arXiv subjects

Xiaodong Yang

Publications and source records attributed to Xiaodong Yang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control

We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge. In the design, the spatial conditional scheme is adaptive and customizable. It allows weighting different conditional inputs differently at different spatial locations. This enables highly controllable world generation and finds use in various world-to-world transfer use cases, including Sim2Real. We conduct extensive evaluations to analyze the proposed model and demonstrate its applications for Physical AI, including robotics Sim2Real and autonomous vehicle data enrichment. We further demonstrate an inference scaling strategy to achieve real-time world generation with an NVIDIA GB200 NVL72 rack. To help accelerate research development in the field, we open-source our models and code at https://github.com/nvidia-cosmos/cosmos-transfer1.

cs.CV↗

arXiv2025

Experimental realization and synchronization of a quantum van der Pol oscillator

Classical self-sustained oscillators, that generate periodic motion without periodic external forcing, are ubiquitous in science and technology. The realization of nonclassical self-oscillators is an important goal of quantum physics. We here present the experimental implementation of a quantum van der Pol oscillator, a paradigmatic autonomous quantum driven-dissipative system with nonlinear damping, using a single trapped atom. We demonstrate the existence of a quantum limit cycle in phase space in the absence of a drive and the occurrence of quantum synchronization when the nonlinear oscillator is externally driven. We additionally show that synchronization can be enhanced with the help of squeezing perpendicular to the direction of the drive and, counterintuitively, linear dissipation. We also observe the bifurcation to a bistable phase-space distribution for large squeezing. Our results pave the way for the exploration of self-sustained quantum oscillators and their application to quantum technology.

quant-ph↗

arXiv2025

Expanding-and-Shrinking Binary Neural Networks

While binary neural networks (BNNs) offer significant benefits in terms of speed, memory and energy, they encounter substantial accuracy degradation in challenging tasks compared to their real-valued counterparts. Due to the binarization of weights and activations, the possible values of each entry in the feature maps generated by BNNs are strongly constrained. To tackle this limitation, we propose the expanding-and-shrinking operation, which enhances binary feature maps with negligible increase of computation complexity, thereby strengthening the representation capacity. Extensive experiments conducted on multiple benchmarks reveal that our approach generalizes well across diverse applications ranging from image classification, object detection to generative diffusion model, while also achieving remarkable improvement over various leading binarization algorithms based on different architectures including both CNNs and Transformers.

cs.CV↗

arXiv2025

Variational Quantum Metrology with Loschmidt Echo

By utilizing quantum mechanical effects, such as superposition and entanglement, quantum metrology promises higher precision than the classical strategies. It is, however, practically challenging to realize the quantum advantages. This is mainly due to the difficulties in engineering non-classical probe state and performing nontrivial measurement in practise, particularly with a large number of particles. Here we propose a scalable scheme with a symmetrical variational quantum circuit which, same as the Loschmidt echo, consists of a forward and a backward evolution. We show that in this scheme the quantum Fisher information, which quantifies the precision limit, can be efficiently obtained from a measurement signal of the Loschmidt echo. We experimentally implement the scheme on an ensemble of 10-spin quantum processor and successfully achieves a precision near the theoretical limit which outperforms the standard quantum limit with 12.4 dB. The scheme can be efficiently implemented on various noisy intermediate-scale quantum devices which provides a promising routine to demonstrate quantum advantages.

quant-ph↗

arXiv2025

Experimental Realization of Criticality-Enhanced Global Quantum Sensing via Non-Equilibrium Dynamics

Quantum critical systems offer promising advancements in quantum sensing and metrology, yet face limitations like critical slowing down and a restricted criticality-enhanced region. Here, we introduce a critical sensing scheme that mitigate critical slowing down by leveraging the non-equilibrium dynamics of a perturbed Ising spin model, coupled with an adaptive strategy to enlarge its sensing interval. We validate the proposed scheme on a superconducting quantum processor and demonstrate that our scheme achieves a Heisenberg scaling with respect to the encoding duration. Additionally, the adaptive strategy tunes the model to operate near its critical point with limited prior information about the parameter, enabling what is known as global sensing. Our work showcases the metrological applications empowered by non-equilibrium critical dynamics and hence opens up a pathway for devising critical quantum sensors.

quant-ph↗

arXiv2025

Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization

To deal with distribution shifts in graph data, various graph out-of-distribution (OOD) generalization techniques have been recently proposed. These methods often employ a two-step strategy that first creates augmented environments and subsequently identifies invariant subgraphs to improve generalizability. Nevertheless, this approach could be suboptimal from the perspective of consistency. First, the process of augmenting environments by altering the graphs while preserving labels may lead to graphs that are not realistic or meaningfully related to the origin distribution, thus lacking distribution consistency. Second, the extracted subgraphs are obtained from directly modifying graphs, and may not necessarily maintain a consistent predictive relationship with their labels, thereby impacting label consistency. In response to these challenges, we introduce an innovative approach that aims to enhance these two types of consistency for graph OOD generalization. We propose a modifier to obtain both augmented and invariant graphs in a unified manner. With the augmented graphs, we enrich the training data without compromising the integrity of label-graph relationships. The label consistency enhancement in our framework further preserves the supervision information in the invariant graph. We conduct extensive experiments on real-world datasets to demonstrate the superiority of our framework over other state-of-the-art baselines.

cs.LG↗

arXiv2024

Multiscale energy transfers in a forced two-DOF oscillatory system with a grounded nonlinear energy sink

This paper studies the steady-state oscillations and the corresponding energy transfers in the two-DOF mechanical system with a grounded nonlinear energy sink (NES), under an external excitation. Based on the complexification-multiscale method, the slow frequency and the fast frequency of the complex amplitudes on the invariant manifold are analyzed, without omitting any terms. The analytical results show that the complex amplitudes of the primary system responses contain only the slow frequency, while that of the NES responses can contain both the slow frequency and the fast frequency when it triggers the high-order frequency term. In addition, each type of set on the invariant manifold represents the corresponding steady-state oscillations of the system, that is, the fixed point corresponds to the stationary oscillation, the interval corresponds to the nonlinear beat, and the hysteresis loop corresponds to the relaxation oscillation. Accordingly, we rewrite the forms of the complexification system to match the corresponding types of steady-state oscillations. Furthermore, the Hilbert-Huang transform is used to investigate the time-frequency relation of the displacements and the energies of the three steady-state responses. The Hilbert spectrums indicate that there is no energy transfer in the stationary oscillations, the O(ε)/O(ε) type of energy transfer in the nonlinear beats, and the O(ε)/O(ε) and the O(ε)/O(1) types of energy transfer in the relaxation oscillations. The theoretical results are confirmed by numerical simulations.

nlin.CD↗

arXiv2024

Self-Consistent Determination of Single-Impurity Anderson Model Using Hybrid Quantum-Classical Approach on a Spin Quantum Simulator

The accurate determination of the electronic structure of strongly correlated materials using first principle methods is of paramount importance in condensed matter physics, computational chemistry, and material science. However, due to the exponential scaling of computational resources, incorporating such materials into classical computation frameworks becomes prohibitively expensive. In 2016, Bauer et al. proposed a hybrid quantum-classical approach to correlated materials Phys. Rev. X 6, 031045 (2016)}] that can efficiently tackle the electronic structure of complex correlated materials. Here, we experimentally demonstrate that approach to tackle the computational challenges associated with strongly correlated materials. By seamlessly integrating quantum computation into classical computers, we address the most computationally demanding aspect of the calculation, namely the computation of the Green's function, using a spin quantum processor. Furthermore, we realize a self-consistent determination of the single impurity Anderson model through a feedback loop between quantum and classical computations. A quantum phase transition in the Hubbard model from the metallic phase to the Mott insulator is observed as the strength of electron correlation increases. As the number of qubits with high control fidelity continues to grow, our experimental findings pave the way for solving even more complex models, such as strongly correlated crystalline materials or intricate molecules.

quant-ph↗

arXiv2024

Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point Clouds

3D perception in LiDAR point clouds is crucial for a self-driving vehicle to properly act in 3D environment. However, manually labeling point clouds is hard and costly. There has been a growing interest in self-supervised pre-training of 3D perception models. Following the success of contrastive learning in images, current methods mostly conduct contrastive pre-training on point clouds only. Yet an autonomous driving vehicle is typically supplied with multiple sensors including cameras and LiDAR. In this context, we systematically study single modality, cross-modality, and multi-modality for contrastive learning of point clouds, and show that cross-modality wins over other alternatives. In addition, considering the huge difference between the training sources in 2D images and 3D point clouds, it remains unclear how to design more effective contrastive units for LiDAR. We therefore propose the instance-aware and similarity-balanced contrastive units that are tailored for self-driving point clouds. Extensive experiments reveal that our approach achieves remarkable performance gains over various point cloud models across the downstream perception tasks of LiDAR based 3D object detection and 3D semantic segmentation on the four popular benchmarks including Waymo Open Dataset, nuScenes, SemanticKITTI and ONCE.

cs.CV↗

arXiv2024

GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization

Recent studies show that well-devised perturbations on graph structures or node features can mislead trained Graph Neural Network (GNN) models. However, these methods often overlook practical assumptions, over-rely on heuristics, or separate vital attack components. In response, we present GAIM, an integrated adversarial attack method conducted on a node feature basis while considering the strict black-box setting. Specifically, we define an adversarial influence function to theoretically assess the adversarial impact of node perturbations, thereby reframing the GNN attack problem into the adversarial influence maximization problem. In our approach, we unify the selection of the target node and the construction of feature perturbations into a single optimization problem, ensuring a unique and consistent feature perturbation for each target node. We leverage a surrogate model to transform this problem into a solvable linear programming task, streamlining the optimization process. Moreover, we extend our method to accommodate label-oriented attacks, broadening its applicability. Thorough evaluations on five benchmark datasets across three popular models underscore the effectiveness of our method in both untargeted and label-oriented targeted attacks. Through comprehensive analysis and ablation studies, we demonstrate the practical value and efficacy inherent to our design choices.

cs.LG↗

arXiv2024

Long-baseline quantum sensor network as dark matter haloscope

Ultralight dark photons constitute a well-motivated candidate for dark matter. A coherent electromagnetic wave is expected to be induced by dark photons when coupled with Standard-Model photons through kinetic mixing mechanism, and should be spatially correlated within the de Broglie wavelength of dark photons. Here we report the first search for correlated dark-photon signals using a long-baseline network of 15 atomic magnetometers, which are situated in two separated meter-scale shield rooms with a distance of about 1700 km. Both the network's multiple sensors and the shields large size significantly enhance the expected dark-photon electromagnetic signals, and long-baseline measurements confidently reduce many local noise sources. Using this network, we constrain the kinetic mixing coefficient of dark photon dark matter over the mass range 4.1 feV-2.1 peV, which represents the most stringent constraints derived from any terrestrial experiments operating over the aforementioned mass range. Our prospect indicates that future data releases may go beyond the astrophysical constraints from the cosmic microwave background and the plasma heating.

quant-ph↗

arXiv2024

SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering

The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence and suboptimal local optima, partially because it only considers one negative item for each positive item, neglecting the potential impacts of other unobserved items. To address this issue, the recently proposed Sampled Softmax Cross-Entropy (SSM) compares one positive sample with multiple negative samples, leading to better performance. Our comprehensive experiments confirm that recommender systems consistently benefit from multiple negative samples during training. Furthermore, we introduce a \underline{Sim}plified Sampled Softmax \underline{C}ross-\underline{E}ntropy Loss (SimCE), which simplifies the SSM using its upper bound. Our validation on 12 benchmark datasets, using both MF and LightGCN backbones, shows that SimCE significantly outperforms both BPR and SSM.

cs.IR↗

arXiv2024

Multiple Classical Noise Mitigation by Multiobjective Robust Quantum Optimal Control

High-quality control is a fundamental requirement for quantum computation, but practically it is often hampered by the presence of various types of noises, which can be static or time-dependent. In many realistic scenarios, multiple noise sources coexist, and their resulting noise effects need be corrected to a sufficient order, posing significant challenges for the design of effective robust control methods. Here, we explore the method of robust quantum optimal control to generally tackle the problem of resisting multiple noises from a complicated noise environment. Specifically, we confine our analysis to unitary noises that can be described by classical noise models. This method employs a gradient-based multiobjective optimization algorithm to maximize the control figure of merit, and meanwhile to minimize the perturbative effects of the noises that are allowed for. To verify its effectiveness, we apply this method to a number of examples, including roubust entangling gate in trapped ion system and robust controlled-Z gate in superconducting qubits, under commonly encountered static and time-dependent noises. Our simulation results reveal that robust optimal control can find smooth, robust pulses that can simultaneously resist several noises and thus achieve high-fidelity gates. Therefore, we expect that this method will find wide applications on current noisy quantum computing devices.

quant-ph↗

arXiv2024

Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models

Multi-view data arises frequently in modern network analysis e.g. relations of multiple types among individuals in social network analysis, longitudinal measurements of interactions among observational units, annotated networks with noisy partial labeling of vertices etc. We study community detection in these disparate settings via a unified theoretical framework, and investigate the fundamental thresholds for community recovery. We characterize the mutual information between the data and the latent parameters, provided the degrees are sufficiently large. Based on this general result, (i) we derive a sharp threshold for community detection in an inhomogeneous multilayer block model \citep{chen2022global}, (ii) characterize a sharp threshold for weak recovery in a dynamic stochastic block model \citep{matias2017statistical}, and (iii) identify the limiting mutual information in an unbalanced partially labeled block model. Our first two results are derived modulo coordinate-wise convexity assumptions on specific functions -- we provide extensive numerical evidence for their correctness. Finally, we introduce iterative algorithms based on Approximate Message Passing for community detection in these problems.

math.ST↗

arXiv2023

Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content level and appearance level. While the latter is concerned with appearance style, the former problem arises from a different mechanism, i.e, content mismatch in attributes such as camera viewpoint, object placement and lighting conditions. In contrast to the widely-studied appearance-level gap, the content-level discrepancy has not been broadly studied. To address the content-level misalignment, we propose an attribute descent approach that automatically optimizes engine attributes to enable synthetic data to approximate real-world data. We verify our method on object-centric tasks, wherein an object takes up a major portion of an image. In these tasks, the search space is relatively small, and the optimization of each attribute yields sufficiently obvious supervision signals. We collect a new synthetic asset VehicleX, and reformat and reuse existing the synthetic assets ObjectX and PersonX. Extensive experiments on image classification and object re-identification confirm that adapted synthetic data can be effectively used in three scenarios: training with synthetic data only, training data augmentation and numerically understanding dataset content.

cs.CV↗

arXiv2023

Benign Oscillation of Stochastic Gradient Descent with Large Learning Rates

In this work, we theoretically investigate the generalization properties of neural networks (NN) trained by stochastic gradient descent (SGD) algorithm with large learning rates. Under such a training regime, our finding is that, the oscillation of the NN weights caused by the large learning rate SGD training turns out to be beneficial to the generalization of the NN, which potentially improves over the same NN trained by SGD with small learning rates that converges more smoothly. In view of this finding, we call such a phenomenon "benign oscillation". Our theory towards demystifying such a phenomenon builds upon the feature learning perspective of deep learning. Specifically, we consider a feature-noise data generation model that consists of (i) weak features which have a small $\ell_2$-norm and appear in each data point; (ii) strong features which have a larger $\ell_2$-norm but only appear in a certain fraction of all data points; and (iii) noise. We prove that NNs trained by oscillating SGD with a large learning rate can effectively learn the weak features in the presence of those strong features. In contrast, NNs trained by SGD with a small learning rate can only learn the strong features but makes little progress in learning the weak features. Consequently, when it comes to the new testing data which consist of only weak features, the NN trained by oscillating SGD with a large learning rate could still make correct predictions consistently, while the NN trained by small learning rate SGD fails. Our theory sheds light on how large learning rate training benefits the generalization of NNs. Experimental results demonstrate our finding on "benign oscillation".

cs.LG↗

arXiv2023

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

3D perception based on the representations learned from multi-camera bird's-eye-view (BEV) is trending as cameras are cost-effective for mass production in autonomous driving industry. However, there exists a distinct performance gap between multi-camera BEV and LiDAR based 3D object detection. One key reason is that LiDAR captures accurate depth and other geometry measurements, while it is notoriously challenging to infer such 3D information from merely image input. In this work, we propose to boost the representation learning of a multi-camera BEV based student detector by training it to imitate the features of a well-trained LiDAR based teacher detector. We propose effective balancing strategy to enforce the student to focus on learning the crucial features from the teacher, and generalize knowledge transfer to multi-scale layers with temporal fusion. We conduct extensive evaluations on multiple representative models of multi-camera BEV. Experiments reveal that our approach renders significant improvement over the student models, leading to the state-of-the-art performance on the popular benchmark nuScenes.

cs.CV↗

arXiv2023

GEDepth: Ground Embedding for Monocular Depth Estimation

Monocular depth estimation is an ill-posed problem as the same 2D image can be projected from infinite 3D scenes. Although the leading algorithms in this field have reported significant improvement, they are essentially geared to the particular compound of pictorial observations and camera parameters (i.e., intrinsics and extrinsics), strongly limiting their generalizability in real-world scenarios. To cope with this challenge, this paper proposes a novel ground embedding module to decouple camera parameters from pictorial cues, thus promoting the generalization capability. Given camera parameters, the proposed module generates the ground depth, which is stacked with the input image and referenced in the final depth prediction. A ground attention is designed in the module to optimally combine ground depth with residual depth. Our ground embedding is highly flexible and lightweight, leading to a plug-in module that is amenable to be integrated into various depth estimation networks. Experiments reveal that our approach achieves the state-of-the-art results on popular benchmarks, and more importantly, renders significant generalization improvement on a wide range of cross-domain tests.

cs.CV↗