Search

Class imbalance significantly impacts the performance of multi-label classifiers. Oversampling is one of the most popular approaches, as it augments instances associated with less frequent labels to balance the class distribution. Existing oversampling methods generate feature vectors of synthetic samples through replication or linear interpolation and assign labels through neighborhood information. Linear interpolation typically generates new samples between existing data points, which may result in insufficient diversity of synthesized samples and further lead to the overfitting issue. Deep learning-based methods, such as AutoEncoders, have been proposed to generate more diverse and complex synthetic samples, achieving excellent performance on imbalanced binary or multi-class datasets. In this study, we introduce AEMLO, an AutoEncoder-guided Oversampling technique specifically designed for tackling imbalanced multi-label data. AEMLO is built upon two fundamental components. The first is an encoder-decoder architecture that enables the model to encode input data into a low-dimensional feature space, learn its latent representations, and then reconstruct it back to its original dimension, thus applying to the generation of new data. The second is an objective function tailored to optimize the sampling task for multi-label scenarios. We show that AEMLO outperforms the existing state-of-the-art methods with extensive empirical studies.

In this work, we studied the genus fluctuations of the AdS$_{3}$ spacetime. The tunneling action of the high genus AdS$_{3}$ spacetime is formulated in the Siegel upper half space. Adopting the dilute wormhole gas approximation, we computed the genus creation rate in the semiclassical region. We show that a genus is more easily created in the spacetime corresponding to a larger absolute value of the cosmological constant. We find that fluctuations of fat wormholes are more likely to occur than those of thin wormholes. We also studied the influence of genus fluctuations on false vacuum decay. The vacuum decay rate will increase if the effect of genus fluctuations is included. We show that all results do not change qualitatively when the values of certain parameters are changed.

Metaphors are common in everyday language, and the identification and understanding of metaphors are facilitated by models to achieve a better understanding of the text. Metaphors are mainly identified and generated by pre-trained models in existing research, but situations, where tenors or vehicles are not included in the metaphor, cannot be handled. The problem can be effectively solved by using Large Language Models (LLMs), but significant room for exploration remains in this early-stage research area. A multi-stage generative heuristic-enhanced prompt framework is proposed in this study to enhance the ability of LLMs to recognize tenors, vehicles, and grounds in Chinese metaphors. In the first stage, a small model is trained to obtain the required confidence score for answer candidate generation. In the second stage, questions are clustered and sampled according to specific rules. Finally, the heuristic-enhanced prompt needed is formed by combining the generated answer candidates and demonstrations. The proposed model achieved 3rd place in Track 1 of Subtask 1, 1st place in Track 2 of Subtask 1, and 1st place in both tracks of Subtask 2 at the NLPCC-2024 Shared Task 9.

Enabling humanoid robots to perform autonomously loco-manipulation in unstructured environments is crucial and highly challenging for achieving embodied intelligence. This involves robots being able to plan their actions and behaviors in long-horizon tasks while using multi-modality to perceive deviations between task execution and high-level planning. Recently, large language models (LLMs) have demonstrated powerful planning and reasoning capabilities for comprehension and processing of semantic information through robot control tasks, as well as the usability of analytical judgment and decision-making for multi-modal inputs. To leverage the power of LLMs towards humanoid loco-manipulation, we propose a novel language-model based framework that enables robots to autonomously plan behaviors and low-level execution under given textual instructions, while observing and correcting failures that may occur during task execution. To systematically evaluate this framework in grounding LLMs, we created the robot 'action' and 'sensing' behavior library for task planning, and conducted mobile manipulation tasks and experiments in both simulated and real environments using the CENTAURO robot, and verified the effectiveness and application of this approach in robotic tasks with autonomous behavioral planning., Comment: Paper accepted by IROS 2024

The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice questions, making it the most extensive benchmark of its kind. Our evaluation of 24 popular LVLMs, including both open-source and proprietary models, reveals significant challenges in multi-image comprehension, particularly in tasks involving spatial understanding. Even the most advanced models, such as GPT-4o, achieve only 55.7% accuracy on MMIU. Through multi-faceted analytical experiments, we identify key performance gaps and limitations, providing valuable insights for future model and data improvements. We aim for MMIU to advance the frontier of LVLM research and development, moving us toward achieving sophisticated multimodal multi-image user interactions., Comment: Project Page: https://mmiu-bench.github.io/

Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding prompts into language models (LMs). Common methodologies include integrating prompts at the input layer or introducing learnable variables at each transformer layer. Nonetheless, each strategy exhibits inherent limitations. Prompts integrated at the input layer risk underutilization, with their impact potentially diminishing across successive transformer layers. Conversely, the addition of learnable variables to each layer can complicate the training process and increase inference latency. To tackle the issues mentioned above, this paper proposes Dual Low-Rank Adaptation (DualLoRA), a plug-and-play architecture designed for zero-shot DST. DualLoRA incorporates two distinct Low-Rank Adaptation (LoRA) components, targeting both dialogue context processing and prompt optimization, to ensure the comprehensive influence of prompts throughout the transformer model layers. This is achieved without incurring additional inference latency, showcasing an efficient integration into existing architectures. Through rigorous evaluation on the MultiWOZ and SGD datasets, DualLoRA demonstrates notable improvements across multiple domains, outperforming traditional baseline methods in zero-shot settings. Our code is accessible at: \url{https://github.com/suntea233/DualLoRA}., Comment: Accepted by ACL 2024

Recovering pressure fields from image velocimetry measurements has two general strategies: i) directly integrating the pressure gradients from the momentum equation and ii) solving or enforcing the pressure Poisson equation (divergence of the pressure gradients). In this work, we analyze the error propagation of the former strategy and provide some practical insights. For example, we establish the error scaling laws for the Pressure Gradient Integration (PGI) and the Pressure Poisson Equation (PPE). We explain why applying the Helmholtz-Hodge Decomposition (HHD) could significantly reduce the error propagation for the PGI. We also propose to use a novel HHD-based pressure field reconstruction strategy that offers the following advantages: i) effective processing of noisy scattered or structured image velocimetry data on a complex domain and ii) using Radial Basis Functions (RBFs) with curl/divergence-free kernels to provide divergence-free correction to the velocity fields for incompressible flows and curl-free correction for pressure gradients. Complete elimination of divergence-free bias in measured pressure gradient and curl-free bias in the measured velocity field results in superior accuracy. Synthetic velocimetry data based on exact solutions and high-fidelity simulations are used to validate the analysis as well as demonstrate the flexibility and effectiveness of the RBF-HHD solver.

In conventional path integral quantum mechanics, the integral variables are the canonical variables of Hamiltonian mechanics. We show that these integral variables can be transformed into the spacetime metric, leading to a new representation of quantum mechanics. We show that the wave-particle duality can be interpreted as the uncertainty of spacetime for the particle. Summarizing all possible trajectories in conventional path integral quantum mechanics can be transformed into the summation of all possible spacetime metrics. We emphasize that in conventional quantum gravity, it is possible that the classical matter fields correspond to the quantum spacetime. We argue that this is not quite reasonable and propose a new path integral quantum gravity model based on the new interpretation of wave-particle duality. In this model, the aforementioned drawback of conventional quantum gravity naturally disappears.

Root Cause Analysis (RCA) aims at identifying the underlying causes of system faults by uncovering and analyzing the causal structure from complex systems. It has been widely used in many application domains. Reliable diagnostic conclusions are of great importance in mitigating system failures and financial losses. However, previous studies implicitly assume a full observation of the system, which neglect the effect of partial observation (i.e., missing nodes and latent malfunction). As a result, they fail in deriving reliable RCA results. In this paper, we unveil the issues of unobserved confounders and heterogeneity in partial observation and come up with a new problem of root cause analysis with partially observed data. To achieve this, we propose PORCA, a novel RCA framework which can explore reliable root causes under both unobserved confounders and unobserved heterogeneity. PORCA leverages magnified score-based causal discovery to efficiently optimize acyclic directed mixed graph under unobserved confounders. In addition, we also develop a heterogeneity-aware scheduling strategy to provide adaptive sample weights. Extensive experimental results on one synthetic and two real-world datasets demonstrate the effectiveness and superiority of the proposed framework.

Perceptual rivalry, where conflicting sensory information leads to alternating perceptions crucial for associated cognitive function, has attracted researcher's attention for long. Despite progresses being made, recent studies have revealed limitations and inconsistencies in our understanding across various rivalry contexts. We develop a unified physical framework, where perception undergoes a consecutive phase transition process encompassing different multi-state competitions. We reveal the underlying mechanisms of perceptual rivalry by identifying dominant switching paths among perceptual states and quantifying mean perceptual durations, switching frequencies, and proportions of different perceptions. We uncover the underlying nonequilibrium dynamics and thermodynamics by analyzing average nonequilibrium flux and entropy production rate, while associated time series irreversibility reflects the underlying nonequilibrium mechanism of perceptual rivalry and link thermodynamical results with neuro-electrophysiological experiments. Our framework provides a global and physical understanding of brain perception, which may go beyond cognitive science or psychology but embodies the connection with wider fields as decision-making., Comment: 26 pages, 10 figures

The minimum seesaw model with two right-handed neutrinos is considered, where the lightest neutrino is naturally massless. Instead of adopting texture zeros in the lepton Yukawa matrices, which cause both theoretical and experimental troubles, here we propose two-$\boldsymbol\epsilon$ textures, where $\boldsymbol\epsilon$ is a small number. Combined with neutrino oscillation experimental data, we find that a large CP angle is preferred for the normal neutrino mass order. In contrast, the CP angle almost vanishes for the inverted order. This can be well-tested in near-future experiments, such as Hyper-Kamiokande. Besides, the predicted effective Majorana neutrino mass $m_{ee}$ and the total neutrino mass $\sum m^\nu_i$ are also within reach of ongoing or future experiments., Comment: 6 pages, 6 figures,1 table

Enabling robots to autonomously perform hybrid motions in diverse environments can be beneficial for long-horizon tasks such as material handling, household chores, and work assistance. This requires extensive exploitation of intrinsic motion capabilities, extraction of affordances from rich environmental information, and planning of physical interaction behaviors. Despite recent progress has demonstrated impressive humanoid whole-body control abilities, they struggle to achieve versatility and adaptability for new tasks. In this work, we propose HYPERmotion, a framework that learns, selects and plans behaviors based on tasks in different scenarios. We combine reinforcement learning with whole-body optimization to generate motion for 38 actuated joints and create a motion library to store the learned skills. We apply the planning and reasoning features of the large language models (LLMs) to complex loco-manipulation tasks, constructing a hierarchical task graph that comprises a series of primitive behaviors to bridge lower-level execution with higher-level planning. By leveraging the interaction of distilled spatial geometry and 2D observation with a visual language model (VLM) to ground knowledge into a robotic morphology selector to choose appropriate actions in single- or dual-arm, legged or wheeled locomotion. Experiments in simulation and real-world show that learned motions can efficiently adapt to new tasks, demonstrating high autonomy from free-text commands in unstructured scenes. Videos and website: hy-motion.github.io/, Comment: Project page: https://hy-motion.github.io/

We study the fidelity of information retrieval in the black hole final state model by taking into account the interactions between the collapsing matter and the infalling Hawking radiation inside the event horizon. By utilizing a scrambling unitary operator to model these interactions, our direct calculations suggest that the information is almost lost during the process of black hole evaporation. We then proceed to employ the Yoshida-Kitaev decoding strategy for information retrieval. Although we observe a finite improvement in decoding fidelity, it does not reach unity. This indicates that the issue of unitarity in black hole evaporation may not be fully resolved within the framework of the final state model.

Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases. Towards this goal, there is a notable shift to building compound AI systems, wherein LLMs are integrated into an expansive software infrastructure with many components like models, retrievers, databases and tools. In this paper, we introduce a blueprint architecture for compound AI systems to operate in enterprise settings cost-effectively and feasibly. Our proposed architecture aims for seamless integration with existing compute and data infrastructure, with ``stream'' serving as the key orchestration concept to coordinate data and instructions among agents and other components. Task and data planners, respectively, break down, map, and optimize tasks and data to available agents and data sources defined in respective registries, given production constraints such as accuracy and latency., Comment: Compound AI Systems Workshop at the Data+AI Summit 2024

High precision gyroscopes in space are important for sophisticated scientific experiments and deep space navigation. Microgravity in the space provides an ideal condition for operation of a cold atom gyroscope. To demonstrate this advantage, an atom interferometer (AI) was launched and installed in the China Space Station in 2022. Here reported is a realization of the cold atom gyroscope with this AI. By applying point source interferometry, spatial fringes are obtained and acceleration and rotation are extracted. The angles of the Raman lasers are precisely calibrated to avoid measurement error, and other systematic errors are also considered for the rotation measurement. The evaluated rotation measurement is (-115.64+/-1.71)*10^-5 rad/s in space, and an acceleration measurement resolution of 1.03*10^-6 m/s^2 is also obtained for a single image. This study conducts the first AI-based gyroscope in space and paves a way for future space-based AI experiments., Comment: 12 pages, 5 figures

This paper focuses on the area of RGB(visible)-NIR(near-infrared) cross-modality image registration, which is crucial for many downstream vision tasks to fully leverage the complementary information present in visible and infrared images. In this field, researchers face two primary challenges - the absence of a correctly-annotated benchmark with viewpoint variations for evaluating RGB-NIR cross-modality registration methods and the problem of inconsistent local features caused by the appearance discrepancy between RGB-NIR cross-modality images. To address these challenges, we first present the RGB-NIR Image Registration (RGB-NIR-IRegis) benchmark, which, for the first time, enables fair and comprehensive evaluations for the task of RGB-NIR cross-modality image registration. Evaluations of previous methods highlight the significant challenges posed by our RGB-NIR-IRegis benchmark, especially on RGB-NIR image pairs with viewpoint variations. To analyze the causes of the unsatisfying performance, we then design several metrics to reveal the toxic impact of inconsistent local features between visible and infrared images on the model performance. This further motivates us to develop a baseline method named Semantic Guidance Transformer (SGFormer), which utilizes high-level semantic guidance to mitigate the negative impact of local inconsistent features. Despite the simplicity of our motivation, extensive experimental results show the effectiveness of our method., Comment: 18 pages, 7 figures

Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects and provides deeper market insights to businesses and organizations. With the emergence of large language models (LMs), recent studies have proposed using fixed examples for instruction tuning to reformulate ABSA as a generation task. However, the performance is sensitive to the selection of in-context examples; several retrieval methods are based on surface similarity and are independent of the LM generative objective. This study proposes an instruction learning method with retrieval-based example ranking for ABSA tasks. For each target sample, an LM was applied as a scorer to estimate the likelihood of the output given the input and a candidate example as the prompt, and training examples were labeled as positive or negative by ranking the scores. An alternating training schema is proposed to train both the retriever and LM. Instructional prompts can be constructed using high-quality examples. The LM is used for both scoring and inference, improving the generation efficiency without incurring additional computational costs or training difficulties. Extensive experiments on three ABSA subtasks verified the effectiveness of the proposed method, demonstrating its superiority over various strong baseline models. Code and data are released at https://github.com/zgMin/IT-RER-ABSA., Comment: ACL Findings 2024

Compositional reasoning capabilities are usually considered as fundamental skills to characterize human perception. Recent studies show that current Vision Language Models (VLMs) surprisingly lack sufficient knowledge with respect to such capabilities. To this end, we propose to thoroughly diagnose the composition representations encoded by VLMs, systematically revealing the potential cause for this weakness. Specifically, we propose evaluation methods from a novel game-theoretic view to assess the vulnerability of VLMs on different aspects of compositional understanding, e.g., relations and attributes. Extensive experimental results demonstrate and validate several insights to understand the incapabilities of VLMs on compositional reasoning, which provide useful and reliable guidance for future studies. The deliverables will be updated at https://vlms-compositionality-gametheory.github.io/., Comment: 21 pages, 8 figures

User Simulators play a pivotal role in training and evaluating task-oriented dialogue systems. Traditional user simulators typically rely on human-engineered agendas, resulting in generated responses that often lack diversity and spontaneity. Although large language models (LLMs) exhibit a remarkable capacity for generating coherent and contextually appropriate utterances, they may fall short when tasked with generating responses that effectively guide users towards their goals, particularly in dialogues with intricate constraints and requirements. This paper introduces DuetSim, a novel framework designed to address the intricate demands of task-oriented dialogues by leveraging LLMs. DuetSim stands apart from conventional approaches by employing two LLMs in tandem: one dedicated to response generation and the other focused on verification. This dual LLM approach empowers DuetSim to produce responses that not only exhibit diversity but also demonstrate accuracy and are preferred by human users. We validate the efficacy of our method through extensive experiments conducted on the MultiWOZ dataset, highlighting improvements in response quality and correctness, largely attributed to the incorporation of the second LLM. Our code is accessible at: https://github.com/suntea233/DuetSim., Comment: Accepted by COLING 2024

Chain of thought (CoT) has proven useful for problems requiring complex reasoning. Many of these problems are both textual and multimodal. Given the inputs in different modalities, a model generates a rationale and then uses it to answer a question. Because of the hallucination issue, the generated soft negative rationales with high textual quality but illogical semantics do not always help improve answer accuracy. This study proposes a rationale generation method using soft negative sampling (SNSE-CoT) to mitigate hallucinations in multimodal CoT. Five methods were applied to generate soft negative samples that shared highly similar text but had different semantics from the original. Bidirectional margin loss (BML) was applied to introduce them into the traditional contrastive learning framework that involves only positive and negative samples. Extensive experiments on the ScienceQA dataset demonstrated the effectiveness of the proposed method. Code and data are released at https://github.com/zgMin/SNSE-CoT., Comment: Accepted by LREC-COLING 2024

We propose that the thermodynamics and the kinetics of state switching for the asymptotically flat black hole enclosed by a cavity can be studied in terms of the free energy landscape formalism. The generalized free energy for the black hole enclosed by a cavity in the canonical ensemble is derived by using the York's approach, where the temperature on the cavity and the charges inside the cavity are kept as the fixed parameters. By quantifying the corresponding free energy landscape, we obtain the phase diagrams for the black hole in cavity, which reveal a Hawking-Page type transition for the uncharged black hole and a Van der Waals type transition for the charged black hole. We further assume that the dynamics of black hole state switching is mutually determined by the gradient force and the stochastic force arising from the free energy landscape and the thermal noises respectively. We then derive a recurrence relation for the $n$-momentum of the first passage time distribution function, which enables the calculation of the kinetic times characterized by the mean first passage time and its relative fluctuation. Our analysis illustrates that the kinetics of black hole state switching is determined by the ensemble temperature and the barrier height on the free energy landscape.

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise similarity as a key prior guidance for the decoder. However, such a prior representation suffers from coarse granularity and poor generalization to new classes since these high-level feature maps have obvious category bias. In this work, we propose to replace the visual prior representation with the visual-text alignment capacity to capture more reliable guidance and enhance the model generalization. Specifically, we design two kinds of training-free prior information generation strategy that attempts to utilize the semantic alignment capability of the Contrastive Language-Image Pre-training model (CLIP) to locate the target class. Besides, to acquire more accurate prior guidance, we build a high-order relationship of attention maps and utilize it to refine the initial prior information. Experiments on both the PASCAL-5{i} and COCO-20{i} datasets show that our method obtains a clearly substantial improvement and reaches the new state-of-the-art performance., Comment: Accepted by CVPR 2024; The camera-ready version

The pre-training for language models captures general language understanding but fails to distinguish the affective impact of a particular context to a specific word. Recent works have sought to introduce contrastive learning (CL) for sentiment-aware pre-training in acquiring affective information. Nevertheless, these methods present two significant limitations. First, the compatibility of the GPU memory often limits the number of negative samples, hindering the opportunities to learn good representations. In addition, using only a few sentiment polarities as hard labels, e.g., positive, neutral, and negative, to supervise CL will force all representations to converge to a few points, leading to the issue of latent space collapse. This study proposes a soft momentum contrastive learning (SoftMCL) for fine-grained sentiment-aware pre-training. Instead of hard labels, we introduce valence ratings as soft-label supervision for CL to fine-grained measure the sentiment similarities between samples. The proposed SoftMCL is conducted on both the word- and sentence-level to enhance the model's ability to learn affective information. A momentum queue was introduced to expand the contrastive samples, allowing storing and involving more negatives to overcome the limitations of hardware platforms. Extensive experiments were conducted on four different sentiment-related tasks, which demonstrates the effectiveness of the proposed SoftMCL method. The code and data of the proposed SoftMCL is available at: https://www.github.com/wangjin0818/SoftMCL/., Comment: Accepted by LREC-COLING 2024

In the circuit quantum electrodynamics architectures, to realize a long-range quantum network mediated by flying photon, it is necessary to shape the temporal profile of emitted photons to achieve high transfer efficiency between two quantum nodes. In this work, we demonstrate a new single-rail and dual-rail time-bin shaped photon generator without additional flux-tunable elements, which can act as a quantum interface of a point-to-point quantum network. In our approach, we adopt a qubit-resonator-transmission line configuration, and the effective coupling strength between the qubit and the resonator can be varied by parametrically modulating the qubit frequency. In this way, the coupling is directly proportional to the parametric modulation amplitude and covers a broad tunable range beyond 20 MHz for the sample we used. Additionally, when emitting shaped photons, we find that the spurious frequency shift (-0.4 MHz) due to parametric modulation is small and can be readily calibrated through chirping. We develop an efficient photon field measurement setup based on the data stream processing of GPU. Utilizing this system, we perform photon temporal profile measurement, quantum state tomography of photon field, and quantum process tomography of single-rail quantum state transfer based on a heterodyne measurement scheme. The single-rail encoding state transfer fidelity of shaped photon emission is 90.32%, and that for unshaped photon is 97.20%, respectively. We believe that the fidelity of shaped photon emission is mainly limited by the qubit coherence time. The results demonstrate that our method is hardware efficient, simple to implement, and scalable. It could become a viable tool in a high-quality quantum network utilizing both single-rail and dual-rail time-bin encoding.

Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering $32$ core meta-tasks and $162$ subtasks in multimodal understanding. Due to its extensive task coverage, MMT-Bench enables the evaluation of LVLMs using a task map, facilitating the discovery of in- and out-of-domain tasks. Evaluation results involving $30$ LVLMs such as the proprietary GPT-4V, GeminiProVision, and open-sourced InternVL-Chat, underscore the significant challenges posed by MMT-Bench. We anticipate that MMT-Bench will inspire the community to develop next-generation multimodal foundation models aimed at achieving general-purpose multimodal intelligence., Comment: 77 pages, 41 figures

Automated dialogue systems are important applications of artificial intelligence, and traditional systems struggle to understand user emotions and provide empathetic feedback. This study integrates emotional intelligence technology into automated dialogue systems and creates a dialogue generation model with emotional intelligence through deep learning and natural language processing techniques. The model can detect and understand a wide range of emotions and specific pain signals in real time, enabling the system to provide empathetic interaction. By integrating the results of the study "Can artificial intelligence detect pain and express pain empathy?", the model's ability to understand the subtle elements of pain empathy has been enhanced, setting higher standards for emotional intelligence dialogue systems. The project aims to provide theoretical understanding and practical suggestions to integrate advanced emotional intelligence capabilities into dialogue systems, thereby improving user experience and interaction quality.

With the rapid advancement of technology, Augmented Reality (AR) technology, known for its ability to deeply integrate virtual information with the real world, is gradually transforming traditional work modes and teaching methods. Particularly in the realms of remote work and online education, AR technology demonstrates a broad spectrum of application prospects. This paper delves into the application potential and actual effects of AR technology in remote work and education. Through a systematic literature review, this study outlines the key features, advantages, and challenges of AR technology. Based on theoretical analysis, it discusses the scientific basis and technical support that AR technology provides for enhancing remote work efficiency and promoting innovation in educational teaching models. Additionally, by designing an empirical research plan and analyzing experimental data, this article reveals the specific performance and influencing factors of AR technology in practical applications. Finally, based on the results of the experiments, this research summarizes the application value of AR technology in remote work and education, looks forward to its future development trends, and proposes forward-looking research directions and strategic suggestions, offering empirical foundation and theoretical guidance for further promoting the in-depth application of AR technology in related fields.

The discovery of drug-target interactions (DTIs) plays a crucial role in pharmaceutical development. The deep learning model achieves more accurate results in DTI prediction due to its ability to extract robust and expressive features from drug and target chemical structures. However, existing deep learning methods typically generate drug features via aggregating molecular atom representations, ignoring the chemical properties carried by motifs, i.e., substructures of the molecular graph. The atom-drug double-level molecular representation learning can not fully exploit structure information and fails to interpret the DTI mechanism from the motif perspective. In addition, sequential model-based target feature extraction either fuses limited contextual information or requires expensive computational resources. To tackle the above issues, we propose a hierarchical graph representation learning-based DTI prediction method (HiGraphDTI). Specifically, HiGraphDTI learns hierarchical drug representations from triple-level molecular graphs to thoroughly exploit chemical information embedded in atoms, motifs, and molecules. Then, an attentional feature fusion module incorporates information from different receptive fields to extract expressive target features.Last, the hierarchical attention mechanism identifies crucial molecular segments, which offers complementary views for interpreting interaction mechanisms. The experiment results not only demonstrate the superiority of HiGraphDTI to the state-of-the-art methods, but also confirm the practical ability of our model in interaction interpretation and new DTI discovery.

In the realm of video object segmentation (VOS), the challenge of operating under low-light conditions persists, resulting in notably degraded image quality and compromised accuracy when comparing query and memory frames for similarity computation. Event cameras, characterized by their high dynamic range and ability to capture motion information of objects, offer promise in enhancing object visibility and aiding VOS methods under such low-light conditions. This paper introduces a pioneering framework tailored for low-light VOS, leveraging event camera data to elevate segmentation accuracy. Our approach hinges on two pivotal components: the Adaptive Cross-Modal Fusion (ACMF) module, aimed at extracting pertinent features while fusing image and event modalities to mitigate noise interference, and the Event-Guided Memory Matching (EGMM) module, designed to rectify the issue of inaccurate matching prevalent in low-light settings. Additionally, we present the creation of a synthetic LLE-DAVIS dataset and the curation of a real-world LLE-VOS dataset, encompassing frames and events. Experimental evaluations corroborate the efficacy of our method across both datasets, affirming its effectiveness in low-light scenarios., Comment: CVPR 2024

The systematic error induced by the quadratic Zeeman effect is non-negligible in atom interferometers and must be precisely evaluated. We theoretically analyze the phase shift induced by the Zeeman effect, and use a hyperfine ground state exchange (HGSE) method to evaluate the systematic error in the long-baseline $^{85}$Rb-$^{87}$Rb dual-species atom interferometer due to the quadratic Zeeman effect. Compared to the two evaluation methods, mapping the absolute magnetic field in the interference region and performing phase measurements at different bias fields, the HGSE method could obtain the systematic error in real time in case of slow drifts of either the ambient magnetic field or other systematic effects irrelevant to the hyperfine ground states. To validate the effectiveness of the HGSE method, we also employ the mapping magnetic field method and modulating bias field method independently to cross-check and yield consistent results of three methods within an accuracy of $10^{-11}$ level. The HGSE method is helpful in evaluating and suppressing the quadratic Zeeman-effect-induced systematic error in long-baseline atom interferometer-based precision measurements, such as equivalence principle tests.

Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected with equal probability when constructing mini-batches. However, the intrinsic class imbalance in multi-label data may bias the model towards majority labels, since samples relevant to minority labels may be underrepresented in each mini-batch. Meanwhile, during the training process, we observe that instances associated with minority labels tend to induce greater losses. Existing heuristic batch selection methods, such as priority selection of samples with high contribution to the objective function, i.e., samples with high loss, have been proven to accelerate convergence while reducing the loss and test error in single-label data. However, batch selection methods have not yet been applied and validated in multi-label data. In this study, we introduce a simple yet effective adaptive batch selection algorithm tailored to multi-label deep learning models. It adaptively selects each batch by prioritizing hard samples related to minority labels. A variant of our method also takes informative label correlations into consideration. Comprehensive experiments combining five multi-label deep learning models on thirteen benchmark datasets show that our method converges faster and performs better than random batch selection.

We study the axion and axion-like particle production from the $\eta\to\pi\pi a$ decay within the $SU(3)$ chiral perturbation theory up to the one-loop level. The conventional $SU(3)$ chiral low energy constants are found to be able to reabsorb all the divergences from the chiral loops in the $\eta\to\pi\pi a$ decay amplitude, and hence render the amplitude independent of the renormalization scale. The unitarized $\eta\to\pi\pi a$ decay amplitudes are constructed to take into account the $\pi\pi$ final-state interactions and also properly reproduce the perturbative results from the chiral perturbation theory. Detailed analyses between the perturbative amplitudes and the unitarized ones are given in the phenomenological discussions. By taking the values of the chiral low energy constants in literature, we predict the Dalitz distributions, the spectra of the $\pi\pi$ and $a\pi$ systems, and also the branching ratios of the $\eta\to\pi\pi a$ process by varying $m_a$ from 0 to $m_\eta-2m_{\pi}$., Comment: 25 pages, 7 figures

Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth training data such as images based on model gradients. However, reconstructing high-resolution images by existing GIAs faces two challenges: inferior accuracy and slow-convergence, especially when duplicating labels exist in the training batch. To address these challenges, we present an Accurate and Fast-convergent Gradient Inversion attack algorithm, called AFGI, with two components: Label Recovery Block (LRB) which can accurately restore duplicating labels of private images based on exposed gradients; VME Regularization Term, which includes the total variance of reconstructed images, the discrepancy between three-channel means and edges, between values from exposed gradients and reconstructed images, respectively. The AFGI can be regarded as a white-box attack strategy to reconstruct images by leveraging labels recovered by LRB. In particular, AFGI is efficient that accurately reconstruct ground-truth images when users' training batch size is up to 48. Our experimental results manifest that AFGI can diminish 85% time costs while achieving superb inversion quality in the ImageNet dataset. At last, our study unveils the shortcomings of FL in privacy-preservation, prompting the development of more advanced countermeasure strategies.

As a new distributed computing framework that can protect data privacy, federated learning (FL) has attracted more and more attention in recent years. It receives gradients from users to train the global model and releases the trained global model to working users. Nonetheless, the gradient inversion (GI) attack reflects the risk of privacy leakage in federated learning. Attackers only need to use gradients through hundreds of thousands of simple iterations to obtain relatively accurate private data stored on users' local devices. For this, some works propose simple but effective strategies to obtain user data under a single-label dataset. However, these strategies induce a satisfactory visual effect of the inversion image at the expense of higher time costs. Due to the semantic limitation of a single label, the image obtained by gradient inversion may have semantic errors. We present a novel gradient inversion strategy based on canny edge detection (MGIC) in both the multi-label and single-label datasets. To reduce semantic errors caused by a single label, we add new convolution layers' blocks in the trained model to obtain the image's multi-label. Through multi-label representation, serious semantic errors in inversion images are reduced. Then, we analyze the impact of parameters on the difficulty of input image reconstruction and discuss how image multi-subjects affect the inversion performance. Our proposed strategy has better visual inversion image results than the most widely used ones, saving more than 78% of time costs in the ImageNet dataset.

Effectively and efficiently adapting a pre-trained language model (PLM) for human-centered text understanding (HCTU) is challenging since user tokens are million-level in most personalized applications and do not have concrete explicit semantics. A standard and parameter-efficient approach (e.g., LoRA) necessitates memorizing numerous suits of adapters for each user. In this work, we introduce a personalized LoRA (PLoRA) with a plug-and-play (PnP) framework for the HCTU task. PLoRA is effective, parameter-efficient, and dynamically deploying in PLMs. Moreover, a personalized dropout and a mutual information maximizing strategies are adopted and hence the proposed PLoRA can be well adapted to few/zero-shot learning scenarios for the cold-start issue. Experiments conducted on four benchmark datasets show that the proposed method outperforms existing methods in full/few/zero-shot learning scenarios for the HCTU task, even though it has fewer trainable parameters. For reproducibility, the code for this paper is available at: https://github.com/yoyo-yun/PLoRA., Comment: Accepted by AAAI 2024

The question "Can machines think?" and the Turing Test to assess whether machines could achieve human-level intelligence is one of the roots of AI. With the philosophical argument "I think, therefore I am", this paper challenge the idea of a "thinking machine" supported by current AIs since there is no sense of self in them. Current artificial intelligence is only seemingly intelligent information processing and does not truly understand or be subjectively aware of oneself and perceive the world with the self as human intelligence does. In this paper, we introduce a Brain-inspired and Self-based Artificial Intelligence (BriSe AI) paradigm. This BriSe AI paradigm is dedicated to coordinating various cognitive functions and learning strategies in a self-organized manner to build human-level AI models and robotic applications. Specifically, BriSe AI emphasizes the crucial role of the Self in shaping the future AI, rooted with a practical hierarchical Self framework, including Perception and Learning, Bodily Self, Autonomous Self, Social Self, and Conceptual Self. The hierarchical framework of the Self highlights self-based environment perception, self-bodily modeling, autonomous interaction with the environment, social interaction and collaboration with others, and even more abstract understanding of the Self. Furthermore, the positive mutual promotion and support among multiple levels of Self, as well as between Self and learning, enhance the BriSe AI's conscious understanding of information and flexible adaptation to complex environments, serving as a driving force propelling BriSe AI towards real Artificial General Intelligence.

The inherent polarization gradients in tight optical tweezers can be used to couple the atomic spins to the two-body motion under the action of a microwave spin-flip transition, so that such a spin-motion coupling offers an important control knob on the motional states of optically trapped two colliding atoms. Here, after preparing two elastically scattering $^{85}$Rb atoms in the three-dimensional ground-state in the optical tweezer, we employed this control in order to probe the colliding energies of elastic and inelastic channels. The combination of microwave spectra and corresponding s-wave pseudopotential model allows us to infer the effect of the state-dependent trapping potentials on the elastic colliding energies, as well as to reveal how the presence of inelastic interactions affects elastic part of the relative potential. Our work shows that the spin-motion coupling in a tight optical tweezer expand the experimental toolbox for fundamental studies of ultracold collisions in the two body systems with reactive collisions, and potentially for that of more complex interactions, such as optically trapped atom-molecule and molecule-molecule interactions., Comment: 8 pages, 5 figures

Many nano and quantum devices, with their sizes often spanning from millimeters down to sub-nanometer, have intricate low-dimensional, non-uniform, or hierarchical structures on surfaces and interfaces. Since their functionalities are dependent on these structures, high-resolution surface-sensitive characterization becomes imperative to gain a comprehensive understanding of the function-structure relationship. We thus developed hard X-ray ptychographic reflectometry imaging, a new technique that merges the high-resolution two-dimensional imaging capabilities of hard X-ray ptychography for extended objects, with the high-resolution depth profiling capabilities of X-ray reflectivity for layered structures. The synergy of these two methods fully leverages both amplitude and phase information from ptychography reconstruction to not only reveal surface topography and localized structures such as shapes and electron densities, but also yields statistical details such as interfacial roughness that is not readily accessible through coherent imaging solely. The hard X-ray ptychographic reflectometry imaging is well-suited for three-dimensional imaging of mesoscopic samples, particularly those comprising planar or layered nanostructures on opaque supports, and could also offer a high-resolution surface metrology and defect analysis on semiconductor devices such as integrated nanocircuits and lithographic photomasks for microchip fabrications., Comment: 43 pages, 11 figures

The Mpemba effect was originally referred to as the faster icing of a higher-temperature system than a lower-temperature system, and was later generalized to anomalous decays of both classical and quantum observables to equilibrium states. Mpemba effect is mostly considered in classical systems and during cooling processes towards equilibrium states. We investigate the emergence of the effect in nonequilibrium quantum systems where the system has no asymptotic equilibrium state to approach. Instead, the system is put in contact with two different baths, and only a nonequilibrium state exists, sustained by constant energy injection from the surrounding thermal baths. Firstly, we show that the nonequilibrium conditions can dramatically enlarge the parameter regimes where the MPE emerges. Secondly, we demonstrate that the anomalous MPEs and inverse MPEs emerge in the evolution of quantum correlations in the two-site fermionic system and that nonequilibrium conditions can expedite or delay the MPEs. Thirdly, we show that the nonequilibrium-induced quantum coherence can have considerable contributions to the emergence of the MPE which the conventional Lindbladian dynamics fails to capture., Comment: 6 pages. Typos are corrected, two figures are added, and some other minor modifications are made

We studied the Hayden-Preskill thought experiment with the local projective measurement. Compared to the original model, the measurement is applied on the Hawking radiation that was emitted after throwing the quantum diary into the black hole. Within this setup, we explored various aspects of this model, including the information recovery from the black hole, the relation to the black hole final state proposal, the relation between the Yoshida-Kitaev protocol and Petz recovery map, the effects of the decoherence, and the quantum simulations of the decoding protocols. These aspects may provide us new insights into the non-perturbative nature of quantum black holes.

Spin is one fundamental property of microscopic particles. A lot of theoretical work postulated the possible coupling between spin and gravitation, which could result in the violation of equivalence principle. In a recent joint mass-and-energy test of weak equivalence principle (WEP) with a 10-meter $^{85}$Rb-$^{87}$Rb dual-species atom interferometer, the E${\rm \ddot{o}}$tv${\rm \ddot{o}}$s parameters of four $^{85}$Rb-$^{87}$Rb combinations with specific atomic spin states were measured to the $10^{-10}$-level. These experimental results are used to constrain the postulated spin-gravity coupling effects in a robust way. The bounds on the spin-independent and spin-dependent anomalous passive gravitational mass tensors are consistently set to the $10^{-10}$-level, which improve existing bounds by three orders of magnitude., Comment: 4 pages, 2 figures

The wear-free sliding of layers or flakes of graphene-like 2D materials, important in many experimental systems, may occur either smoothly or through stick-slip, depending on driving conditions, corrugation, twist angles, as well as edges and defects. No single parameter has been so far identified to discriminate a priori between the two sliding regimes. Such a parameter, $\eta$, does exist in the ideal (Prandtl-Tomlinson) problem of a point particle sliding across a 1D periodic lattice potential. In that case $\eta >1$ implies mechanical instability, generally leading to stick-slip, with $\eta = \frac{2\pi^2 U_0}{K_\mathrm{p} a^2}$, where $U_0$ is the potential magnitude, $a$ the lattice spacing, and $K_\mathrm{p}$ the pulling spring constant. Here we show, supported by a repertoire of graphene flake/graphene sliding simulations, that a similar stick-slip predictor $\eta_\mathrm{eff}$ can be defined with the same form but suitably defined $U_\mathrm{eff}$, $a_\mathrm{eff}$ and $K_\mathrm{eff}$. Remarkably, simulations show that $a_\mathrm{eff} = a$ of the substrate remains an excellent approximation, while $K_\mathrm{eff}$ is an effective stiffness parameter, combining equipment and internal elasticity. Only the effective energy barrier $U_\mathrm{eff}$ needs to be estimated in order to predict whether stick-slip sliding of a 2D island or extended layer is expected or not. In a misaligned defect-free circular graphene sliding island of contact area $A$, we show that $U_\mathrm{eff}$, whose magnitude for a micrometer size diameter is of order 1 eV, scales as $A^{1/4}$, thus increasing very gently with size. The PT-like parameter $\eta_\mathrm{eff}$ is therefore proposed as a valuable tool in 2D layer sliding., Comment: submitted to Physical Review B

Noise plays a crucial role in the regulation of cellular and organismal function and behavior. Exploring noise's impact is key to understanding fundamental biological processes, such as gene expression, signal transduction, and the mechanisms of development and evolution. Currently, a comprehensive method to quantify dynamical behavior of cellular noise within these biochemical systems is lacking. In this study, we introduce an optically-controlled perturbation system utilizing the light-sensitive Phytochrome B (PhyB) from \textit{Arabidopsis thaliana}, which enables precise noise modulation with high spatial-temporal resolution. Our system exhibits exceptional sensitivity to light, reacting consistently to pulsed light signals, distinguishing it from other photoreceptor-based promoter systems that respond to a single light wavelength. To characterize our system, we developed a stochastic model for phytochromes that accounts for photoactivation/deactivation, thermal reversion, and the dynamics of the light-activated gene promoter system. To precisely control our system, we determined the rate constants for this model using an omniscient deep neural network that can directly map rate constant combinations to time-dependent state joint distributions. By adjusting the activation rates through light intensity and degradation rates via N-terminal mutagenesis, we illustrate that out optical-controlled perturbation can effectively modulate molecular expression level as well as noise. Our results highlight the potential of employing an optically-controlled gene perturbation system as a noise-controlled stimulus source. This approach, when combined with the analytical capabilities of a sophisticated deep neural network, enables the accurate estimation of rate constants from observational data in a broad range of biochemical reaction networks., Comment: 33 pages, 4 figures

We calculate the form factors for the baryon number violation processes of a heavy-flavor baryon decaying into a pseudoscalar meson and a lepton. In the framework of the Standard Model effective field theory, the leptoquark operators at the bottom quark scale, whose matrix elements define the form factors, are derived by integrating out the high energy physics. Under the QCD factorization approach, the form factors of the baryon number violation processes at leading power can be factorized into the convolution of the long-distance hadron wave functions as well as the short-distance hard and jet functions representing the hard scale and hard-collinear scale effects, separately. Based on measurements of the baryon number violation processes by LHCb, we further impose constraints on the new physics constants of leptoquark operators., Comment: 13 pages, 3 figures

The decay of sunspot plays a key role in magnetic flux transportation in solar active regions (ARs). To better understand the physical mechanism of the entire decay process of a sunspot, an {\alpha}-configuration sunspot in AR NOAA 12411 was studied. Based on the continuum intensity images and vector magnetic field data with stray light correction from Solar Dynamics Observatory/Helioseismic and Magnetic Imager, the area, vector magnetic field and magnetic flux in the umbra and penumbra are calculated with time, respectively. Our main results are as follows: (1) The decay curves of the sunspot area in its umbra, penumbra, and whole sunspot take the appearance of Gaussian profiles. The area decay rates of the umbra, penumbra and whole sunspot are -1.56 MSH/day, -12.61 MSH/day and -14.04 MSH/day, respectively; (2) With the decay of the sunspot, the total magnetic field strength and the vertical component of the penumbra increase, and the magnetic field of the penumbra becomes more vertical. Meanwhile, the total magnetic field strength and vertical magnetic field strength for the umbra decrease, and the inclination angle changes slightly with an average value of about 20{\deg}; (3) The magnetic flux decay curves of the sunspot in its umbra, penumbra, and whole sunspot exhibit quadratic patterns, their magnetic flux decay rates of the umbra, penumbra and whole sunspot are -9.84 * 10^19 Mx/day, -1.59 * 10^20 Mx/day and -2.60 * 10^20 Mx/day , respectively. The observation suggests that the penumbra may be transformed into the umbra, resulting in the increase of the average vertical magnetic field strength and the reduction of the inclination angle in the penumbra during the decay of the sunspot.

We employ the approach of path integral in the phase space to study the kinetics of state switching associated with black hole phase transitions. Under the assumption that the state switching process of the black hole is described by the stochastic Langevin equation based on the free energy landscape, we derived the Martin-Siggia-Rose-Janssen-de Dominicis (MSRJD) functional and obtained the path integral expression of the transition probability. The MSRJD functional inherently represents the path integral in the phase space, allowing us to extract the effective Hamiltonian for the dynamics of state switching process. By solving the Hamiltonian equations of motion, we obtain the kinetic path in the phase space using an example of the RNAdS black hole. Furthermore, the dominant kinetic path within the configuration space is calculated. We also discuss the kinetic rate by using the functional formalism. Finally, we examine two further examples: Hawking-Page phase transition and Gauss-Bonnet black hole phase transition at the triple point. Our analysis demonstrates that, concerning the Hawking-Page phase transition, while a dominant kinetic path in the phase space from the large SAdS black hole to the thermal AdS space is present, there is no kinetic path for the inverse process. For the Gauss-Bonnet black hole phase transition at the triple point, the state switching processes between the small, the intermediate and the large Gauss-Bonnet black holes constitute a chemical reaction cycle., Comment: More discussions on generalized free energy from York's approach and phase portrait at the critical point, and a brief review of time-dependent Ginzburg-Landau model are added

The way metal interfaces evolve during frictional sliding, and how that evolution can be externally influenced under external drivers are important questions, hard to investigate experimentally because the contacts themselves are generally difficult to access. Here we focus on an elementary constituent of a general metal-metal interface, namely an ultra-thin individual nanocontact, where recent rheological studies of crystalline gold nanocontacts [Nature 569, 393 (2019)] showed a dramatic and unexpected mechanical softening as a result of external oscillatory tensile stress. The question which we address through realistic nonequilibrium molecular dynamics simulations is to what extent such mechanical softening might influence the shearing habit of gold nanocontacts at room temperature. It is found that the shearing evolution, which occurs through a series of discrete slips, is indeed rheologically softened, even though not completely, by the oscillations. Differences also emerge for different types of external oscillation, tensile or rotational. The relevance of these results for future experiments will be discussed., Comment: submitted to Physical Review Materials

Axion-pion scattering amplitudes at finite temperatures are calculated within chiral perturbation theory up to the one loop level. Unitarization procedure is implemented to these amplitudes in order to extend the applicable range of energy and temperature. The influence of the thermal axion-pion scattering amplitudes on the $a\pi\to\pi\pi$ cross sections and the axion thermalization rate is investigated, with the emphasis on the comparison with the zero-temperature-amplitude case. A brief discussion on the cosmological implication of the axion thermalization rate, that is calculated by using the $a\pi\to\pi\pi$ amplitudes at finite temperatures, is also given. The thermal corrections to the axion-pion scattering amplitudes can cause around a $10\%$ shift of the determination of the axion decay constant $f_a$ and its mass $m_a$, comparing with the results by using the $a\pi\to\pi\pi$ amplitudes at zero temperature., Comment: 26 pages, 7 figures

Understanding the nature of repeating FRBs is crucial to probe the physics of FRBs. In this work, we analyze the statistics of waiting time between bursts of three repeating FRBs from four data sets. We find a universally pronounced dependency of the waiting times on the previous time interval (denoted as $\lambda_0$). We observe a temporal clustering where short waiting times tend to be followed by short ones, and long by long. This memory dependency is manifested in the conditional mean waiting time as well as in the conditional mean residual time to the next burst, both of which increase in direct proportion to $\lambda_0$. Consequently, the likelihood of experiencing a subsequent FRB burst within a given time window after the preceding burst is significantly influenced by the burst history. We reveal that, for the first time, these memory effects are present in the scale-invariant preconditioned waiting time distribution. We show that the memory effect provides a unified description of waiting times which may account for both the repeating FRBs and the apparent non-repeating FRBs (i.e. only observed one time). These results shed new light on the mechanism of FRBs.

A dynamic gravimeter with an atomic interferometer (AI) can perform absolute gravity measurements with high precision. AI-based dynamic gravity measurement is a type of joint measurement that uses AI sensors and a classical accelerometer. The coupling of the two sensors may degrade the measurement precision. In this study, we analyzed the cross-coupling effect and introduced a recovery vector to suppress this effect. We improved the phase noise of the interference fringe by a factor of 1.9 by performing marine gravity measurements using an AI-based gravimeter and optimizing the recovery vector. Marine gravity measurements were performed, and high gravity measurement precision was achieved. The external and inner coincidence accuracies of the gravity measurement are 0.42 mGal and 0.46 mGal, which were improved by factors of 4.18 and 4.21 by optimizing the cross-coupling effect.