arXiv subjects

Wenhui Li

Publications and source records attributed to Wenhui Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Magnetic Bloch States at Integer Flux Quanta Induced by Super-moiré Potential in Graphene Aligned with Twisted Boron Nitride

Two-dimensional electron systems in both magnetic fields and periodic potentials are described by Hofstadter butterfly, a fundamental problem of solid-state physics. While moiré systems provide a powerful method to realize this spectrum, previous experiments, however, have been limited to fractional flux quanta regime due to the difficulty of building ~ 50 nm periodic modulations. Here, we demonstrate a super-moiré strategy to overcome this challenge. By aligning monolayer graphene (G) with 1.0° twisted hexagonal boron nitride (t-hBN), a 63.2 nm bichromatic G/t-hBN super-moiré is constructed, made possible by exploiting the electrostatic nature of t-hBN potential. Under magnetic field B, magnetic Bloch states at integer flux quanta (1-9) are achieved and observed as integer Brown-Zak oscillations, expanding the flux quanta from factions to integers. Theoretical analysis reproduces these experimental findings. This work opens new avenues to study unexplored Hofstadter butterfly, explore emergent topological order at integer flux quanta and engineer long-wavelength periodic modulations.

cond-mat.mes-hall↗

arXiv2024

Highly anisotropic Drude-weight-reduction and enhanced linear-dichroism in van der Waals Weyl semimetal Td-MoTe2 with coherent interlayer electronic transport

Weyl semimetal (WSM) states can be achieved by breaking spatial-inversion symmetry or time reversal symmetry. However, the anisotropy of the energy reduction contributing to the emergence of WSM states has seldom been investigated by experiments. A van der Waals metal MoTe2 exhibits a type-II WSM phase below the monoclinic-to-orthorhombic-phase-transition temperature Tc ~ 250 K. Here, we report a combined linearly-polarized optical-spectroscopy and electrical-transport study of MoTe2 at different temperatures. The Drude components in the a-axis, b-axis and c-axis optical conductivity spectra, together with the metallic out-of-plane and in-plane electrical resistivities, indicate the coherent inter-layer and in-plane charge transports. Moreover, the Drude weight in σ1a(ω), rather than the Drude weights in σ1b(ω) and σ1c(ω), decreases dramatically below Tc, which exhibits a highly anisotropic decrease in its Drude weight and thus suggests a strongly anisotropic reduction of the electronic kinetic energy in the WSM phase. Furthermore, below Tc, due to the in-plane anisotropic spectral-weight transfer from Drude component to high-energy region, the in-plane inter-band-absorption anisotropy increases remarkably around 770 meV, and has the largest value (~ 0.68) of normalized linear dichroism among the reported type-II WSMs. Our work sheds light on seeking new WSMs and developing novel photonic devices based on WSMs.

cond-mat.mtrl-sci↗

arXiv2024

Gate-controlled superconducting switch in GaSe/NbSe$_2$ van der Waals heterostructure

The demand for low-power devices is on the rise as semiconductor engineering approaches the quantum limit and quantum computing continues to advance. Two-dimensional (2D) superconductors, thanks to their rich physical properties, hold significant promise for both fundamental physics and potential applications in superconducting integrated circuits and quantum computation. Here, we report a gate-controlled superconducting switch in GaSe/NbSe$_2$ van der Waals (vdW) heterostructure. By injecting high-energy electrons into NbSe$_2$ under an electric field, a non-equilibrium state is induced, resulting in significant modulation of the superconducting properties. Owing to the intrinsic polarization of ferroelectric GaSe, a much steeper subthreshold slope and asymmetric modulation are achieved, which is beneficial to the device performance. Based on these results, a superconducting switch is realized that can reversibly and controllably switch between the superconducting and normal state under an electric field. Our findings highlight a significant high-energy injection effect from band engineering in 2D vdW heterostructures combining superconductors and ferroelectric semiconductors, and demonstrate the potential applications for superconducting integrated circuits.

cond-mat.supr-con↗

arXiv2024

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey

Recently, the text-to-image diffusion model has gained considerable attention from the community due to its exceptional image generation capability. A representative model, Stable Diffusion, amassed more than 10 million users within just two months of its release. This surge in popularity has facilitated studies on the robustness and safety of the model, leading to the proposal of various adversarial attack methods. Simultaneously, there has been a marked increase in research focused on defense methods to improve the robustness and safety of these models. In this survey, we provide a comprehensive review of the literature on adversarial attacks and defenses targeting text-to-image diffusion models. We begin with an overview of text-to-image diffusion models, followed by an introduction to a taxonomy of adversarial attacks and an in-depth review of existing attack methods. We then present a detailed analysis of current defense methods that improve model robustness and safety. Finally, we discuss ongoing challenges and explore promising future research directions. For a complete list of the adversarial attack and defense methods covered in this survey, please refer to our curated repository at https://github.com/datar001/Awesome-AD-on-T2IDM.

cs.CR↗

arXiv2024

MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition

Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on the vision side by identifying views with high prediction confidence from multiple rendered views of a 3D shape. On the textual side, the strategy of hierarchical prompts is proposed for the first time. The first layer prompts several classification candidates with traditional class-level descriptions, while the second layer refines the prediction based on function-level descriptions or further distinctions between the candidates. Remarkably, without the need for additional training, our proposed method achieves impressive zero-shot 3D classification accuracies of 84.44%, 91.51%, and 66.17% on ModelNet40, ModelNet10, and ShapeNet Core55, respectively. Furthermore, we will make the code publicly available to facilitate reproducibility and further research in this area.

cs.CV↗

arXiv2024

PRG: Prompt-Based Distillation Without Annotation via Proxy Relational Graph

In this paper, we propose a new distillation method for extracting knowledge from Large Foundation Models (LFM) into lightweight models, introducing a novel supervision mode that does not require manually annotated data. While LFMs exhibit exceptional zero-shot classification abilities across datasets, relying solely on LFM-generated embeddings for distillation poses two main challenges: LFM's task-irrelevant knowledge and the high density of features. The transfer of task-irrelevant knowledge could compromise the student model's discriminative capabilities, and the high density of features within target domains obstructs the extraction of discriminative knowledge essential for the task. To address this issue, we introduce the Proxy Relational Graph (PRG) method. We initially extract task-relevant knowledge from LFMs by calculating a weighted average of logits obtained through text prompt embeddings. Then we construct sample-class proxy graphs for LFM and student models, respectively, to model the correlation between samples and class proxies. Then, we achieve the distillation of selective knowledge by aligning the relational graphs produced by both the LFM and the student model. Specifically, the distillation from LFM to the student model is achieved through two types of alignment: 1) aligning the sample nodes produced by the student model with those produced by the LFM, and 2) aligning the edge relationships in the student model's graph with those in the LFM's graph. Our experimental results validate the effectiveness of PRG, demonstrating its ability to leverage the extensive knowledge base of LFMs while skillfully circumventing their inherent limitations in focused learning scenarios. Notably, in our annotation-free framework, PRG achieves an accuracy of 76.23\% (T: 77.9\%) on CIFAR-100 and 72.44\% (T: 75.3\%) on the ImageNet-1K.

cs.CV↗

arXiv2024

Towards Deconfounded Image-Text Matching with Causal Inference

Prior image-text matching methods have shown remarkable performance on many benchmark datasets, but most of them overlook the bias in the dataset, which exists in intra-modal and inter-modal, and tend to learn the spurious correlations that extremely degrade the generalization ability of the model. Furthermore, these methods often incorporate biased external knowledge from large-scale datasets as prior knowledge into image-text matching model, which is inevitable to force model further learn biased associations. To address above limitations, this paper firstly utilizes Structural Causal Models (SCMs) to illustrate how intra- and inter-modal confounders damage the image-text matching. Then, we employ backdoor adjustment to propose an innovative Deconfounded Causal Inference Network (DCIN) for image-text matching task. DCIN (1) decomposes the intra- and inter-modal confounders and incorporates them into the encoding stage of visual and textual features, effectively eliminating the spurious correlations during image-text matching, and (2) uses causal inference to mitigate biases of external knowledge. Consequently, the model can learn causality instead of spurious correlations caused by dataset bias. Extensive experiments on two well-known benchmark datasets, i.e., Flickr30K and MSCOCO, demonstrate the superiority of our proposed method.

cs.CV↗

arXiv2024

Spatially Dependent in-Gap States Induced by Andreev Tunneling through a Single Electronic State

By using low-temperature scanning tunneling microscopy and spectroscopy (STM/STS), we observe in-gap states induced by Andreev tunneling through a single impurity state in a low carrier density superconductor (NaAlSi). The energy-symmetric in-gap states appear when the impurity state is located within the superconducting gap. In-gap states can cross the Fermi level, and they show X-shaped spatial variation. We interpret the in-gap states as a consequence of the Andreev tunneling through the impurity state, which involves the formation or breakup of a Cooper pair. Due to the low carrier density in NaAlSi, the in-gap state is tunable by controlling the STM tip-sample distance. Under strong external magnetic fields, the impurity state shows Zeeman splitting when it is located near the Fermi level. Our findings not only demonstrate the Andreev tunneling involving single electronic state, but also provide new insights for understanding the spatially-dependent in-gap states in low carrier density superconductors.

cond-mat.supr-con↗

arXiv2023

Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation

Existing methods of cross-modal domain adaptation for 3D semantic segmentation predict results only via 2D-3D complementarity that is obtained by cross-modal feature matching. However, as lacking supervision in the target domain, the complementarity is not always reliable. The results are not ideal when the domain gap is large. To solve the problem of lacking supervision, we introduce masked modeling into this task and propose a method Mx2M, which utilizes masked cross-modality modeling to reduce the large domain gap. Our Mx2M contains two components. One is the core solution, cross-modal removal and prediction (xMRP), which makes the Mx2M adapt to various scenarios and provides cross-modal self-supervision. The other is a new way of cross-modal feature matching, the dynamic cross-modal filter (DxMF) that ensures the whole method dynamically uses more suitable 2D-3D complementarity. Evaluation of the Mx2M on three DA scenarios, including Day/Night, USA/Singapore, and A2D2/SemanticKITTI, brings large improvements over previous methods on many metrics.

cs.CV↗

arXiv2023

Fast Single-shot Imaging of Individual Ions via Homodyne Detection of Rydberg-Blockade-Induced Absorption

We introduce well-separated $^{87}$Rb$^+$ ions into an atomic ensemble by microwave ionization of Rydberg excitations and realize single-shot imaging of the individual ions with an exposure time of 1 $μ$s. This imaging sensitivity is reached by using homodyne detection of ion-Rydberg-atom interaction induced absorption. We obtain an ion detection fidelity of (80 $\pm$ 5)\% from analyzing the absorption spots in acquired single-shot images. These \textit{in situ} images provide a direct visualization of the ion-Rydberg interaction blockade and reveal clear spatial correlations between Rydberg excitations. The capability of imaging individual ions in a single shot is of interest for investigating collisional dynamics in hybrid ion-atom systems and for exploring ions as a probe for measurements of quantum gases.

physics.atom-ph↗

arXiv2023

Ion Imaging via Long-Range Interaction with Rydberg Atoms

We demonstrate imaging of ions in an atomic gas with ion-Rydberg atom interaction induced absorption. This is made possible by utilizing a multi-photon electromagnetically induced transparency (EIT) scheme and the extremely large electric polarizability of a Rydberg state with high orbital angular momentum. We process the acquired images to obtain the distribution of ion clouds and to spectroscopically investigate the effect of the ions on the EIT resonance. Furthermore, we show that our method can be employed to image the dynamics of ions in a time resolved way. As an example, we map out the avalanche ionization of a gas of Rydberg atoms. The minimal disruption and the flexibility offered by this imaging technique make it ideally suited for the investigation of cold hybrid ion-atom systems.

physics.atom-ph↗

arXiv2022

Telecom-wavelength spectra of a Rydberg state in a hot vapor

We study telecom-wavelength spectra of a Rydberg state in an atomic vapor with a three-photon excitation scheme. Two lasers of 780 nm and 776 nm are used to pump Rubidium-85 atoms in a vapor cell to the $5D_{\mathrm{5/2}}$ state, from which a probe beam of 1292 nm in the O-band telecommunication wavelength drives a transition to the $21F_{\mathrm{7/2}}$ Rydberg state. We investigate the probe spectra over the power of pump lasers. The simulation based on a 4-level theoretical model captures the main features of the experimental results. This spectroscopic study paves the way for future experiments of making a direct link between fiber optics and radio transmission via Rydberg atoms.

physics.atom-ph↗

arXiv2021

Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory

This paper considers deep visual recognition on long-tailed data. To be general, we consider two applied scenarios, \ie, deep classification and deep metric learning. Under the long-tailed data distribution, the majority classes (\ie, tail classes) only occupy relatively few samples and are prone to lack of within-class diversity. A radical solution is to augment the tail classes with higher diversity. To this end, we introduce a simple and reliable method named Memory-based Jitter (MBJ). We observe that during training, the deep model constantly changes its parameters after every iteration, yielding the phenomenon of \emph{weight jitters}. Consequentially, given a same image as the input, two historical editions of the model generate two different features in the deeply-embedded space, resulting in \emph{feature jitters}. Using a memory bank, we collect these (model or feature) jitters across multiple training iterations and get the so-called Memory-based Jitter. The accumulated jitters enhance the within-class diversity for the tail classes and consequentially improves long-tailed visual recognition. With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i.e.}, deep image classification and deep metric learning (on long-tailed data). Extensive experiments on five long-tailed classification benchmarks and two deep metric learning benchmarks demonstrate significant improvement. Moreover, the achieved performance are on par with the state of the art on both tasks.

cs.CV↗

arXiv2021

On Skew Convolutional and Trellis Codes

Two new classes of skew codes over a finite field $\F$ are proposed, called skew convolutional codes and skew trellis codes. These two classes are defined by, respectively, left or right sub-modules over the skew fields of fractions of skew polynomials over $\F$. The skew convolutional codes can be represented as periodic time-varying ordinary convolutional codes. The skew trellis codes are in general nonlinear over $\F$. Every code from both classes has a code trellis and can be decoded by Viterbi or BCJR algorithms.

cs.IT↗

arXiv2020

Directional THz generation in hot Rb vapor excited to a Rydberg state

We optically excite $^{85}$Rb atoms in a heated vapor cell to a low-lying Rydberg state 10D$_{5/2}$ and observe directional terahertz (THz) beams at 3.3 THz and 7.8 THz. These THz fields are generated by amplified spontaneous emission from the 10D$_{5/2}$ state to the 11P$_{3/2}$ and 8F$_{7/2}$ states, respectively. In addition, we observe ultraviolet (UV) light produced by four-wave mixing of optical pump lasers and the 3.3 THz field. We characterize the generated THz power over the detuning and power of pump lasers, and identify experimental conditions favoring THz and UV generation, respectively. Our scheme paves a new pathway towards generating high-power narrow-band THz radiation.

physics.atom-ph↗

arXiv2020

Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial span, while the tail classes have significantly small spatial span, due to the lack of intra-class diversity. This uneven distribution between head and tail classes distorts the overall feature space, which compromises the discriminative ability of the learned features. Intuitively, we seek to expand the distribution of the tail classes by transferring from the head classes, so as to alleviate the distortion of the feature space. To this end, we propose to construct each feature into a "feature cloud". If a sample belongs to a tail class, the corresponding feature cloud will have relatively large distribution range, in compensation to its lack of diversity. It allows each tail sample to push the samples from other classes far away, recovering the intra-class diversity of tail classes. Extensive experimental evaluations on person re-identification and face recognition tasks confirm the effectiveness of our method.

cs.CV↗

arXiv2019

Collimated UV light generation by two-photon excitation to a Rydberg state in Rb vapor

We use two continuous-wave (CW) laser beams of 780 nm and 515 nm to optically drive $^{85}$Rb atoms in a heated vapor cell to a low-lying Rydberg state 10D$_{5/2}$. We observe a collimated ultraviolet (UV) beam at 311 nm, corresponding to the transition frequency from the 11P$_{3/2}$ state to the 5S$_{1/2}$ state. This indicates the presence of a coherent four-wave mixing process, built up by two input laser fields as well as a terahertz (THz) radiation of 3.28 THz that is generated by amplified spontaneous emission between the 10D$_{5/2}$ and the 11P$_{3/2}$ states. We characterize the 311 nm UV light generation and its dependence on various physical parameters. This scheme could open up a new possibility for generating narrow-band THz waves as well as deep UV radiation.

physics.atom-ph↗

arXiv2018

Efficient microwave-to-optical conversion using Rydberg atoms

We demonstrate microwave-to-optical conversion using six-wave mixing in $^{87}$Rb atoms where the microwave field couples to two atomic Rydberg states, and propagates collinearly with the converted optical field. We achieve a photon conversion efficiency of ~5% in the linear regime of the converter. In addition, we theoretically investigate all-resonant six-wave mixing and outline a realistic experimental scheme for reaching efficiencies greater than 60%.

physics.atom-ph↗