Searcharxiv⌕ Search

arXiv subjects

Zhenyu Sun

Publications and source records attributed to Zhenyu Sun.

At least 19 recordsLinked to original sources
arXiv2026

CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-Centric 3D Scene Generation

Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantically aligned visual content, as well as the construction of accurate geometric structures. In this paper, we propose CGGS, a text-to-3D framework aiming to enhance 3D-content-awareness and address geometric distortions in ego-centric scene generation. Firstly, the Ego-centric Generator is proposed by fine-tuning a Multi-View Latent Diffusion Model with consistency-augmented loss to generate consistent, high-fidelity 2D content aligned with textual descriptions. Then, Layout Decorator leverages optical flow and point-track correspondence to estimate depth, therefore producing dense point clouds as coarse layouts from the ego-centric 2D priors. Building on this initialization, Geometric Refiner is proposed to enhance 3D Gaussian reconstruction via an entropy-based Mutual Information Depth Loss (MID) combined with a hierarchical optimization scheme for improving visual quality and geometric structure. Comprehensive experiments demonstrate that CGGS outperforms previous methods in generating coherent and accurate text-driven 3D scenes.

cs.GR↗
arXiv2026

In-Context Reward Adaptation for Robust Preference Modeling

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model often lacks the robustness required to generalize to unseen preference domains. While existing multi-reward frameworks attempt to address this, they are often restricted to a fixed set of known domains and fail to adapt to unseen human distributions without costly retraining. In this work, we propose In-Context Reward Adaptation, a transformer-based framework designed to model diverse and unseen human preferences on the fly. By leveraging the in-context learning capabilities of transformers, our approach adaptively infers the underlying reward structure from a small set of preference demonstrations. We demonstrate that while a standard transformer architecture is insufficient for this task by characterizing an asymptotic bias to the ground-truth, incorporating human response time as an auxiliary input signal enables the model to successfully adapt to preferences from previously unseen domains. Our findings show that this approach provides a more robust foundation for preference modeling, allowing for the representation of heterogeneous rewards and preference distribution shift, and offering a scalable path toward more flexible human-AI alignment.

cs.LG↗
arXiv2026

EAPFusion: Intrinsic Evolving Auxiliary Prior Guidance for Infrared and Visible Image Fusion

Infrared-visible image fusion aims to create an information-rich fused image by integrating the complementary thermal saliency from infrared sensing and fine textures from visible imaging. Such accurate fusion is essential for real-world perception applications in complex scenes, including nighttime autonomous driving, search and rescue, and surveillance, and can further benefit downstream tasks such as semantic segmentation. However, most existing fusion methods rely upon static trained weights that cannot adapt to scene-specific content at inference time, and often suffer from a granularity mismatch when coarse auxiliary semantics are injected, which makes it difficult to simultaneously highlight targets and preserve details. In this work, we propose EAPFusion to address these issues by using self-evolving intrinsic priors instead of relying on external auxiliary models. Concretely, EAPFusion maintains a compact set of intrinsic priors and progressively updates them across scales. These evolved priors are utilized to dynamically generate convolutional kernels, shifting the paradigm from fixed, pre-trained filters to instance-adaptive parameters via prior-conditioned dynamic convolution. Furthermore, we design a channel-level fusion module that shuffles and interleaves infrared and visible channels, applying local channel mixing to boost cross-modal complementarity. Experiments on different datasets, including cross-dataset evaluation and semantic segmentation, show that the proposed method achieves state-of-the-art quantitative and qualitative fusion results, and consistently boosts downstream performance. Code is coming soon.

cs.CV↗
arXiv2026

Continuously tunable dipolar exciton geometry for controlling bosonic quantum phase transitions

The geometry and binding energy of excitons, set by electron-hole wavefunction distributions, are fundamental factors that underpin their many-body interactions and determine optoelectronic properties of semiconductors. However, in typical solid-state systems, these quantities are fixed by material composition and structure. Here we introduce a polarizable interlayer exciton hosted in a two-dimensional tetralayer heterostructure whose dipole length, in-plane radius, and binding energy can be continuously programmed in situ over a wide range, enabling direct control over the nature of excitonic many-body phase transitions. An out-of-plane electric field redistributes layer-hybridized electron-hole wavefunctions, realizing in situ control of exciton geometry through a strong quadratic Stark response. This tunability further regulates the nature of interaction-driven Mott transition, transforming it from gradual to abrupt. Our results establish exciton geometry as a continuously tunable materials parameter, opening routes to exciton-based quantum phase-transition simulators and guiding the design of emergent optoelectronic functionalities from programmable excitonic materials.

cond-mat.mtrl-sci↗
arXiv2025

Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its scalability is limited by synchronization overhead. Asynchronous federated learning (AFL) alleviates this issue by allowing clients to communicate independently, thereby improving wall-clock efficiency in large-scale, hardware-heterogeneous environments. However, asynchrony introduces updates computed on outdated global models (staleness) that can destabilize optimization and hinder convergence. We propose FedRevive, an AFL framework that revives stale updates through data-free knowledge distillation (DFKD). FedRevive integrates parameter-space aggregation with a lightweight, server-side DFKD process that transfers knowledge from stale client updates to the current global model without access to data. A meta-learned generator synthesizes pseudo-samples used for multi-teacher distillation. A hybrid aggregation scheme that combines raw with DFKD updates effectively mitigates staleness while retaining AFL scalability. Experiments on various vision and text benchmarks show that FedRevive achieves faster training by up to 38.4% and higher final accuracy by up to 16.5% than asynchronous baselines.

cs.LG↗
arXiv2025

GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation

This work presents GarmentX, a novel framework for generating diverse, high-fidelity, and wearable 3D garments from a single input image. Traditional garment reconstruction methods directly predict 2D pattern edges and their connectivity, an overly unconstrained approach that often leads to severe self-intersections and physically implausible garment structures. In contrast, GarmentX introduces a structured and editable parametric representation compatible with GarmentCode, ensuring that the decoded sewing patterns always form valid, simulation-ready 3D garments while allowing for intuitive modifications of garment shape and style. To achieve this, we employ a masked autoregressive model that sequentially predicts garment parameters, leveraging autoregressive modeling for structured generation while mitigating inconsistencies in direct pattern prediction. Additionally, we introduce GarmentX dataset, a large-scale dataset of 378,682 garment parameter-image pairs, constructed through an automatic data generation pipeline that synthesizes diverse and high-quality garment images conditioned on parametric garment representations. Through integrating our method with GarmentX dataset, we achieve state-of-the-art performance in geometric fidelity and input image alignment, significantly outperforming prior approaches. We will release GarmentX dataset upon publication.

cs.CV↗
arXiv2024

Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories

Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory. This paper presents a Toy-GS method for accurately rendering large-scale free camera trajectories. Specifically, we propose an adaptive spatial division approach for free trajectories to divide cameras and the sparse point cloud of the entire scene into various regions according to camera poses. Training each local Gaussian in parallel for each area enables us to concentrate on texture details and minimize GPU memory usage. Next, we use the multi-view constraint and position-aware point adaptive control (PPAC) to improve the rendering quality of texture details. In addition, our regional fusion approach combines local and global Gaussians to enhance rendering quality with an increasing number of divided areas. Extensive experiments have been carried out to confirm the effectiveness and efficiency of Toy-GS, leading to state-of-the-art results on two public large-scale datasets as well as our SCUTic dataset. Our proposal demonstrates an enhancement of 1.19 dB in PSNR and conserves 7 G of GPU memory when compared to various benchmarks.

cs.CV↗
arXiv2024

Debiasing Federated Learning with Correlated Client Participation

In cross-device federated learning (FL) with millions of mobile clients, only a small subset of clients participate in training in every communication round, and Federated Averaging (FedAvg) is the most popular algorithm in practice. Existing analyses of FedAvg usually assume the participating clients are independently sampled in each round from a uniform distribution, which does not reflect real-world scenarios. This paper introduces a theoretical framework that models client participation in FL as a Markov chain to study optimization convergence when clients have non-uniform and correlated participation across rounds. We apply this framework to analyze a more general and practical pattern: every client must wait a minimum number of $R$ rounds (minimum separation) before re-participating. We theoretically prove and empirically observe that increasing minimum separation reduces the bias induced by intrinsic non-uniformity of client availability in cross-device FL systems. Furthermore, we develop an effective debiasing algorithm for FedAvg that provably converges to the unbiased optimal solution under arbitrary minimum separation and unknown client availability distribution.

cs.LG↗
arXiv2024

Evidence for Two-dimensional Weyl Fermions in Air-Stable Monolayer PtTe$_{1.75}$

The Weyl semimetals represent a distinct category of topological materials wherein the low-energy excitations appear as the long-sought Weyl fermions. Exotic transport and optical properties are expected because of the chiral anomaly and linear energy-momentum dispersion. While three-dimensional Weyl semimetals have been successfully realized, the quest for their two-dimensional (2D) counterparts is ongoing. Here, we report the realization of 2D Weyl fermions in monolayer PtTe$_{1.75}$, which has strong spin-orbit coupling and lacks inversion symmetry, by combined angle-resolved photoemission spectroscopy, scanning tunneling microscopy, second harmonic generation, X-ray photoelectron spectroscopy measurements, and first-principles calculations. The giant Rashba splitting and band inversion lead to the emergence of three pairs of critical Weyl cones. Moreover, monolayer PtTe$_{1.75}$ exhibits excellent chemical stability in ambient conditions, which is critical for future device applications. The discovery of 2D Weyl fermions in monolayer PtTe$_{1.75}$ opens up new possibilities for designing and fabricating novel spintronic devices.

cond-mat.mes-hall↗
arXiv2024

Evidence for Multiferroicity in Single-Layer CuCrSe$_2$

Multiferroic materials, which simultaneously exhibit ferroelectricity and magnetism, have attracted substantial attention due to their fascinating physical properties and potential technological applications. With the trends towards device miniaturization, there is an increasing demand for the persistence of multiferroicity in single-layer materials at elevated temperatures. Here, we report high-temperature multiferroicity in single-layer CuCrSe$_2$, which hosts room-temperature ferroelectricity and 120 K ferromagnetism. Notably, the ferromagnetic coupling in single-layer CuCrSe$_2$ is enhanced by the ferroelectricity-induced orbital shift of Cr atoms, which is distinct from both types I and II multiferroicity. These findings are supported by a combination of second-harmonic generation, piezo-response force microscopy, scanning transmission electron microscopy, magnetic, and Hall measurements. Our research provides not only an exemplary platform for delving into intrinsic magnetoelectric interactions at the single-layer limit but also sheds light on potential development of electronic and spintronic devices utilizing two-dimensional multiferroics.

cond-mat.mtrl-sci↗
arXiv2024

Aerial-NeRF: Adaptive Spatial Partitioning and Sampling for Large-Scale Aerial Rendering

Recent progress in large-scale scene rendering has yielded Neural Radiance Fields (NeRF)-based models with an impressive ability to synthesize scenes across small objects and indoor scenes. Nevertheless, extending this idea to large-scale aerial rendering poses two critical problems. Firstly, a single NeRF cannot render the entire scene with high-precision for complex large-scale aerial datasets since the sampling range along each view ray is insufficient to cover buildings adequately. Secondly, traditional NeRFs are infeasible to train on one GPU to enable interactive fly-throughs for modeling massive images. Instead, existing methods typically separate the whole scene into multiple regions and train a NeRF on each region, which are unaccustomed to different flight trajectories and difficult to achieve fast rendering. To that end, we propose Aerial-NeRF with three innovative modifications for jointly adapting NeRF in large-scale aerial rendering: (1) Designing an adaptive spatial partitioning and selection method based on drones' poses to adapt different flight trajectories; (2) Using similarity of poses instead of (expert) network for rendering speedup to determine which region a new viewpoint belongs to; (3) Developing an adaptive sampling approach for rendering performance improvement to cover the entire buildings at different heights. Extensive experiments have conducted to verify the effectiveness and efficiency of Aerial-NeRF, and new state-of-the-art results have been achieved on two public large-scale aerial datasets and presented SCUTic dataset. Note that our model allows us to perform rendering over 4 times as fast as compared to multiple competitors. Our dataset, code, and model are publicly available at https://drliuqi.github.io/.

cs.CV↗
arXiv2024

A Stochastic Quasi-Newton Method for Non-convex Optimization with Non-uniform Smoothness

Classical convergence analyses for optimization algorithms rely on the widely-adopted uniform smoothness assumption. However, recent experimental studies have demonstrated that many machine learning problems exhibit non-uniform smoothness, meaning the smoothness factor is a function of the model parameter instead of a universal constant. In particular, it has been observed that the smoothness grows with respect to the gradient norm along the training trajectory. Motivated by this phenomenon, the recently introduced $(L_0, L_1)$-smoothness is a more general notion, compared to traditional $L$-smoothness, that captures such positive relationship between smoothness and gradient norm. Under this type of non-uniform smoothness, existing literature has designed stochastic first-order algorithms by utilizing gradient clipping techniques to obtain the optimal $\mathcal{O}(\epsilon^{-3})$ sample complexity for finding an $\epsilon$-approximate first-order stationary solution. Nevertheless, the studies of quasi-Newton methods are still lacking. Considering higher accuracy and more robustness for quasi-Newton methods, in this paper we propose a fast stochastic quasi-Newton method when there exists non-uniformity in smoothness. Leveraging gradient clipping and variance reduction, our algorithm can achieve the best-known $\mathcal{O}(\epsilon^{-3})$ sample complexity and enjoys convergence speedup with simple hyperparameter tuning. Our numerical experiments show that our proposed algorithm outperforms the state-of-the-art approaches.

cs.LG↗
arXiv2024

Layer-dependent Raman spectroscopy of ultrathin Ta$_2$Pd$_3$Te$_5$

Two-dimensional topological insulators (2DTIs) or quantum spin Hall insulators are attracting increasing attention due to their potential applications in next-generation spintronic devices. Despite their promising prospects, realizable 2DTIs are still limited. Recently, Ta2Pd3Te5, a semiconducting van der Waals material, has shown spectroscopic evidence of quantum spin Hall states. However, achieving controlled preparation of few- to monolayer samples, a crucial step in realizing quantum spin Hall devices, has not yet been achieved. In this work, we fabricated few- to monolayer Ta$_2$Pd$_3$Te$_5$ and performed systematic thickness- and temperature-dependent Raman spectroscopy measurements. Our results demonstrate that Raman spectra can provide valuable information to determine the thickness of Ta2Pd3Te5 thin flakes. Moreover, our angle-resolved polarized Raman (ARPR) spectroscopy measurements show that the intensities of the Raman peaks are strongly anisotropic due to the quasi-one-dimensional atomic structure, providing a straightforward method to determine its crystalline orientation. Our findings may stimulate further efforts to realize quantum devices based on few or monolayer Ta$_2$Pd$_3$Te$_5$.

cond-mat.mtrl-sci↗
arXiv2023

Epitaxial growth of high-quality GaAs on Si(001) using ultrathin buffer layers

The direct growth of III-V semiconductors on silicon holds tremendous potential for photonics applications. However, the inherent differences in their properties lead to defects in the epitaxial layer, including threading dislocations (TDs), antiphase boundaries (APBs), and thermal cracks, significantly impacting device performance. Current processes struggle to suppress these defects simultaneously, necessitating the development of methods to inhibit TDs and APBs in a thin buffer on silicon. This study introduces a GaSb buffer layer during GaAs epitaxy on a silicon (001) substrate. This approach successfully suppresses defect formation by promoting the formation of interfacial misfit dislocation (IMF) arrays at both the AlSb/Si and GaAs/GaSb interfaces. The resulting GaAs layer exhibits a step-flow surface with a rough mean square of approximately 3.8 nm and a full width at half maximum of 158 arcsec. Remarkably, the growth is achieved without any observable interfacial intermixing. Building on this platform, InAs/GaAs quantum dots (QDs) are grown with a density of 3.8E10/cm2, emitting at a wavelength of 1288 nm. This breakthrough holds immense promise for developing high-quality GaAs films with reduced defect densities on silicon for O band lasers, laying the foundation for the mass production of silicon-based integrated circuits.

cond-mat.mtrl-sci↗
arXiv2023

Incentivized Federated Learning and Unlearning

To protect users' right to be forgotten in federated learning, federated unlearning aims at eliminating the impact of leaving users' data on the global learned model. The current research in federated unlearning mainly concentrated on developing effective and efficient unlearning techniques. However, the issue of incentivizing valuable users to remain engaged and preventing their data from being unlearned is still under-explored, yet important to the unlearned model performance. This paper focuses on the incentive issue and develops an incentive mechanism for federated learning and unlearning. We first characterize the leaving users' impact on the global model accuracy and the required communication rounds for unlearning. Building on these results, we propose a four-stage game to capture the interaction and information updates during the learning and unlearning process. A key contribution is to summarize users' multi-dimensional private information into one-dimensional metrics to guide the incentive design. We further investigate whether allowing federated unlearning is beneficial to the server and users, compared to a scenario without unlearning. Interestingly, users usually have a larger total payoff in the scenario with higher costs, due to the server's excess incentives under information asymmetry. The numerical results demonstrate the necessity of unlearning incentives for retaining valuable leaving users, and also show that our proposed mechanisms decrease the server's cost by up to 53.91\% compared to state-of-the-art benchmarks.

cs.GT↗
arXiv2023

SUGAR: Spherical Ultrafast Graph Attention Framework for Cortical Surface Registration

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses, to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration, enhancing the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 minutes. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

eess.IV↗
arXiv2023

Machine-Learning-Assisted and Real-Time-Feedback-Controlled Growth of InAs/GaAs Quantum Dots

Self-assembled InAs/GaAs quantum dots (QDs) have properties highly valuable for developing various optoelectronic devices such as QD lasers and single photon sources. The applications strongly rely on the density and quality of these dots, which has motivated studies of the growth process control to realize high-quality epi-wafers and devices. Establishing the process parameters in molecular beam epitaxy (MBE) for a specific density of QDs is a multidimensional optimization challenge, usually addressed through time-consuming and iterative trial-and-error. Here, we report a real-time feedback control method to realize the growth of QDs with arbitrary density, which is fully automated and intelligent. We developed a machine learning (ML) model named 3D ResNet 50 trained using reflection high-energy electron diffraction (RHEED) videos as input instead of static images and providing real-time feedback on surface morphologies for process control. As a result, we demonstrated that ML from previous growth could predict the post-growth density of QDs, by successfully tuning the QD densities in near-real time from 1.5E10 cm-2 down to 3.8E8 cm-2 or up to 1.4E11 cm-2. Compared to traditional methods, our approach, with in situ tuning capabilities and excellent reliability, can dramatically expedite the material optimization process and improve the reproducibility of MBE, constituting significant progress for thin film growth techniques. The concepts and methodologies proved feasible in this work are promising to be applied to a variety of material growth processes, which will revolutionize semiconductor manufacturing for optoelectronic and microelectronic industries.

cond-mat.mes-hall↗
arXiv2023

Realization of a two-dimensional checkerboard lattice in monolayer Cu$_2$N

Two-dimensional checkerboard lattice, the simplest line-graph lattice, has been intensively studied as a toy model, while material design and synthesis remain elusive. Here, we report theoretical prediction and experimental realization of the checkerboard lattice in monolayer Cu$_2$N. Experimentally, monolayer Cu$_2$N can be realized in the well-known N/Cu(100) and N/Cu(111) systems that were previously mistakenly believed to be insulators. Combined angle-resolved photoemission spectroscopy measurements, first-principles calculations, and tight-binding analysis show that both systems host checkerboard-derived hole pockets near the Fermi level. In addition, monolayer Cu$_2$N has outstanding stability in air and organic solvents, which is crucial for further device applications.

cond-mat.mtrl-sci↗