arXiv subjects

Qi Yu

Publications and source records attributed to Qi Yu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Tracking Quantum Dynamics in an Optical Cavity for Recovering Purity and Squeezing via Quantum State Smoothing

Tracking the dynamics of a quantum system is conventionally achieved by monitoring the system continuously in time and filtering the information contained in measurement records via the causal quantum trajectory approach. However, in practical scenarios there is often loss of information to the environment, leading to filtered states that are impure because of decoherence. If real-time tracking is not required, the lost information can be maximally extracted via acausal quantum state smoothing, which has been theoretically proven to better restore the system's coherence (purity) than causal filtering. Interestingly, quantum state smoothing requires assumptions of how any lost quantum information (unobserved by the experimenter) was turned into classical information by the environment. In this work, we experimentally demonstrate smoothing scenarios, using an optical parametric oscillator and introducing `observed' and `unobserved' channels by splitting the output beam into two independent homodyne detectors. We achieve improvement in state purification of 10.3% +/- 1.6%, squeezing restoration of 7.6% +/- 2.6%, and show that smoothed states are better estimates of hidden true states than those from conventional filtering. The estimation techniques used in this paper are promising for many applications in quantum information that incorporate post-processing.

quant-ph↗

arXiv2025

ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications

Weakly-supervised video anomaly detection (WS-VAD) using Multiple Instance Learning (MIL) suffers from label ambiguity, hindering discriminative feature learning. We propose ProDisc-VAD, an efficient framework tackling this via two synergistic components. The Prototype Interaction Layer (PIL) provides controlled normality modeling using a small set of learnable prototypes, establishing a robust baseline without being overwhelmed by dominant normal data. The Pseudo-Instance Discriminative Enhancement (PIDE) loss boosts separability by applying targeted contrastive learning exclusively to the most reliable extreme-scoring instances (highest/lowest scores). ProDisc-VAD achieves strong AUCs (97.98% ShanghaiTech, 87.12% UCF-Crime) using only 0.4M parameters, over 800x fewer than recent ViT-based methods like VadCLIP. Code is available at https://github.com/modadundun/ProDisc-VAD.

cs.CV↗

arXiv2025

FuXi-Air: Urban Air Quality Forecasting Based on Emission-Meteorology-Pollutant multimodal Machine Learning

Air pollution has emerged as a major public health challenge in megacities. Numerical simulations and single-site machine learning approaches have been widely applied in air quality forecasting tasks. However, these methods face multiple limitations, including high computational costs, low operational efficiency, and limited integration with observational data. With the rapid advancement of artificial intelligence, there is an urgent need to develop a low-cost, efficient air quality forecasting model for smart urban management. An air quality forecasting model, named FuXi-Air, has been constructed in this study based on multimodal data fusion to support high-precision air quality forecasting and operated in typical megacities. The model integrates meteorological forecasts, emission inventories, and pollutant monitoring data under the guidance of air pollution mechanism. By combining an autoregressive prediction framework with a frame interpolation strategy, the model successfully completes 72-hour forecasts for six major air pollutants at an hourly resolution across multiple monitoring sites within 25-30 seconds. In terms of both computational efficiency and forecasting accuracy, it outperforms the mainstream numerical air quality models in operational forecasting work. Ablation experiments concerning key influencing factors show that although meteorological data contribute more to model accuracy than emission inventories do, the integration of multimodal data significantly improves forecasting precision and ensures that reliable predictions are obtained under differing pollution mechanisms across megacities. This study provides both a technical reference and a practical example for applying multimodal data-driven models to air quality forecasting and offers new insights into building hybrid forecasting systems to support air pollution risk warning in smart city management.

cs.LG↗

arXiv2025

Joint Optimal Transport and Embedding for Network Alignment

Network alignment, which aims to find node correspondence across different networks, is the cornerstone of various downstream multi-network and Web mining tasks. Most of the embedding-based methods indirectly model cross-network node relationships by contrasting positive and negative node pairs sampled from hand-crafted strategies, which are vulnerable to graph noises and lead to potential misalignment of nodes. Another line of work based on the optimal transport (OT) theory directly models cross-network node relationships and generates noise-reduced alignments. However, OT methods heavily rely on fixed, pre-defined cost functions that prohibit end-to-end training and are hard to generalize. In this paper, we aim to unify the embedding and OT-based methods in a mutually beneficial manner and propose a joint optimal transport and embedding framework for network alignment named JOENA. For one thing (OT for embedding), through a simple yet effective transformation, the noise-reduced OT mapping serves as an adaptive sampling strategy directly modeling all cross-network node pairs for robust embedding learning.For another (embedding for OT), on top of the learned embeddings, the OT cost can be gradually trained in an end-to-end fashion, which further enhances the alignment quality. With a unified objective, the mutual benefits of both methods can be achieved by an alternating optimization schema with guaranteed convergence. Extensive experiments on real-world networks validate the effectiveness and scalability of JOENA, achieving up to 16% improvement in MRR and 20x speedup compared with the state-of-the-art alignment methods.

cs.AI↗

arXiv2025

The quantum nature of ubiquitous vibrational features revealed for ethylene glycol

Vibrational properties of molecules are of widespread interest and importance in chemistry and biochemistry. The reliability of widely employed approximate computational methods is questioned here against the complex experimental spectrum of ethylene glycol. Comparisons between quantum vibrational self-consistent field and virtual-state configuration interaction (VSCF/VCI), adiabatically switched semiclassical initial value representation (AS SCIVR), and thermostatted ring polymer molecular dynamics (TRPMD) calculations are made using a full-dimensional machine-learned potential energy surface. Calculations are done for five low-lying conformers and compared with the experiment, with a focus on the high-frequency, OH-stretches, and CH-stretches, part of the spectrum. Fermi resonances are found in the analysis of VSCF/VCI eigenstates belonging to the CH-stretching band. Results of comparable accuracy, quality, and level of detail are obtained by means of AS SCIVR. The current VSCF/VCI and AS-SCIVR power spectra largely close the gaps between the experiment and TRPMD and classical MD calculations. Analysis of these results provide guidance on what level of accuracy to expect from TRPMD and classical MD calculations of the vibrational spectra for ubiquitous CH and OH-stretches bands. This work shows that even general vibrational features require a proper quantum treatment usually not achievable by the most popular theoretical approaches.

physics.chem-ph↗

arXiv2024

Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials

Most widely used machine learned (ML) potentials for condensed phase applications rely on many-body permutationally invariant polynomial (PIP) or atom-centered neural networks (NN). However, these approaches often lack chemical interpretability in atomistic energy decomposition and the computational efficiency of traditional force fields has not been fully achieved. Here, we present a novel method that combines aspects of both approaches, and achieves state-of-the-art balance of accuracy and force field-level speed. This method utilizes a monomer-centered representation, where the potential energy is decomposed into the sum of chemically meaningful monomeric energies. Without sophisticated neural network design, the structural descriptors of monomers are described by 1-body and 2-body effective interactions, enforced by appropriate sets of PIPs as inputs to the feed forward NN. We demonstrate the performance of this method through systematic assessments of models for gas-phase water trimer, liquid water, and also liquid CO2. The high accuracy, fast speed, and flexibility of this method provide a new route for constructing accurate ML potentials and enabling large-scale quantum and classical simulations for complex molecular systems.

physics.chem-ph↗

arXiv2024

Quantum mechanical deconstruction of vibrational energy transfer rate and pathways modified by collective vibrational strong coupling

Recent experiments have demonstrated that vibrational strong coupling (VSC) between molecular vibrations and the optical cavity field can modify vibrational energy transfer (VET) processes in molecular systems. However, the underlying mechanisms and the behavior of individual molecules under collective VSC remain largely incomplete. In this work, we combine state-of-the-art quantum vibrational spectral calculation, quantum wavepacket dynamics simulations, and ab initio machine-learning potential to elucidate how the vibrational dynamics of water OH stretches can be altered by VSC. Taking the (H$_2$O)$_{21}$-cavity system as an example, we show that the collective VSC breaks the localization picture, promotes the delocalization of OH stretches, and opens new intermolecular vibrational energy pathways involving both neighboring and remote water molecules. The manipulation of the VET process relies on the alignment of the transition dipole moment orientations of the corresponding vibrational states. The emergence of new energy transfer pathways is found to be attributed to cavity-induced vibrational resonance involving OH stretches across different water molecules, along with alterations in mode coupling patterns. Our fully quantum theoretical calculations not only confirm and extend previous findings on cavity-modified energy transfer processes but also provide new insights in energy transfer processes under collective VSC.

physics.chem-ph↗

arXiv2024

Time-In-Range Analyses of Functional Data Subject to Missing with Applications to Inpatient Continuous Glucose Monitoring

Continuous glucose monitoring (CGM) has been increasingly used in US hospitals for the care of patients with diabetes. Time in range (TIR), which measures the percent of time over a specified time window with glucose values within a target range, has served as a pivotal CGM-metric for assessing glycemic control. However, inpatient CGM is prone to a prevailing issue that a limited length of hospital stay can cause insufficient CGM sampling, leading to a scenario with functional data plagued by complex missingness. Current analyses of inpatient CGM studies, however, ignore this issue and typically compute the TIR as the proportion of available CGM glucose values in range. As shown by simulation studies, this can result in considerably biased estimation and inference, largely owing to the nonstationary nature of inpatient CGM trajectories. In this work, we develop a rigorous statistical framework that confers valid inference on TIR in realistic inpatient CGM settings. Our proposals utilize a novel probabilistic representation of TIR, which enables leveraging the technique of inverse probability weighting and semiparametric survival modeling to obtain unbiased estimators of mean TIR that properly account for incompletely observed CGM trajectories. We establish desirable asymptotic properties of the proposed estimators. Results from our numerical studies demonstrate good finite-sample performance of the proposed method as well as its advantages over existing approaches. The proposed method is generally applicable to other functional data settings similar to CGM.

stat.ME↗

arXiv2024

Can We Learn the Energy of Sublimation of Ice from Water Clusters?

This short paper reports a study of the electronic dissociation energies, De, of water clusters from direct ab initio (mostly CCSD(T)) calculations and the q-AQUA and MB-pol potentials. These clusters range in size from 6-25 monomers. These are all in very good agreement with each other, as shown in a recent Perspective by Herman and Xantheas. To the best of our knowledge, we present for the first time results for the De per monomer. To our surprise this quantity appears to be converging to a value close to 12 kcal/mol. An estimate of 1.5 - 2 kcal/mol for the ΔZPE for these clusters puts the value of D0 at 10 to 10.5 kcal/mol. This value is remarkably (and probably fortuitously) close to the reported sublimation enthalpy of 10.2 kcal/mol at 10 K. However, given that these De energies correspond to dissociation of the cluster to N isolated monomers the interpretation of ``vaporization" of these ``solid" clusters is qualitatively reasonable.

physics.chem-ph↗

arXiv2024

$Δ$-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol

Progress in machine learning has facilitated the development of potentials that offer both the accuracy of first-principles techniques and vast increases in the speed of evaluation. Recently,"$Δ$-machine learning" has been used to elevate the quality of a potential energy surface (PES) based on low-level, e.g., density functional theory (DFT) energies and gradients to close to the gold-standard coupled cluster level of accuracy. We have demonstrated the success of this approach for molecules, ranging in size from H$_3$O$^+$ to 15-atom acetyl-acetone and tropolone. These were all done using the B3LYP functional. Here we investigate the generality of this approach for the PBE, M06, M06-2X, and PBE0+MBD functionals, using ethanol as the example molecule. Linear regression with permutationally invariant polynomials is used to fit both low-level and correction PESs. These PESs are employed for standard RMSE analysis for training and test datasets, and then general fidelity tests such as energetics of stationary points, normal mode frequencies, and torsional potentials are examined. We achieve similar improvements in all cases. Interestingly, we obtained significant improvement over DFT gradients where coupled cluster gradients were not used to correct the low-level PES. Finally, we present some results for correcting a recent molecular mechanics force field for ethanol and comment on the possible generality of this approach.

physics.chem-ph↗

arXiv2024

Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness

Prior neural architecture search (NAS) for adversarial robustness works have discovered that a lightweight and adversarially robust neural network architecture could exist in a non-robust large teacher network, generally disclosed by heuristic rules through statistical analysis and neural architecture search, generally disclosed by heuristic rules from neural architecture search. However, heuristic methods cannot uniformly handle different adversarial attacks and "teacher" network capacity. To solve this challenge, we propose a Reinforced Compressive Neural Architecture Search (RC-NAS) for Versatile Adversarial Robustness. Specifically, we define task settings that compose datasets, adversarial attacks, and teacher network information. Given diverse tasks, we conduct a novel dual-level training paradigm that consists of a meta-training and a fine-tuning phase to effectively expose the RL agent to diverse attack scenarios (in meta-training), and making it adapt quickly to locate a sub-network (in fine-tuning) for any previously unseen scenarios. Experiments show that our framework could achieve adaptive compression towards different initial teacher networks, datasets, and adversarial attacks, resulting in more lightweight and adversarially robust architectures.

cs.LG↗

arXiv2024

No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials

Assessments of machine-learned (ML) potentials are an important aspect of the rapid development of this field. We recently reported an assessment of the linear-regression permutationally invariant polynomial (PIP) method for ethanol, using the widely used (revised) MD17 dataset. We demonstrated that the PIP approach outperformed numerous other methods, e.g., ANI, PhysNet, sGDML, p-KRR, with respect to precision and notably with respect to speed [Houston $et$ $al$., $J. Chem. Phys.$ 2022, 156, 044120.]. Here we extend this assessment to the 21-atom aspirin molecule, using the rMD17 dataset. Both energies and forces are used for training and the precision of several PIPs is examined for both. Normal mode frequencies, the methyl torsional potential, and 1d vibrational energies for an OH stretch are presented. Overall, we show that the PIPs approach outperforms other ML methods, including sGDML, ANI, GAP, PhysNet, and ACE, as reported by Kovács $et$ $al.$ in $J. Chem. Theory$ $Comput.$ 2021, 17, 7696-7711.

physics.chem-ph↗

arXiv2023

Latent Space Energy-based Model for Fine-grained Open Set Recognition

Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent trend in OSR shows the benefit of generative models to discriminative unknown detection. As a type of generative model, energy-based models (EBM) are the potential for hybrid modeling of generative and discriminative tasks. However, most existing EBMs suffer from density estimation in high-dimensional space, which is critical to recognizing images from fine-grained classes. In this paper, we explore the low-dimensional latent space with energy-based prior distribution for OSR in a fine-grained visual world. Specifically, based on the latent space EBM, we propose an attribute-aware information bottleneck (AIB), a residual attribute feature aggregation (RAFA) module, and an uncertainty-based virtual outlier synthesis (UVOS) module to improve the expressivity, granularity, and density of the samples in fine-grained classes, respectively. Our method is flexible to take advantage of recent vision transformers for powerful visual classification and generation. The method is validated on both fine-grained and general visual classification datasets while preserving the capability of generating photo-realistic fake images with high resolution.

cs.CV↗

arXiv2023

On Model Explanations with Transferable Neural Pathways

Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus on accuracy and sparsity but the generated pathways may offer limited interpretability thus fall short in explaining the model behavior. In this paper, we suggest two interpretability criteria of neural pathways: (i) same-class neural pathways should primarily consist of class-relevant neurons; (ii) each instance's neural pathway sparsity should be optimally determined. To this end, we propose a Generative Class-relevant Neural Pathway (GEN-CNP) model that learns to predict the neural pathways from the target model's feature maps. We propose to learn class-relevant information from features of deep and shallow layers such that same-class neural pathways exhibit high similarity. We further impose a faithfulness criterion for GEN-CNP to generate pathways with instance-specific sparsity. We propose to transfer the class-relevant neural pathways to explain samples of the same class and show experimentally and qualitatively their faithfulness and interpretability.

cs.CV↗

arXiv2023

Learn to Accumulate Evidence from All Training Samples: Theory and Practice

Evidential deep learning, built upon belief theory and subjective logic, offers a principled and computationally efficient way to turn a deterministic neural network uncertainty-aware. The resultant evidential models can quantify fine-grained uncertainty using the learned evidence. To ensure theoretically sound evidential models, the evidence needs to be non-negative, which requires special activation functions for model training and inference. This constraint often leads to inferior predictive performance compared to standard softmax models, making it challenging to extend them to many large-scale datasets. To unveil the real cause of this undesired behavior, we theoretically investigate evidential models and identify a fundamental limitation that explains the inferior performance: existing evidential activation functions create zero evidence regions, which prevent the model to learn from training samples falling into such regions. A deeper analysis of evidential activation functions based on our theoretical underpinning inspires the design of a novel regularizer that effectively alleviates this fundamental limitation. Extensive experiments over many challenging real-world datasets and settings confirm our theoretical findings and demonstrate the effectiveness of our proposed approach.

cs.LG↗

arXiv2023

Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks

Recent years have seen a surge in research on dynamic graph representation learning, which aims to model temporal graphs that are dynamic and evolving constantly over time. However, current work typically models graph dynamics with recurrent neural networks (RNNs), making them suffer seriously from computation and memory overheads on large temporal graphs. So far, scalability of dynamic graph representation learning on large temporal graphs remains one of the major challenges. In this paper, we present a scalable framework, namely SpikeNet, to efficiently capture the temporal and structural patterns of temporal graphs. We explore a new direction in that we can capture the evolving dynamics of temporal graphs with spiking neural networks (SNNs) instead of RNNs. As a low-power alternative to RNNs, SNNs explicitly model graph dynamics as spike trains of neuron populations and enable spike-based propagation in an efficient way. Experiments on three large real-world temporal graph datasets demonstrate that SpikeNet outperforms strong baselines on the temporal node classification task with lower computational costs. Particularly, SpikeNet generalizes to a large temporal graph (2.7M nodes and 13.9M edges) with significantly fewer parameters and computation overheads.Our code is publicly available at \url{https://github.com/EdisonLeeeee/SpikeNet}.

cs.NE↗

arXiv2023

Model-free Quantum Gate Design and Calibration using Deep Reinforcement Learning

High-fidelity quantum gate design is important for various quantum technologies, such as quantum computation and quantum communication. Numerous control policies for quantum gate design have been proposed given a dynamical model of the quantum system of interest. However, a quantum system is often highly sensitive to noise, and obtaining its accurate modeling can be difficult for many practical applications. Thus, the control policy based on a quantum system model may be unpractical for quantum gate design. Also, quantum measurements collapse quantum states, which makes it challenging to obtain information through measurements during the control process. In this paper, we propose a novel training framework using deep reinforcement learning for model-free quantum control. The proposed framework relies only on the measurement at the end of the control process and offers the ability to find the optimal control policy without access to quantum systems during the learning process. The effectiveness of the proposed technique is numerically demonstrated for model-free quantum gate design and quantum gate calibration using off-policy reinforcement learning algorithms.

eess.SY↗

arXiv2022

Evidential Conditional Neural Processes

The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance. However, the current CNP models only capture the overall uncertainty for the prediction made on a target data point. They lack a systematic fine-grained quantification on the distinct sources of uncertainty that are essential for model training and decision-making under the few-shot setting. We propose Evidential Conditional Neural Processes (ECNP), which replace the standard Gaussian distribution used by CNP with a much richer hierarchical Bayesian structure through evidential learning to achieve epistemic-aleatoric uncertainty decomposition. The evidential hierarchical structure also leads to a theoretically justified robustness over noisy training tasks. Theoretical analysis on the proposed ECNP establishes the relationship with CNP while offering deeper insights on the roles of the evidential parameters. Extensive experiments conducted on both synthetic and real-world data demonstrate the effectiveness of our proposed model in various few-shot settings.

cs.LG↗