arXiv subjects

Han Yan

Publications and source records attributed to Han Yan.

At least 55 records · Page 3Linked to original sources

arXiv2025

Learning to Synthesize Compatible Fashion Items Using Semantic Alignment and Collocation Classification: An Outfit Generation Framework

The field of fashion compatibility learning has attracted great attention from both the academic and industrial communities in recent years. Many studies have been carried out for fashion compatibility prediction, collocated outfit recommendation, artificial intelligence (AI)-enabled compatible fashion design, and related topics. In particular, AI-enabled compatible fashion design can be used to synthesize compatible fashion items or outfits in order to improve the design experience for designers or the efficacy of recommendations for customers. However, previous generative models for collocated fashion synthesis have generally focused on the image-to-image translation between fashion items of upper and lower clothing. In this paper, we propose a novel outfit generation framework, i.e., OutfitGAN, with the aim of synthesizing a set of complementary items to compose an entire outfit, given one extant fashion item and reference masks of target synthesized items. OutfitGAN includes a semantic alignment module, which is responsible for characterizing the mapping correspondence between the existing fashion items and the synthesized ones, to improve the quality of the synthesized images, and a collocation classification module, which is used to improve the compatibility of a synthesized outfit. In order to evaluate the performance of our proposed models, we built a large-scale dataset consisting of 20,000 fashion outfits. Extensive experimental results on this dataset show that our OutfitGAN can synthesize photo-realistic outfits and outperform state-of-the-art methods in terms of similarity, authenticity and compatibility measurements.

cs.LG↗

arXiv2025

BAG: Body-Aligned 3D Wearable Asset Generation

While recent advancements have shown remarkable progress in general 3D shape generation models, the challenge of leveraging these approaches to automatically generate wearable 3D assets remains unexplored. To this end, we present BAG, a Body-aligned Asset Generation method to output 3D wearable asset that can be automatically dressed on given 3D human bodies. This is achived by controlling the 3D generation process using human body shape and pose information. Specifically, we first build a general single-image to consistent multiview image diffusion model, and train it on the large Objaverse dataset to achieve diversity and generalizability. Then we train a Controlnet to guide the multiview generator to produce body-aligned multiview images. The control signal utilizes the multiview 2D projections of the target human body, where pixel values represent the XYZ coordinates of the body surface in a canonical space. The body-conditioned multiview diffusion generates body-aligned multiview images, which are then fed into a native 3D diffusion model to produce the 3D shape of the asset. Finally, by recovering the similarity transformation using multiview silhouette supervision and addressing asset-body penetration with physics simulators, the 3D asset can be accurately fitted onto the target human body. Experimental results demonstrate significant advantages over existing methods in terms of image prompt-following capability, shape diversity, and shape quality. Our project page is available at https://bag-3d.github.io/.

cs.CV↗

arXiv2024

PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image

We present PhyCAGE, the first approach for physically plausible compositional 3D asset generation from a single image. Given an input image, we first generate consistent multi-view images for components of the assets. These images are then fitted with 3D Gaussian Splatting representations. To ensure that the Gaussians representing objects are physically compatible with each other, we introduce a Physical Simulation-Enhanced Score Distillation Sampling (PSE-SDS) technique to further optimize the positions of the Gaussians. It is achieved by setting the gradient of the SDS loss as the initial velocity of the physical simulation, allowing the simulator to act as a physics-guided optimizer that progressively corrects the Gaussians' positions to a physically compatible state. Experimental results demonstrate that the proposed method can generate physically plausible compositional 3D assets given a single image.

cs.CV↗

arXiv2024

Conformal Boundary as Holographic Dual to the Hyperbolic Fracton Model

In addition to describing our universe, gravitational theories profoundly inspire the study of emergent properties of exotic phases of matter. While the Anti-de Sitter/conformal field theory (AdS/CFT) correspondence is one of the most celebrated examples, the field of fractonic matter -- driven in part by gapless phases resembling linearized gravity -- has also seen rapid developments. Despite the deep implications of both areas, connections between them remain sparse, primarily due to the difficulty in constructing explicit models that encapsulate both fields' essential features. Here we demonstrate the efficacy of the recently proposed Hyperbolic Fracton Model as a concrete model for AdS/CFT duality. Using explicit numerical and analytical calculations on the discrete hyperbolic lattice, we show that the boundary state exhibits conformal field theory properties. Our main result is that bulk defects induce an emergent temperature for the boundary state, proportional to the defect perimeter, in quantitative agreement with the expected behaviour of a black hole in AdS spacetime. The Hyperbolic Fracton Model thus emerges as a unique lattice model of holographic principle equipped with a well-defined bulk Hamiltonian, and offers a promising gateway for studying a wide range of holographic phenomena.

cond-mat.str-el↗

arXiv2024

Fractional matter coupled to the emergent gauge field in a quantum spin ice

Electronic spins can form long-range entangled phases of condensed matter named quantum spin liquids. Their existence is conceptualized in models of two- or three-dimensional frustrated magnets that evade symmetry-breaking order down to zero temperature. Quantum spin ice (QSI) is a theoretically well-established example described by an emergent quantum electrodynamics, with excitations behaving like photon and matter quasiparticles. The latter are fractionally charged and equivalent to the `spinons' emerging from coherent phases of singlets in one dimension, where clear experimental proofs of fractionalization exist. However, in frustrated magnets it remains difficult to establish consensual evidence for quantum spin liquid ground states and their fractional excitations. Here, we use backscattering neutron spectroscopy to achieve extremely high resolution of the time-dependent magnetic response of the candidate QSI material Ce$_2$Sn$_2$O$_7$. We find a gapped spectrum featuring a threshold and peaks that match theories for pair production and propagation of fractional matter excitations (spinons) strongly coupled to a background gauge field. The multiple peaks are a specific signature of the $π$-flux phase of QSI, providing spectroscopic evidence for fractionalization in a three-dimensional quantum spin liquid.

cond-mat.str-el↗

arXiv2024

Statistical Inference for Four-Regime Segmented Regression Models

Segmented regression models offer model flexibility and interpretability as compared to the global parametric and the nonparametric models, and yet are challenging in both estimation and inference. We consider a four-regime segmented model for temporally dependent data with segmenting boundaries depending on multivariate covariates with non-diminishing boundary effects. A mixed integer quadratic programming algorithm is formulated to facilitate the least square estimation of the regression and the boundary parameters. The rates of convergence and the asymptotic distributions of the least square estimators are obtained for the regression and the boundary coefficients, respectively. We propose a smoothed regression bootstrap to facilitate inference on the parameters and a model selection procedure to select the most suitable model within the model class with at most four segments. Numerical simulations and a case study on air pollution in Beijing are conducted to demonstrate the proposed approach, which shows that the segmented models with three or four regimes are suitable for the modeling of the meteorological effects on the PM2.5 concentration.

stat.ME↗

arXiv2024

Transfer Learning with General Estimating Equations

We consider statistical inference for parameters defined by general estimating equations under the covariate shift transfer learning. Different from the commonly used density ratio weighting approach, we undertake a set of formulations to make the statistical inference semiparametric efficient with simple inference. It starts with re-constructing the estimation equations to make them Neyman orthogonal, which facilitates more robustness against errors in the estimation of two key nuisance functions, the density ratio and the conditional mean of the moment function. We present a divergence-based method to estimate the density ratio function, which is amenable to machine learning algorithms including the deep learning. To address the challenge that the conditional mean is parametric-dependent, we adopt a nonparametric multiple-imputation strategy that avoids regression at all possible parameter values. With the estimated nuisance functions and the orthogonal estimation equation, the inference for the target parameter is formulated via the empirical likelihood without sample splittings. We show that the proposed estimator attains the semiparametric efficiency bound, and the inference can be conducted with the Wilks' theorem. The proposed method is further evaluated by simulations and an empirical study on a transfer learning inference for ground-level ozone pollution

stat.ME↗

arXiv2024

Zeeman polaritons as a platform for probing Dicke physics in condensed matter

The interaction of an ensemble of two-level atoms and a quantized electromagnetic field, described by the Dicke Hamiltonian, is an extensively studied problem in quantum optics. However, experimental efforts to explore similar physics in condensed matter typically employ bosonic matter modes (e.g., phonons, magnons, and plasmons) that are describable as simple harmonic oscillators, i.e., an infinite ladder of equally spaced energy levels. Here, we examine ultrastrong coupling between a coherent light mode and an ensemble of paramagnetic spins, a finite-multilevel system, in Gd$_3$Ga$_5$O$_{12}$. The electron paramagnetic resonance of Gd$^{3+}$ ions is tuned by a magnetic field into resonance with a Fabry--Pérot cavity mode, resulting in the formation of spin--photon hybrid states, or Zeeman polaritons. We observe that the light--matter coupling strength, measured through the vacuum Rabi splitting, decreases with increasing temperature, which can be explained by the temperature-dependent population difference between the lower and higher-energy states, a trait of a finite-level system. This finding demonstrates that a spin--boson system is more compatible with the Dicke model and has advantages over boson--boson systems for pursuing experimental realizations of phenomena predicted for ultrastrongly coupled light--matter hybrids.

quant-ph↗

arXiv2024

Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane

We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D shape, Frankenstein simultaneously generates multiple separated shapes, each corresponding to a semantically meaningful part. The 3D scene information is encoded in one single tri-plane tensor, from which multiple Singed Distance Function (SDF) fields can be decoded to represent the compositional shapes. During training, an auto-encoder compresses tri-planes into a latent space, and then the denoising diffusion process is employed to approximate the distribution of the compositional scenes. Frankenstein demonstrates promising results in generating room interiors as well as human avatars with automatically separated parts. The generated scenes facilitate many downstream applications, such as part-wise re-texturing, object rearrangement in the room or avatar cloth re-targeting. Our project page is available at: https://wolfball.github.io/frankenstein/.

cs.CV↗

arXiv2024

Experimentally tunable QED in dipolar-octupolar quantum spin ice

We propose a readily achievable experimental setting where an external magnetic field is used to tune the emergent quantum electrodynamics (eQED) of dipolar-octupolar quantum spin ice (DO-QSI). In $U(1)_π$ DO-QSI -- the proposed ground state of QSI candidates Ce$_2$Zr$_2$O$_7$, Ce$_2$Sn$_2$O$_7$ and Ce$_2$Hf$_2$O$_7$ -- we show that the field can be used to control the emergent speed of light (and, consequently, the emergent fine structure constant). Depending on the field's alignment with the crystal, one may induce different speeds for the two polarizations of the emergent photons, in a fascinating analogue of the electro-optic Kerr effect. In $U(1)_0$ DO-QSI -- yet to be uncovered experimentally -- we find a number of unusual field-induced transitions, including a transition between $0$- and $π$-flux QSI phases, as well as phases with frustrated flux configurations. We discuss experimental signatures of these effects in the spinon excitation spectrum, which can be readily accessed for instance in inelastic neutron scattering measurements. Our proposal opens the gate to a plethora of experimentally accessible, engineerable eQED phenomena in the emergent universes of quantum spin ice.

cond-mat.str-el↗

arXiv2024

NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation

3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints. Existing methods often decompose 3D shapes into a sequence of localized components, treating each element in isolation without considering spatial consistency. As a result, these approaches exhibit limited versatility in 3D data representation and shape generation, hindering their ability to generate highly diverse 3D shapes that comply with the specified constraints. In this paper, we introduce a novel spatial-aware 3D shape generation framework that leverages 2D plane representations for enhanced 3D shape modeling. To ensure spatial coherence and reduce memory usage, we incorporate a hybrid shape representation technique that directly learns a continuous signed distance field representation of the 3D shape using orthogonal 2D planes. Additionally, we meticulously enforce spatial correspondences across distinct planes using a transformer-based autoencoder structure, promoting the preservation of spatial relationships in the generated 3D shapes. This yields an algorithm that consistently outperforms state-of-the-art 3D shape generation methods on various tasks, including unconditional shape generation, multi-modal shape completion, single-view reconstruction, and text-to-shape synthesis. Our project page is available at https://weizheliu.github.io/NeuSDFusion/ .

cs.CV↗

arXiv2024

Constraining the stochastic gravitational wave background using the future lunar seismometers

Motivated by the old idea of using the moon as a resonant gravitational-wave (GW) detector, as well as the recent updates in modeling the lunar response to GWs, we re-evaluate the feasibility of using a network of lunar seismometers to constrain the stochastic GW background (SGWB). In particular, using the updated model of the lunar response, we derive the pattern functions for the two polarizations of GW. With these pattern functions, we further calculate the overlap reduction functions for a network of lunar seismometers, where we have relaxed the conventional assumption that lunar seismometers are perfectly leveled to measure only the vertical acceleration. We apply our calculation to two future lunar projects, namely, Chang'e and the Lunar Gravitational-Wave Antenna (LGWA). We find that the two projects could constrain the SGWB to a level of $Ω_{\text{GW}}^{\text{Chang'e}} < 2.4 \times 10^{2}$ and $Ω_{\text{GW}}^{\text{LGWA}} < 2.0 \times 10^{-10}$, respectively, which corresponds to a signal-to-noise ratio of SNR $=3$. These results are better than the constraints placed previously on the SGWB in the mid-frequency band (around $10^{-3}- 10~\text{Hz}$) by various types of experiments.

gr-qc↗

arXiv2024

BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation

We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation. To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.

cs.CV↗

arXiv2024

Magnetic properties of the spiral spin liquid and surrounding phases in the square lattice XY model

Spiral spin liquids possess a subextensively degenerate ground-state manifold, represented by a continuum of energy minima in reciprocal space. Since a small change of the spiral state wavevector requires a global change of the spin configuration in real space, it is a priori unclear how such systems can fluctuate within the degenerate ground state manifold. Only recently it was proposed that momentum vortices are responsible for the liquidity of the spiral phase and that these systems are closely related to an emergent rank-2 U(1) gauge theory [H. Yan and J. Reuther, Phys. Rev. Research 4, 023175 (2022)]. As a consequence of this gauge structure, four-fold pinch-point singularities were found in a generalized spin correlator. In this article, we use classical Monte Carlo and molecular dynamics calculations to embed the previously studied spiral spin liquid into a broader phase diagram of the square lattice XY model. We find a multitude of unusual phases and phase transitions surrounding the spiral spin liquid such as an effective four-state Potts transition into a colinear double-striped phase resulting from the spontaneous breaking of two coupled $\mathbb{Z}_2$ symmetries. Since this phase is stabilized by entropic effects selecting the momenta away from the spiral manifold, it undergoes a re-entrance phenomenon at low temperatures into a nematic spiral phase. We also observe a region of parameters where the phase transition into the spiral spin liquid does not break any symmetries and where the critical exponents do not match those of standard universality classes. We study the importance of momentum vortices in driving this phase transition and discuss the possibility of a Kosterlitz-Thouless transition of momentum vortices. Finally, we explore the regime where the rank-2 U(1) gauge theory is valid by investigating the four-fold pinch point singularities across the phase diagram

cond-mat.str-el↗

arXiv2024

Chiral two-dimensional MoS2 by molecular functionalization as ultra-sensitive detectors for circularly polarized light

Inducing chirality in optically and electronically active materials is interesting for applications in sensing and quantum information transmission. Two-dimensional (2D) transition metal chalcogenides (TMDs) possess excellent electronic and optical properties but are achiral. Here we demonstrate chirality induction in atomically thin layers of 2D MoS2 by functionalization with chiral thiol molecules. Analysis of X-ray absorption near-edge structure and Raman optical activity with circularly polarized excitation suggest chemical and electronic interactions that leads chirality transfer from the molecules to the MoS2. We confirm chirality induction in 2D MoS2 with circular dichroism measurements that show absorption bands at wavelengths of 380-520 nm and 520-600 nm with giant molar ellipticity of 10^8 deg cm2/dmol 2-3 orders of magnitude higher than 3D chiral materials. Phototransistors fabricated from atomically thin chiral MoS2 for detection of circularly polarized light exhibit responsivity of >10^2 A/W and maximum anisotropy g-factor of 1.98 close to the theoretical maximum of 2.0, which indicates that the chiral states of photons are fully distinguishable by the photodetectors. Our results demonstrate that it is possible achieve chirality induction in monolayer MoS2 by molecular functionalization and realise ultra-sensitive detectors for circularly polarized photons.

cond-mat.mtrl-sci↗

arXiv2024

Towards a Consistent Calculation of the Lunar Response to Gravitational Waves

The recent increasing interest in detecting gravitational waves (GWs) by lunar seismic measurement urges us to have a clear understanding of the response of the moon to passing GWs. In this paper, we clarify the relationship between two seemly different response functions which have been derived previously using two different methods, one taking the field-theory approach and the other using the tidal force induced by GWs. We revisit their derivation and prove, by both analytical arguments and numerical calculations, that the two response functions are equivalent. Their apparent difference can be attributed to the choice of different coordinates. Using the correct response function, we calculate the sensitivities (to GWs) of several designed lunar seismometers, and find that the sensitivity curves between $10^{-3}$ and $0.1$ Hz are much flatter than the previous calculations based on normal-mode model. Our results will help clarifying the scientific objectives of lunar GW observation, as well as provide important constraints on the design of lunar GW detectors.

gr-qc↗

arXiv2024

RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments

Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication. Their cost-effectiveness and energy efficiency enable the integration of numerous passive and reflective elements, enabling near-field propagation. In this paper, we tackle the challenges of RIS-aided 3D localization and synchronization in multipath environments, focusing on the near-field of mmWave systems. Specifically, our approach involves formulating a maximum likelihood (ML) estimation problem for the channel parameters. To initiate this process, we leverage a combination of canonical polyadic decomposition (CPD) and orthogonal matching pursuit (OMP) to obtain coarse estimates of the time of arrival (ToA) and angle of departure (AoD) under the far-field approximation. Subsequently, distances are estimated using $l_{1}$-regularization based on a near-field model. Additionally, we introduce a refinement phase employing the spatial alternating generalized expectation maximization (SAGE) algorithm. Finally, a weighted least squares approach is applied to convert channel parameters into position and clock offset estimates. To extend the estimation algorithm to ultra-large (UL) RIS-assisted localization scenarios, it is further enhanced to reduce errors associated with far-field approximations, especially in the presence of significant near-field effects, achieved by narrowing the RIS aperture. Moreover, the Cramér-Rao Bound (CRB) is derived and the RIS phase shifts are optimized to improve the positioning accuracy. Numerical results affirm the efficacy of the proposed estimation algorithm.

eess.SP↗

arXiv2023

Gravitational wave analogues in spin nematics and cold atoms

Many large-scale phenomena in our Universe, such as gravitational waves, are challenging to reproduce in laboratory settings. However, parallels with condensed matter systems can provide alternative routes for experimental accessibility. Here we show how spin nematic phases provide a low-energy avenue for accessing the physics of linearized gravity, and in particular that their Goldstone modes are relativistically-dispersing massless spin-2 excitations, analogous to gravitational waves. We show at the level of the action that the low-energy effective field theory describing a spin nematic is in correspondence with that of linearized gravity. We then explicitly identify a microscopic model of a spin-1 magnet whose excitations in the low energy limit are relativistically dispersing, massless spin-2 Bosons which are in one-to-one correspondence with gravitational waves and, supported by simulation, outline a procedure for directly observing these analogue waves in a cold gas of $^{23}$Na atoms.

cond-mat.str-el↗