arXiv subjects

Yue Dai

Publications and source records attributed to Yue Dai.

At least 37 records · Page 2Linked to original sources

arXiv2025

EdgeOL: Efficient in-situ Online Learning on Edge Devices

Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes. Online model fine-tuning is widely adopted to satisfy these needs. However, an inappropriate fine-tuning scheme could involve significant energy consumption, making it challenging to deploy on edge devices. In this paper, we propose EdgeOL, an edge online learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy

cs.LG↗

arXiv2025

Graph-Based Multimodal Contrastive Learning for Chart Question Answering

Chart question answering (ChartQA) is challenged by the heterogeneous composition of chart elements and the subtle data patterns they encode. This work introduces a novel joint multimodal scene graph framework that explicitly models the relationships among chart components and their underlying structures. The framework integrates both visual and textual graphs to capture structural and semantic characteristics, while a graph contrastive learning strategy aligns node representations across modalities enabling their seamless incorporation into a transformer decoder as soft prompts. Moreover, a set of tailored Chain of Thought (CoT) prompts is proposed to enhance multimodal large language models (MLLMs) in zero-s ot scenarios by mitigating hallucinations. Extensive evaluations on benchmarks including ChartQA, OpenCQA, and ChartX demonstrate significant performance improvements and validate the efficacy of the proposed approach.

cs.CL↗

arXiv2025

Enhancing Document Key Information Localization Through Data Augmentation

The Visually Rich Form Document Intelligence and Understanding (VRDIU) Track B focuses on the localization of key information in document images. The goal is to develop a method capable of localizing objects in both digital and handwritten documents, using only digital documents for training. This paper presents a simple yet effective approach that includes a document augmentation phase and an object detection phase. Specifically, we augment the training set of digital documents by mimicking the appearance of handwritten documents. Our experiments demonstrate that this pipeline enhances the models' generalization ability and achieves high performance in the competition.

cs.CV↗

arXiv2024

Using Reinforcement Learning to Guide Graph State Generation for Photonic Quantum Computers

Photonic quantum computer (PQC) is an emerging and promising quantum computing paradigm that has gained momentum in recent years. In PQC, which leverages the measurement-based quantum computing (MBQC) model, computations are executed by performing measurements on photons in graph states (i.e., sets of entangled photons) that are generated before measurements. The graph state in PQC is generated deterministically by quantum emitters. The generation process is achieved by applying a sequence of quantum gates to quantum emitters. In this process, i) the time required to complete the process, ii) the number of quantum emitters used, and iii) the number of CZ gates performed between emitters greatly affect the fidelity of the generated graph state. However, prior work for determining the generation sequence only focuses on optimizing the number of quantum emitters. Moreover, identifying the optimal generation sequence has vast search space. To this end, we propose RLGS, a novel compilation framework to identify optimal generation sequences that optimize the three metrics. Experimental results show that RLGS achieves an average reduction in generation time of 31.1%, 49.6%, and 57.5% for small, medium, and large graph states compared to the baseline.

quant-ph↗

arXiv2024

MSG-Chart: Multimodal Scene Graph for ChartQA

Automatic Chart Question Answering (ChartQA) is challenging due to the complex distribution of chart elements with patterns of the underlying data not explicitly displayed in charts. To address this challenge, we design a joint multimodal scene graph for charts to explicitly represent the relationships between chart elements and their patterns. Our proposed multimodal scene graph includes a visual graph and a textual graph to jointly capture the structural and semantical knowledge from the chart. This graph module can be easily integrated with different vision transformers as inductive bias. Our experiments demonstrate that incorporating the proposed graph module enhances the understanding of charts' elements' structure and semantics, thereby improving performance on publicly available benchmarks, ChartQA and OpenCQA.

cs.CL↗

arXiv2024

Improving GPU Multi-Tenancy Through Dynamic Multi-Instance GPU Reconfiguration

Continuous learning (CL) has emerged as one of the most popular deep learning paradigms deployed in modern cloud GPUs. Specifically, CL has the capability to continuously update the model parameters (through model retraining) and use the updated model (if available) to serve overtime arriving inference requests. It is generally beneficial to co-locate the retraining and inference together to enable timely model updates and avoid model transfer overheads. This brings the need for GPU sharing among retraining and inferences. Meanwhile, multiple CL workloads can share the modern GPUs in the cloud, leading to multi-tenancy execution. In this paper, we observe that prior GPU-sharing techniques are not optimized for multi-tenancy CL workloads. Specifically, they do not coherently consider the accuracy of the retraining model and the inference service level objective (SLO) attainment. Moreover, they cannot accommodate the overtime dynamics (e.g., inference arrival intensity) in CL execution. In this paper, we propose MIGRator, a novel GPU reconfiguration runtime that dynamically performs GPU reconfiguration for multi-tenancy CL workloads. MIGRator is based on the recent NVIDIA multi-instance GPU (MIG) to mitigate resource contention and formulates the reconfiguration optimization into Integer Linear Programming (ILP) to dynamically identify, reconfigure, and allocate the GPU instances. MIGRator leverages the "Goodput" metric in the ILP objective function to consider both inference SLO attainment and model accuracy in the reconfiguration exploration. We evaluate MIGRator using representative multi-tenancy CL workloads. The results show our approach outperforms the state-of-the-art GPU sharing techniques (i.e., Ekya, Astraea, and PARIS) by 17\%, 21\%, and 20\%, respectively.

cs.DC↗

arXiv2024

Observation of floating surface state in obstructed atomic insulator candidate NiP$_2$

Obstructed atomic insulator is recently proposed as an unconventional material, in which electric charge centers localized at sites away from the atoms. A half-filling surface state would emerge at specific interfaces cutting through these charge centers and avoid intersecting any atoms. In this article, we utilized angle-resolved photoemission spectroscopy and density functional theory calculations to study one of the obstructed atomic insulator candidates, NiP$_2$. A floating surface state with large effective mass that is isolated from all bulk states is resolved on the (100) cleavage plane, distinct from previously reported surface states in obstructed atomic insulators that are merged into bulk bands. Density functional theory calculation results elucidate that this floating surface state is originated from the obstructed Wannier charge centers, albeit underwent surface reconstruction that splits the half-filled obstructed surface state. Our findings not only shed lights on the spectroscopy study of obstructed atomic insulators and obstructed surface states, but also provide possible route for development of new catalysts.

cond-mat.mtrl-sci↗

arXiv2024

Molecule-induced surface second-order nonlinearity in an inversion symmetric microcavity

Inversion symmetry eliminates the second-order nonlinear responses in materials commonly used in silicon photonics with electric-dipole approximation. The lack of effective methods to induce the second-order nonlinearity in silicon photonic materials prevents their applications in second-order nonlinear integrated photonics. Here, we experimentally demonstrate a surface second-order nonlinear optics approach for boosting the second harmonic (SH) generation process in a silica microcavity. By leveraging the molecule-induced surface second-order nonlinearity, a record high SH efficiency of about 6.7% W-1 is achieved in a silica microcavity functionalized with a surface asymmetrically-aligned molecular monolayer, which is enhanced of two to four orders of magnitude compared to that before molecule-functionalization. Furthermore, we derive the equations that govern the surface second-order nonlinear process in inversion symmetric microcavities. Our method not only enables high efficiency second-order nonlinear frequency conversions in silica photonics, but also can apply to other inversion symmetric material platforms for integrated photonics.

physics.optics↗

arXiv2024

Observation of Spin Splitting in Room-Temperature Metallic Antiferromagnet CrSb

Recently, unconventional antiferromagnets that enable the splitting of electronic spins have been theoretically proposed and experimentally realized, where the magnetic sublattices containing moments pointing at different directions are connected by a novel set of symmetries. Such spin splitting (SS) is substantial, $k$-dependent, and independent of the spin-orbit coupling strength, making these magnets promising materials for antiferromagnetic spintronics. Here, combined with angle-resolved photoemission spectroscopy (ARPES) and density functional theory (DFT) calculations, we perform a systematic study on CrSb, a metallic spin-split antiferromagnet candidate with $T_N$ = 703 K. Our data reveals the electronic structure of CrSb along both out-of-plane and in-plane momentum directions, which renders anisotropic $k$-dependent SS and agrees well with the calculational results. The magnitude of such SS reaches up to at least 0.8 eV at non-high-symmetry momentum points, which is significantly higher than the largest known SOC-induced SS. This compound expands the choice of materials in the field of antiferromagnetic spintronics and is likely to stimulate subsequent investigations of high-efficiency spintronic devices that are functional at room temperature.

cond-mat.mtrl-sci↗

arXiv2024

SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing

There has been a proliferation of artificial intelligence applications, where model training is key to promising high-quality services for these applications. However, the model training process is both time-intensive and energy-intensive, inevitably affecting the user's demand for application efficiency. Layer freezing, an efficient model training technique, has been proposed to improve training efficiency. Although existing layer freezing methods demonstrate the great potential to reduce model training costs, they still remain shortcomings such as lacking generalizability and compromised accuracy. For instance, existing layer freezing methods either require the freeze configurations to be manually defined before training, which does not apply to different networks, or use heuristic freezing criteria that is hard to guarantee decent accuracy in different scenarios. Therefore, there lacks a generic and smart layer freezing method that can automatically perform ``in-situation'' layer freezing for different networks during training processes. To this end, we propose a generic and efficient training framework (SmartFRZ). The core proposed technique in SmartFRZ is attention-guided layer freezing, which can automatically select the appropriate layers to freeze without compromising accuracy. Experimental results show that SmartFRZ effectively reduces the amount of computation in training and achieves significant training acceleration, and outperforms the state-of-the-art layer freezing approaches.

cs.LG↗

arXiv2023

Smart Meters Integration in Distribution System State Estimation with Collaborative Filtering and Deep Gaussian Process

The problem of state estimations for electric distribution system is considered. A collaborative filtering approach is proposed in this paper to integrate the slow time-scale smart meter measurements in the distribution system state estimation, in which the deep Gaussian process is incorporated to infer the fast time-scale pseudo measurements and avoid anomalies. Numerical tests have demonstrated the higher estimation accuracy of the proposed method.

eess.SY↗

arXiv2022

ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining

The growing interest in developing corpora of persuasive texts has promoted applications in automated systems, e.g., debating and essay scoring systems; however, there is little prior work mining image persuasiveness from an argumentative perspective. To expand persuasiveness mining into a multi-modal realm, we present a multi-modal dataset, ImageArg, consisting of annotations of image persuasiveness in tweets. The annotations are based on a persuasion taxonomy we developed to explore image functionalities and the means of persuasion. We benchmark image persuasiveness tasks on ImageArg using widely-used multi-modal learning methods. The experimental results show that our dataset offers a useful resource for this rich and challenging topic, and there is ample room for modeling improvement.

cs.CL↗

arXiv2022

An Analysis of Deep Reinforcement Learning Agents for Text-based Games

Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals.In TBG agent design and training process, balancing the efficiency and performance of the agent models is a major challenge. Finding TBG agent deep learning modules' performance in standardized environments, and testing their performance among different evaluation types is also important for TBG agent research. We constructed a standardized TBG agent with no hand-crafted rules, formally categorized TBG evaluation types, and analyzed selected methods in our environment.

cs.CL↗

arXiv2022

Not all entangled states are useful for ancilla-assisted quantum process tomography

It is well known that one can extract all the information of an unknown quantum channel by means of quantum process tomography, such as standard quantum-process tomography and ancilla-assisted quantum process tomography (AAQPT). Furthermore, it has been shown that entanglement is not necessary for AAQPT, there exist separable states which are also useful for it. Surprisingly, in this work we find that not all entangled states are useful for AAQPT, there also exist some entangled states which are useless. The realignment operation used in entanglement detection can be related to the question whether a bipartite state is useful for AAQPT. We derive the relationship between them and show the process of extracting the complete information of an unknown channel by the realignment operation. Based on this relationship, we present examples of a two-qutrit entangled state and a two-qutrit bound entangled state. Both of these two examples are entangled but they cannot be used for AAQPT. Last but not least, experimental verification has also been performed on the IBM platform.

quant-ph↗

arXiv2022

Infrared Radiation of Graphene Electrothermal Film Triggered Alpha and Theta Brainwaves

The alpha and theta frequency brainwave activity in Electroencephalogram (EEG) signal has been correlated with attention, inhibitory processes, memory, perceptual abilities, and sleep. The enhanced alpha and theta brainwave activity may bring positive behavioral modifications such as promoting creativity and a quick sleep. Herein, we discover that infrared radiation from multilayer graphene electrothermal film can obviously promote the appearance of alpha and theta brainwave in human mind. In particular, the occurrence frequency of the alpha and theta waves in EEG can be effectively enhanced up to 2.3 and 3.0 times, respectively. And the duration time of the alpha and theta waves in EEG can also be effectively extended. The mechanism may be attributed to the efficient infrared radiation caused by graphene mainly focused on the range from 7 to 14 micron, coinciding with the radiation wavelength of natural human body, which can be effectively absorbed by the human skin and speed up the blood microcirculation and metabolism. The comparative effect of different working temperature and heating materials such as water, Cu and even monolayer graphene are systematically investigated, indicating the infrared radiation from the multilayer graphene electrothermal film at 50 degrees has the largest enhancement effect of alpha and theta brainwaves. The multilayer graphene film electrical heater represents a convenient and surprising way for triggering the alpha and theta brainwaves, which has many potential applications in the area of enlarged health cerements.

physics.app-ph↗

arXiv2021

Observation of the tradeoff between internal quantum nonseparability and external classical correlations

The monogamy relations of entanglement are highly significant. However, they involve only amounts of entanglement shared by different subsystems. Results on monogamy relations between entanglement and other kinds of correlations, and particularly classical correlations, are very scarce. Here we experimentally observe a tradeoff relation between internal quantum nonseparability and external total correlations in a photonic system and found that even purely classical external correlations have a detrimental effect on internal nonseparability. The nonseparability we consider, measured by the concurrence, is between different degrees of freedom within the same photon, and the external classical correlations, measured by the standard quantum mutual information, are generated between the photons of a photon pair using the time-bin method. Our observations show that to preserve the internal entanglement in a system, it is necessary to maintain low external correlations, including classical ones, between the system and its environment.

quant-ph↗

arXiv2020

Detecting and estimating coherence based on coherence witnesses

Quantum coherence has wide-ranging applications from quantum thermodynamics to quantum metrology, quantum channel discrimination and even quantum biology. Thus, detecting and quantifying coherence are two fundamental problems in quantum resource theory. Here, we introduce feasible methods to detect and estimate the coherence by constructing coherence witnesses for any finite-dimensional states. Our coherence witnesses detect coherent states by testing whether the expectation value of the witness is negative or not. Two typical coherence witnesses are proposed and discussed based on our witness-constructing method, which are also used to estimate the robustness of coherence, $l_1$-norm and $l_2$-norm of coherence measures. Furthermore, we compare one of our coherence witness with a previously introduced witness, by proving that our witness is strictly stronger than that previous witness. We also present an application of coherence in a quantum metrology task, in which we estimate an unknown parameter by measuring our coherence witness.

quant-ph↗

arXiv2020

Mid-infrared single photon detector with superconductor Mo$_{80}$Si$_{20}$ nanowire

A mid-infrared single photon detector (MIR-SNSPD) was reported based on 30 nm-wide superconductor molybdenum silicide nanowires in this work. Saturated quantum efficiencies (QEs) were achieved at the wavelength ranging from 1.55 to 5.07 micrometer in experiments. At the same time, the intrinsic dark count rate (DCR) was below 100 cps. Thus, this device produced a noise equivalent power (NEP) of 4.5 * 10-19 W/sqrt(Hz). The results provide the foundation of developing 10 micrometer-SNSPD for the applications of infrared astronomy observation.

physics.app-ph↗