arXiv subjects

Rui He

Publications and source records attributed to Rui He.

At least 37 records · Page 2Linked to original sources

arXiv2025

Diffusion-Guided Mask-Consistent Paired Mixing for Endoscopic Image Segmentation

Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when trained as common samples, overlooks the structural benefit of mask conditioning and introduces synthetic-real domain shift. We propose a paired, diffusion-guided paradigm that fuses the strengths of both. For each real image, a synthetic counterpart is generated under the same mask and the pair is used as a controllable input for Mask-Consistent Paired Mixing (MCPMix), which mixes only image appearance while supervision always uses the original hard mask. This produces a continuous family of intermediate samples that smoothly bridges synthetic and real appearances under shared geometry, enlarging diversity without compromising pixel-level semantics. To keep learning aligned with real data, Real-Anchored Learnable Annealing (RLA) adaptively adjusts the mixing strength and the loss weight of mixed samples over training, gradually re-anchoring optimization to real data and mitigating distributional bias. Across Kvasir-SEG, PICCOLO, CVC-ClinicDB, a private NPC-LES cohort, and ISIC 2017, the approach achieves state-of-the-art segmentation performance and consistent gains over baselines. The results show that combining label-preserving mixing with diffusion-driven diversity, together with adaptive re-anchoring, yields robust and generalizable endoscopic segmentation.

cs.CV↗

arXiv2025

Tunable symmetry breaking in a hexagonal-stacked moiré magnet

Symmetry plays a central role in defining magnetic phases, making tunable symmetry breaking across magnetic transitions highly desirable for discovering non-trivial magnetism. Magnetic moiré superlattices, formed by twisting two-dimensional (2D) magnetic crystals, have been theoretically proposed and experimentally explored as platforms for unconventional magnetic states. However, despite recent advances, tuning symmetry breaking in moiré magnetism remains limited, as twisted 2D magnets, such as rhombohedral (R)-stacked twisted CrI_3, largely inherit the magnetic properties and symmetries of their constituent layers. Here, in hexagonal-stacked twisted double bilayer (H-tDB) CrI_3, we demonstrate clear symmetry evolution as the twist angle increases from 180^{\circ} to 190^{\circ}. While the net magnetization remains zero across this twist angle range, the magnetic phase breaks only the three-fold rotational symmetry at 180^{\circ}, but it breaks all of the rotational, mirror, and time-reversal symmetries at intermediate twist angles between 181^{\circ} and 185^{\circ}, and all broken symmetries are recovered at 190^{\circ}. These pronounced symmetry breakings at intermediate twist angles are accompanied by metamagnetic behaviors, evidenced by symmetric double hysteresis loops around zero magnetic field. Together, these results reveal that H-tDB CrI_3 at intermediate twist angles host a distinct moiré magnetic phase, featuring periodic in-plane spin textures with broken rotational, mirror, and time-reversal symmetries, which is markedly different from the out-of-plane layered antiferromagnetism in bilayer CrI_3 and the predominantly out-of-plane moiré magnetism in R-tDB CrI_3. Our work establishes H-stacked CrI_3 moiré magnets as a versatile platform for engineering magnetic properties, including and likely beyond complex spin textures.

cond-mat.mtrl-sci↗

arXiv2025

SPAC: A Python Package for Spatial Single-Cell Analysis of Multiplex Imaging

Multiplexed immunofluorescence microscopy captures detailed measurements of spatially resolved, multiple biomarkers simultaneously, revealing tissue composition and cellular interactions in situ among single cells. The growing scale and dimensional complexity of these datasets demand reproducible, comprehensive and user-friendly computational tools. To address this need, we developed SPAC (SPAtial single-Cell analysis), a Python-based package and a corresponding shiny application within an integrated, modular SPAC ecosystem (Liu et al., 2025) designed specifically for biologists without extensive coding expertise. Following image segmentation and extraction of spatially resolved single-cell data, SPAC streamlines downstream phenotyping and spatial analysis, facilitating characterization of cellular heterogeneity and spatial organization within tissues. Through scalable performance, specialized spatial statistics, highly customizable visualizations, and seamless workflows from dataset to insights, SPAC significantly lowers barriers to sophisticated spatial analyses.

cs.SE↗

arXiv2025

Long-lived Zone-boundary Magnons in an Antiferromagnet

Antiferromagnetic (AFM) insulators exhibit many desirable features for spintronic applications such as fast dynamics in the THz range and robustness to fluctuating external fields. However, large damping typically associated with THz magnons presents a serious challenge for THz magnonic applications. Here, we report long-lived short-wavelength zone boundary magnons in the honeycomb AFM insulator CoTiO3, recently found to host topological magnons. We find that its zone-boundary THz magnons exhibit longer lifetimes than its zone-center magnons. This unusual momentum-dependent long magnon lifetime originates from several factors including the antiferromagnetic order, exchange anisotropy, a finite magnon gap, and magnon band dispersion. Our work suggests that magnon-magnon interaction may not be detrimental to magnon lifetimes and should be included in future searches for topological magnons.

cond-mat.mes-hall↗

arXiv2025

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models

Unrestricted adversarial examples (UAEs), allow the attacker to create non-constrained adversarial examples without given clean samples, posing a severe threat to the safety of deep learning models. Recent works utilize diffusion models to generate UAEs. However, these UAEs often lack naturalness and imperceptibility due to simply optimizing in intermediate latent noises. In light of this, we propose SemDiff, a novel unrestricted adversarial attack that explores the semantic latent space of diffusion models for meaningful attributes, and devises a multi-attributes optimization approach to ensure attack success while maintaining the naturalness and imperceptibility of generated UAEs. We perform extensive experiments on four tasks on three high-resolution datasets, including CelebA-HQ, AFHQ and ImageNet. The results demonstrate that SemDiff outperforms state-of-the-art methods in terms of attack success rate and imperceptibility. The generated UAEs are natural and exhibit semantically meaningful changes, in accord with the attributes' weights. In addition, SemDiff is found capable of evading different defenses, which further validates its effectiveness and threatening.

cs.LG↗

arXiv2025

Dataset Condensation for Recommendation

Training recommendation models on large datasets requires significant time and resources. It is desired to construct concise yet informative datasets for efficient training. Recent advances in dataset condensation show promise in addressing this problem by synthesizing small datasets. However, applying existing methods of dataset condensation to recommendation has limitations: (1) they fail to generate discrete user-item interactions, and (2) they could not preserve users' potential preferences. To address the limitations, we propose a lightweight condensation framework tailored for recommendation (DConRec), focusing on condensing user-item historical interaction sets. Specifically, we model the discrete user-item interactions via a probabilistic approach and design a pre-augmentation module to incorporate the potential preferences of users into the condensed datasets. While the substantial size of datasets leads to costly optimization, we propose a lightweight policy gradient estimation to accelerate the data synthesis. Experimental results on multiple real-world datasets have demonstrated the effectiveness and efficiency of our framework. Besides, we provide a theoretical analysis of the provable convergence of DConRec. Our implementation is available at: https://github.com/JiahaoWuGit/DConRec.

cs.IR↗

arXiv2025

Growth of hexagonal BN crystals by traveling-solvent floating zone

Large, high-purity single-crystals of hexagonal BN (h-BN) are essential for exploiting its many desirable and interesting properties. Here, we demonstrate via X-ray tomography, X-ray diffraction and scanning electron microscopy that h-BN crystals can be grown by traveling-solvent floating-zone (TSFZ). The diameters of grown boules range from 3 - 5 mm with lengths from 2 - 10 mm. Tomography indicates variable grain sizes within the boules, with the largest having areas of $\approx$ 1 mm $\times$ 2 mm and thickness $\approx$ 0.5 mm. Although the boules contain macroscale flux inclusions, the h-BN lattice itself is of high quality for samples grown under optimized conditions. The currently optimized growth procedure employs an Fe flux, moderate N$_2$ pressure ($P_{N2} \approx$ 6 bar), and a growth rate of 0.1 mm/h. Raman spectroscopy for an optimized sample gives an average linewidth of 7.7(2) cm$^{-1}$ for the E$_{\mathrm{2g}}$ intralayer mode at 1365.46(4) cm$^{-1}$ and 1.0(1) cm$^{-1}$ for the E$_{\mathrm{2g}}$ interlayer shear mode at 51.78(9) cm$^{-1}$. The corresponding photoluminescence spectrum shows sharp phonon-assisted free exciton peaks and minimal signal in the energy range corresponding to carbon-related defects ($E$ = 3.9 4.1 eV). Our work demonstrates the viability of growing h-BN by the TSFZ technique, thereby opening a new route towards larger, high-quality crystals and advancing the state of h-BN related research.

cond-mat.mtrl-sci↗

arXiv2025

Normalized Solutions for nonlinear Schrödinger-Poisson equations involving nearly mass-critical exponents

We study the Schrödinger-Poisson-Slater equation \begin{equation*}\left\{\begin{array}{lll} -Δu + λu + \big(|x|^{-1} \ast |u|^{2}\big)u = V(x) u^{ p_{\varepsilon}-1 }, \, \text{ in } \mathbb{R}^{3},\\[2mm] \int_{\mathbb{R}^3}u^2 \,dx= a,\,\, u > 0,\,\, u \in H^{1}(\mathbb{R}^{3}), \end{array} \right. \end{equation*} where $λ$ is a Lagrange multiplier, $V(x)$ is a real-valued potential, $a\in \mathbb{R}_{+}$ is a constant, $ p_{\varepsilon} = \frac{10}{3} \pm \varepsilon$ and $\varepsilon>0$ is a small parameter. In this paper, we prove that it is the positive critical value of the potential $V$ that affects the existence of single-peak solutions for this problem. Furthermore, we prove the local uniqueness of the solutions we construct.

math.AP↗

arXiv2024

A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation

Lesion segmentation on nasal endoscopic images is challenging due to its complex lesion features. Fully-supervised deep learning methods achieve promising performance with pixel-level annotations but impose a significant annotation burden on experts. Although weakly supervised or semi-supervised methods can reduce the labelling burden, their performance is still limited. Some weakly semi-supervised methods employ a novel annotation strategy that labels weak single-point annotations for the entire training set while providing pixel-level annotations for a small subset of the data. However, the relevant weakly semi-supervised methods only mine the limited information of the point itself, while ignoring its label property and surrounding reliable information. This paper proposes a simple yet efficient weakly semi-supervised method called the Point-Neighborhood Learning (PNL) framework. PNL incorporates the surrounding area of the point, referred to as the point-neighborhood, into the learning process. In PNL, we propose a point-neighborhood supervision loss and a pseudo-label scoring mechanism to explicitly guide the model's training. Meanwhile, we proposed a more reliable data augmentation scheme. The proposed method significantly improves performance without increasing the parameters of the segmentation neural network. Extensive experiments on the NPC-LES dataset demonstrate that PNL outperforms existing methods by a significant margin. Additional validation on colonoscopic polyp segmentation datasets confirms the generalizability of the proposed PNL.

cs.CV↗

arXiv2024

Spontaneously formed phonon frequency combs in van der Waals solid CrXTe$_3$ (X=Ge,Si)

Optical phonon engineering through nonlinear effects has been utilized in ultrafast control of material properties. However, nonlinear optical phonons typically exhibit rapid decay due to strong mode-mode couplings, limiting their effectiveness in temperature or frequency sensitive applications. In this study, we report the observation of long-lived nonlinear optical phonons through the spontaneous formation of phonon frequency combs in the van der Waals material CrXTe$_3$ (X=Ge, Si) using high-resolution Raman scattering. Unlike conventional optical phonons, the highest $A_g$ mode in CrGeTe$_3$ splits into equidistant, sharp peaks forming a frequency comb that persists for hundreds of oscillations and survives up to 100K before decaying. These modes correspond to localized oscillations of Ge$_2$Te$_6$ clusters, isolated from Cr hexagons, behaving as independent quantum oscillators. Introducing a cubic nonlinear term to the harmonic oscillator model, we simulate the phonon time evolution and successfully replicate the observed comb structure. Similar frequency comb behavior is observed in CrSiTe$_3$, demonstrating the generalizability of this phenomenon. Our findings reveal that Raman scattering effectively probes high-frequency nonlinear phonon modes, providing new insight into generating long-lived, tunable phonon frequency combs with applications in ultrafast material control and phonon-based technologies.

cond-mat.mes-hall↗

arXiv2024

Trajectory Planning for Autonomous Driving in Unstructured Scenarios Based on Graph Neural Network and Numerical Optimization

In unstructured environments, obstacles are diverse and lack lane markings, making trajectory planning for intelligent vehicles a challenging task. Traditional trajectory planning methods typically involve multiple stages, including path planning, speed planning, and trajectory optimization. These methods require the manual design of numerous parameters for each stage, resulting in significant workload and computational burden. While end-to-end trajectory planning methods are simple and efficient, they often fail to ensure that the trajectory meets vehicle dynamics and obstacle avoidance constraints in unstructured scenarios. Therefore, this paper proposes a novel trajectory planning method based on Graph Neural Networks (GNN) and numerical optimization. The proposed method consists of two stages: (1) initial trajectory prediction using the GNN, (2) trajectory optimization using numerical optimization. First, the graph neural network processes the environment information and predicts a rough trajectory, replacing traditional path and speed planning. This predicted trajectory serves as the initial solution for the numerical optimization stage, which optimizes the trajectory to ensure compliance with vehicle dynamics and obstacle avoidance constraints. We conducted simulation experiments to validate the feasibility of the proposed algorithm and compared it with other mainstream planning algorithms. The results demonstrate that the proposed method simplifies the trajectory planning process and significantly improves planning efficiency.

cs.RO↗

arXiv2024

Large Language Models can be Guided to Evade AI-Generated Text Detection

Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the misuse of LLMs, such as plagiarism and spamming, have led to the development of multiple detectors, including fine-tuned classifiers and statistical methods. In this study, we equip LLMs with prompts, rather than relying on an external paraphraser, to evaluate the vulnerability of these detectors. We propose a novel Substitution-based In-Context example Optimization method (SICO) to automatically construct prompts for evading the detectors. SICO is cost-efficient as it requires only 40 human-written examples and a limited number of LLM inferences to generate a prompt. Moreover, once a task-specific prompt has been constructed, it can be universally used against a wide range of detectors. Extensive experiments across three real-world tasks demonstrate that SICO significantly outperforms the paraphraser baselines and enables GPT-3.5 to successfully evade six detectors, decreasing their AUC by 0.5 on average. Furthermore, a comprehensive human evaluation show that the SICO-generated text achieves human-level readability and task completion rates, while preserving high imperceptibility. Finally, we propose an ensemble approach to enhance the robustness of detectors against SICO attack. The code is publicly available at https://github.com/ColinLu50/Evade-GPT-Detector.

cs.CL↗

arXiv2024

Exciton-activated effective phonon magnetic moment in monolayer MoS2

Optical excitation of chiral phonons plays a vital role in studying the phonon-driven magnetic phenomena in solids. Transition metal dichalcogenides host chiral phonons at high symmetry points of the Brillouin zone, providing an ideal platform to explore the interplay between chiral phonons and valley degree of freedom. Here, we investigate the helicity-resolved magneto-Raman response of monolayer MoS2 and identify a doubly degenerate Brillouin-zone-center chiral phonon mode at ~270 cm-1. Our wavelength- and temperature-dependent measurements show that this chiral phonon is activated through the resonant excitation of A exciton. Under an out-of-plane magnetic field, the chiral phonon exhibits giant Zeeman splitting, which corresponds to an effective magnetic moment of ~2.5mu_B. Moreover, we carry out theoretical calculations based on the morphic effects in nonmagnetic crystals, which reproduce the linear Zeeman splitting and Raman cross-section of the chiral phonon. Our study provides important insights into lifting the chiral phonon degeneracy in an achiral covalent material, paving a new route to excite and control chiral phonons.

cond-mat.mtrl-sci↗

arXiv2023

Dimensionality crossover to 2D vestigial nematicity from 3D zigzag antiferromagnetism in an XY-type honeycomb van der Waals magnet

Fluctuations and disorder effects are substantially enhanced in reduced dimensionalities. While they are mostly considered as the foe for long-range orders, fluctuations and disorders can also stimulate the emergence of novel phases of matter, for example, vestigial orders. Taking 2D magnetism as a platform, existing efforts have been focused on maintaining 2D long-range magnetic orders by suppressing fluctuations, whereas the other side, exploiting fluctuations for realizing new 2D magnetic phases, remains as an uncharted territory. Here, using a combination of NV spin relaxometry, optical spectroscopy, and Monte Carlo simulations, we report, in an XY-type honeycomb magnet NiPS3, the phase transition from the zigzag AFM order in 3D bulk to a new Z3 vestigial Potts-nematicity in 2D few layers. Spin fluctuations are shown to significantly enhance over the GHz-THz range as the layer number of NiPS3 reduces, using the NV spin relaxometry and the optical Raman quasi-elastic scattering. As a result, the Raman signatures of the zigzag AFM for bulk NiPS3, a zone-folded phonon at ~30cm-1 from the broken translational symmetry (PBTS) and a degeneracy lift of two phonons at ~180cm-1 for the broken 3-fold rotational symmetry (PBRS), evolve into the disappearance of PBTS and the survival of PBRS in few-layer NiPS3, with a critical thickness of ~10nm. The optical linear dichroism microscopy images all three nematic domain states in a single few-layer NiPS3 flake. The large-scale Monte Carlo simulations for bilayer NiPS3 model confirms the absence of long-range zigzag AFM order but the formation of the Z3 vestigial Potts-nematic phase, corroborating with the experimental finding. Our results demonstrate the positivity of strong fluctuations in creating new phases of matter after destroying more conventional ones, and offer an unprecedented pathway for developing novel 2D phases.

cond-mat.mtrl-sci↗

arXiv2023

CVPR 2023 Text Guided Video Editing Competition

Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable Diffusion and Imagen, generative AI has improved dramatically on video tasks. But it's hard to evaluate progress in these video tasks because there is no standard benchmark. So, we propose a new dataset for text-guided video editing (TGVE), and we run a competition at CVPR to evaluate models on our TGVE dataset. In this paper we present a retrospective on the competition and describe the winning method. The competition dataset is available at https://sites.google.com/view/loveucvpr23/track4.

cs.CV↗

arXiv2023

No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have used classifier calibration after FL training, but this approach falls short in improving the poor feature representations caused by training-time classifier biases. Resolving the classifier bias dilemma in FL requires a full understanding of the mechanisms behind the classifier. Recent advances in neural collapse have shown that the classifiers and feature prototypes under perfect training scenarios collapse into an optimal structure called simplex equiangular tight frame (ETF). Building on this neural collapse insight, we propose a solution to the FL's classifier bias problem by utilizing a synthetic and fixed ETF classifier during training. The optimal classifier structure enables all clients to learn unified and optimal feature representations even under extremely heterogeneous data. We devise several effective modules to better adapt the ETF structure in FL, achieving both high generalization and personalization. Extensive experiments demonstrate that our method achieves state-of-the-art performances on CIFAR-10, CIFAR-100, and Tiny-ImageNet.

cs.LG↗

arXiv2023

Multi-Domain Learning From Insufficient Annotations

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-shared information extraction and domain-private information preservation, following the shared-private framework (SP models), which offers significant advantages over single-domain learning. However, the limited availability of annotated data in each domain considerably hinders the effectiveness of conventional supervised MDL approaches in real-world applications. In this paper, we introduce a novel method called multi-domain contrastive learning (MDCL) to alleviate the impact of insufficient annotations by capturing both semantic and structural information from both labeled and unlabeled data.Specifically, MDCL comprises two modules: inter-domain semantic alignment and intra-domain contrast. The former aims to align annotated instances of the same semantic category from distinct domains within a shared hidden space, while the latter focuses on learning a cluster structure of unlabeled instances in a private hidden space for each domain. MDCL is readily compatible with many SP models, requiring no additional model parameters and allowing for end-to-end training. Experimental results across five textual and image multi-domain datasets demonstrate that MDCL brings noticeable improvement over various SP models.Furthermore, MDCL can further be employed in multi-domain active learning (MDAL) to achieve a superior initialization, eventually leading to better overall performance.

cs.LG↗

arXiv2023

Revealing intrinsic domains and fluctuations of moiré magnetism by a wide-field quantum microscope

Moiré magnetism featured by stacking engineered atomic registry and lattice interactions has recently emerged as an appealing quantum state of matter at the forefront condensed matter physics research. Nanoscale imaging of moiré magnets is highly desirable and serves as a prerequisite to investigate a broad range of intriguing physics underlying the interplay between topology, electronic correlations, and unconventional nanomagnetism. Here we report spin defect-based wide-field imaging of magnetic domains and spin fluctuations in twisted double trilayer (tDT) chromium triiodide CrI3. We explicitly show that intrinsic moiré domains of opposite magnetizations appear over arrays of moiré supercells in low-twist-angle tDT CrI3. In contrast, spin fluctuations measured in tDT CrI3 manifest little spatial variations on the same mesoscopic length scale due to the dominant driving force of intralayer exchange interaction. Our results enrich the current understanding of exotic magnetic phases sustained by moiré magnetism and highlight the opportunities provided by quantum spin sensors in probing microscopic spin related phenomena on two-dimensional flatland.

cond-mat.mes-hall↗