Task

Recommendation systems usually recommend the existing contents to different users. However, in comparison to static recommendation methods, a recommendation logic that dynamically adjusts based on user interest preferences may potentially attract a larger user base. Thus, we consider paraphrasing existing content based on the interests of the users to modify the content to better align with the preferences of users. In this paper, we propose a new task named Target-Audience Oriented Content Paraphrase aims to generate more customized contents for the target audience. We introduce the task definition and the corresponding framework for the proposed task and the creation of the corresponding datasets. We utilize the Large Language Models (LLMs) and Large Vision Models (LVMs) to accomplish the base implementation of the TOP framework and provide the referential baseline results for the proposed task.

cs.MM↗

arXiv2024

Topological Quantum Mechanics on Orbifolds and Orbifold Index

In this paper, we study topological quantum mechanical models on symplectic orbifolds. The correlation map gives an explicit orbifold version of quantum HKR map. The exact semi-classical approximation in this model leads to a geometric and quantum field theoretic interpretation of the orbifold algebraic index.

math.QA↗

arXiv2024

Searching for singlet vector-like leptons via pair production at ILC

Vector-like leptons (VLLs) as one kind of the most intriguing particles, have been widely concerned in several extensions of the Standard Model (SM). In this work, we explore the discovery potential of VLLs via pair production in the context of models that satisfy asymptotic safety at the International Linear Collider (ILC). The expected sensitivities of the ILC with the center of mass energy $\sqrt{s} =$ 1 TeV and the integrated luminosity $\mathcal{L}$ = 1 ab$^{-1}$ to the parameter space of this kind of VLL models are derived. The results we obtained show that, for the VLL with mass $M_F$ in the region of $M_{F}\in$ [101GeV, 463GeV], the Yukawa coupling $κ$ can be as low as $κ\in$ [0.032, 0.098].

hep-ph↗

arXiv2024

Doping induced multiferroicity and quantum anomalous Hall effect in $α$-In$_2$Se$_3$ thin films

In flat-band materials, the strong Coulomb interaction between electrons can lead to exotic physical phenomena. Recently, $α$-In$_2$Se$_3$ thin films were found to possess ferroelectricity and flat bands. In this work, using first-principles calculations, we find that for the monolayer, there is a Weyl point at $Γ$ in the flat band, where the inclusion of the spin-orbit coupling opens a gap. Shifting the Fermi level into the spin-orbit gap gives rise to nontrivial band topology, which is preserved for the bilayer regardless of the interlayer polarization couplings. We further calculate the Chern number and edge states for both the monolayer and bilayer, for which the results suggest that they become quantum anomalous Hall insulators under appropriate dopings. Moreover, we find that the doping-induced magnetism for In$_2$Se$_3$ bilayer is strongly dependent on the interlayer polarization coupling. Therefore, doping the flat bands in In$_2$Se$_3$ bilayer can also yield multiferroicity, where the magnetism is electrically tunable as the system transforms between different polarization states. Our study thus reveals that multiferroicity and nontrivial band topology can be unified into one material for designing multifunctional electronic devices.

cond-mat.mtrl-sci↗

arXiv2023

ChatGPT is a Potential Zero-Shot Dependency Parser

Pre-trained language models have been widely used in dependency parsing task and have achieved significant improvements in parser performance. However, it remains an understudied question whether pre-trained language models can spontaneously exhibit the ability of dependency parsing without introducing additional parser structure in the zero-shot scenario. In this paper, we propose to explore the dependency parsing ability of large language models such as ChatGPT and conduct linguistic analysis. The experimental results demonstrate that ChatGPT is a potential zero-shot dependency parser, and the linguistic analysis also shows some unique preferences in parsing outputs.

cs.CL↗

arXiv2023

L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors

Language-based colorization produces plausible and visually pleasing colors under the guidance of user-friendly natural language descriptions. Previous methods implicitly assume that users provide comprehensive color descriptions for most of the objects in the image, which leads to suboptimal performance. In this paper, we propose a unified model to perform language-based colorization with any-level descriptions. We leverage the pretrained cross-modality generative model for its robust language understanding and rich color priors to handle the inherent ambiguity of any-level descriptions. We further design modules to align with input conditions to preserve local spatial structures and prevent the ghosting effect. With the proposed novel sampling strategy, our model achieves instance-aware colorization in diverse and complex scenarios. Extensive experimental results demonstrate our advantages of effectively handling any-level descriptions and outperforming both language-based and automatic colorization methods. The code and pretrained models are available at: https://github.com/changzheng123/L-CAD.

cs.CV↗

arXiv2023

DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction

Most current Event Extraction (EE) methods focus on the high-resource scenario, which requires a large amount of annotated data and can hardly be applied to low-resource domains. To address EE more effectively with limited resources, we propose the Demonstration-enhanced Schema-guided Generation (DemoSG) model, which benefits low-resource EE from two aspects: Firstly, we propose the demonstration-based learning paradigm for EE to fully use the annotated data, which transforms them into demonstrations to illustrate the extraction process and help the model learn effectively. Secondly, we formulate EE as a natural language generation task guided by schema-based prompts, thereby leveraging label semantics and promoting knowledge transfer in low-resource scenarios. We conduct extensive experiments under in-domain and domain adaptation low-resource settings on three datasets, and study the robustness of DemoSG. The results show that DemoSG significantly outperforms current methods in low-resource scenarios.

cs.CL↗

arXiv2023

Type-aware Decoding via Explicitly Aggregating Event Information for Document-level Event Extraction

Document-level event extraction (DEE) faces two main challenges: arguments-scattering and multi-event. Although previous methods attempt to address these challenges, they overlook the interference of event-unrelated sentences during event detection and neglect the mutual interference of different event roles during argument extraction. Therefore, this paper proposes a novel Schema-based Explicitly Aggregating~(SEA) model to address these limitations. SEA aggregates event information into event type and role representations, enabling the decoding of event records based on specific type-aware representations. By detecting each event based on its event type representation, SEA mitigates the interference caused by event-unrelated information. Furthermore, SEA extracts arguments for each role based on its role-aware representations, reducing mutual interference between different roles. Experimental results on the ChFinAnn and DuEE-fin datasets show that SEA outperforms the SOTA methods.

cs.CL↗

arXiv2023

Multiple types of unconventional quasiparticles in the chiral crystal CsBe$_2$F$_5$

Unconventional topological quasiparticles have recently garnered significant attention in the realm of condensed matter physics. Here, based on first-principles calculations and symmetry analysis, we reveal the coexistence of multiple types of interesting unconventional topological quasiparticles in the phonon spectrum of the chiral crystal CsBe$_2$F$_5$. Specifically, we identified eight entangled phonon bands in CsBe$_2$F$_5$, which give rise to various unconventional topological quasiparticles, including the spin-1 Weyl point, the charge-2 Dirac point, the nodal surface, and the hourglass nodal loop. We demonstrate that these unconventional topological quasiparticles are protected by crystal symmetry. We show that there are two large Fermi arcs connecting projections of the bulk spin-1 Weyl point and charge-2 Dirac point on the (001) surface and across the entire surface Brillouin zone. Our work not only elucidates the intriguing topological properties of chiral crystals but also provides an excellent material platform for exploring the fascinating physics associated with multiple types of unconventional topological quasiparticles.

cond-mat.mtrl-sci↗

arXiv2023

Upper bound of a band complex

Band structure for a crystal generally consists of connected components in energy-momentum space, known as band complexes. Here, we explore a fundamental aspect regarding the maximal number of bands that can be accommodated in a single band complex. We show that in principle a band complex can have no finite upper bound for certain space groups. It means infinitely many bands can entangle together, forming a connected pattern stable against symmetry-preserving perturbations. This is demonstrated by our developed inductive construction procedure, through which a given band complex can always be grown into a larger one by gluing a basic building block to it. As a by-product, we demonstrate the existence of arbitrarily large accordion type band structures containing $N_C=4n$ bands, with $n\in\mathbb{N}$.

cond-mat.mtrl-sci↗

arXiv2023

Vertex algebras and quantum master equation

We study the effective Batalin-Vilkovisky quantization theory for chiral deformation of two dimensional conformal field theories. We establish an exact correspondence between renormalized quantum master equations for effective functionals and Maurer-Cartan equations for chiral vertex operators. The generating functions are proven to have modular property with mild holomorphic anomaly. As an application, we construct an exact solution of quantum B-model (BCOV theory) in complex one dimension that solves the higher genus mirror symmetry conjecture on elliptic curves.

math.QA↗

arXiv2023

2D Ladder polyborane: an ideal Dirac semimetal with a multi-feld-tunable band gap

Hydrogen, a simple and magic element, has attracted increasing attention for its effective incorporation within solids and powerful manipulation of electronic states. Here, we show that hydrogenation tackles common problems in two-dimensional borophene, e.g., stability and applicability. As a prominent example, a ladder-like boron hydride sheet, named as 2D ladder polyborane, achieves the desired outcome, enjoying the cleanest scenario with an anisotropic and tilted Dirac cone, that can be fully depicted by a minimal two-band tight-binding model. Introducing external fields, such as an electric field or a circularly-polarized light field can effectively induce distinctive massive Dirac fermions, whereupon four types of multi-field-driven topological domain walls hosting tunable chirality and valley indexes are further established. Moreover, the 2D ladder polyborane is thermodynamically stable at room temperature and supports highly switchable Dirac fermions, providing an ideal platform for realizing and exploring the various multi-field-tunable electronic states.

cond-mat.mes-hall↗

arXiv2023

Regularized Integrals on Elliptic Curves and Holomorphic Anomaly Equations

We derive residue formulas for the regularized integrals (introduced by Li-Zhou) on configuration spaces of elliptic curves. Based on these formulas, we prove that the regularized integrals satisfy holomorphic anomaly equations, providing a mathematical formulation of the so-called contact term singularities. We also discuss residue formulas for the ordered $A$-cycle integrals and establish their relations with those for the regularized integrals.

math.DG↗