arXiv subjects

Yang Xiao

Publications and source records attributed to Yang Xiao.

At least 199 records · Page 11Linked to original sources

arXiv2024

Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learning

Accurate recognition of aviation commands is vital for flight safety and efficiency, as pilots must follow air traffic control instructions precisely. This paper addresses challenges in speech command recognition, such as noisy environments and limited computational resources, by advancing keyword spotting technology. We create a dataset of standardized airport tower commands, including routine and emergency instructions. We enhance broadcasted residual learning with squeeze-and-excitation and time-frame frequency-wise squeeze-and-excitation techniques, resulting in our BC-SENet model. This model focuses on crucial information with fewer parameters. Our tests on five keyword spotting models, including BC-SENet, demonstrate superior accuracy and efficiency. These findings highlight the effectiveness of our model advancements in improving speech command recognition for aviation safety and efficiency in noisy, high-stakes environments. Additionally, BC-SENet shows comparable performance on the common Google Speech Command dataset.

cs.SD↗

arXiv2024

Towards a Client-Centered Assessment of LLM Therapists by Client Simulation

Although there is a growing belief that LLMs can be used as therapists, exploring LLMs' capabilities and inefficacy, particularly from the client's perspective, is limited. This work focuses on a client-centered assessment of LLM therapists with the involvement of simulated clients, a standard approach in clinical medical education. However, there are two challenges when applying the approach to assess LLM therapists at scale. Ethically, asking humans to frequently mimic clients and exposing them to potentially harmful LLM outputs can be risky and unsafe. Technically, it can be difficult to consistently compare the performances of different LLM therapists interacting with the same client. To this end, we adopt LLMs to simulate clients and propose ClientCAST, a client-centered approach to assessing LLM therapists by client simulation. Specifically, the simulated client is utilized to interact with LLM therapists and complete questionnaires related to the interaction. Based on the questionnaire results, we assess LLM therapists from three client-centered aspects: session outcome, therapeutic alliance, and self-reported feelings. We conduct experiments to examine the reliability of ClientCAST and use it to evaluate LLMs therapists implemented by Claude-3, GPT-3.5, LLaMA3-70B, and Mixtral 8*7B. Codes are released at https://github.com/wangjs9/ClientCAST.

cs.CL↗

arXiv2024

How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation

In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs). However, due to the lack of systematic evaluation of LLMs' simulated behaviors, the believability of LLMs among humans remains ambiguous, i.e., it is unclear which behaviors of LLMs are convincingly human-like and which need further improvements. In this work, we design SimulateBench to evaluate the believability of LLMs when simulating human behaviors. In specific, we evaluate the believability of LLMs based on two critical dimensions: 1) consistency: the extent to which LLMs can behave consistently with the given information of a human to simulate; and 2) robustness: the ability of LLMs' simulated behaviors to remain robust when faced with perturbations. SimulateBench includes 65 character profiles and a total of 8,400 questions to examine LLMs' simulated behaviors. Based on SimulateBench, we evaluate the performances of 10 widely used LLMs when simulating characters. The experimental results reveal that current LLMs struggle to align their behaviors with assigned characters and are vulnerable to perturbations in certain factors.

cs.CL↗

arXiv2024

Speed of Random Walks in Dirichlet Environment on a Galton-Watson Tree

This paper deals with a transient random walk in Dirichlet environment, or equivalently a linearly edge reinforced random walk, on a Galton-Watson tree. We compute the stationary distribution of the environment seen from the particle of an edge reinforced random walk. We obtain a formula for the speed and give a necessary and sufficient condition for the walk to have a positive speed under some moment conditions on the offspring distribution of the tree.

math.PR↗

arXiv2024

Post-hoc and manifold explanations analysis of facial expression data based on deep learning

The complex information processing system of humans generates a lot of objective and subjective evaluations, making the exploration of human cognitive products of great cutting-edge theoretical value. In recent years, deep learning technologies, which are inspired by biological brain mechanisms, have made significant strides in the application of psychological or cognitive scientific research, particularly in the memorization and recognition of facial data. This paper investigates through experimental research how neural networks process and store facial expression data and associate these data with a range of psychological attributes produced by humans. Researchers utilized deep learning model VGG16, demonstrating that neural networks can learn and reproduce key features of facial data, thereby storing image memories. Moreover, the experimental results reveal the potential of deep learning models in understanding human emotions and cognitive processes and establish a manifold visualization interpretation of cognitive products or psychological attributes from a non-Euclidean space perspective, offering new insights into enhancing the explainability of AI. This study not only advances the application of AI technology in the field of psychology but also provides a new psychological theoretical understanding the information processing of the AI. The code is available in here: https://github.com/NKUShaw/Psychoinformatics.

cs.CV↗

arXiv2024

Calculations of bound-state $β^-$-decay half-lives of highly ionized $^{163}$Dy$^{66+}$, $^{187}$Re$^{75+}$ and $^{205}$Tl$^{81+}$

We propose a theoretical method to calculate the bound-state $β$-decay half-lives of highly-ionized atoms, which is based on the combination of the Takahashi-Yokoi model and our recently-developed projected shell model that can take into account both allowed and first-forbidden transitions of nuclear $β$ decay. Three examples that are of much experimental interests, $^{163}$Dy$^{66+}$, $^{187}$Re$^{75+}$ and $^{205}$Tl$^{81+}$ are taken for calculations. The ground and low-lying states of related nuclei are described reasonably. The bound-state $β$-decay half-lives of $^{163}$Dy$^{66+}$ and $^{187}$Re$^{75+}$ are described within a factor of two and four by our calculations without and with the quenching factors in allowed and first-forbidden transitions. The bound-state $β$-decay half-life of the last $s$-process branching point $^{205}$Tl$^{81+}$ is predicted to be 58 and 305 days for cases without and with the quenching factors in calculations. The presented method provides a theoretical way to calculate systematically the bound-state $β$-decay half-lives of nuclei from light to heavy ones including odd-mass and even-mass cases for the first time.

nucl-th↗

arXiv2024

Anomalous Long-Distance Coherence in Critically-Driven Cavity Magnonics

Developing quantum networks necessitates coherently connecting distant systems via remote strong coupling. Here, we demonstrate long-distance coherence in cavity magnonics operating in the linear regime. By locally setting the cavity near critical coupling with travelling photons, non-local magnon-photon coherence is established via strong coupling over a 2-meter distance. We observe two anomalies in this long-distance coherence: first, the coupling strength oscillates twice the period of conventional photon-mediated couplings; second, clear mode splitting is observed within the cavity linewidth. Both effects cannot be explained by conventional coupled-mode theory, which reveal the tip of an iceberg of photon-mediated coupling in systems under critical driving. Our work shows the potential of using critical phenomena for harnessing long-distance coherence in distributed systems.

quant-ph↗

arXiv2024

New vacuum stability limit from cosmological history

The stability of the electroweak vacuum imposes important constraints on new physics models. Such new physics models may introduce one or more new thermal phases with a lower free energy than that of the electroweak vacuum. In this case, the early universe may stay or have already evolved into one of these deeper vacuum states. We investigate this possibility in detail in the singlet extension of the Standard Model, and delineate the corresponding constraints in its parameter space. We also discuss the situation in supersymmetry as another example. To account for the possibility that the universe is trapped in a non-electroweak vacuum, we propose a procedure of calculating the vacuum stability limit efficiently.

hep-ph↗

arXiv2024

SCALE: Constructing Structured Natural Language Comment Trees for Software Vulnerability Detection

Recently, there has been a growing interest in automatic software vulnerability detection. Pre-trained model-based approaches have demonstrated superior performance than other Deep Learning (DL)-based approaches in detecting vulnerabilities. However, the existing pre-trained model-based approaches generally employ code sequences as input during prediction, and may ignore vulnerability-related structural information, as reflected in the following two aspects. First, they tend to fail to infer the semantics of the code statements with complex logic such as those containing multiple operators and pointers. Second, they are hard to comprehend various code execution sequences, which is essential for precise vulnerability detection. To mitigate the challenges, we propose a Structured Natural Language Comment tree-based vulnerAbiLity dEtection framework based on the pre-trained models, named SCALE. The proposed Structured Natural Language Comment Tree (SCT) integrates the semantics of code statements with code execution sequences based on the Abstract Syntax Trees (ASTs). Specifically, SCALE comprises three main modules: (1) Comment Tree Construction, which aims at enhancing the model's ability to infer the semantics of code statements by first incorporating Large Language Models (LLMs) for comment generation and then adding the comment node to ASTs. (2) Structured Natural Language Comment Tree Construction}, which aims at explicitly involving code execution sequence by combining the code syntax templates with the comment tree. (3) SCT-Enhanced Representation, which finally incorporates the constructed SCTs for well capturing vulnerability patterns.

cs.SE↗

arXiv2024

Scaling limit of the random walk on a Galton-Watson tree with regular varying offspring distribution

We consider a random walk on a Galton-Watson tree whose offspring distribution has a regular varying tail of order $κ\in (1,2)$. We prove the convergence of the renormalised height function of the walk towards the continuous-time height process of a spectrally positive strictly stable Lévy process, jointly with the convergence of the renormalised trace of the walk towards the continuum tree coded by the latter continuous-time height process.

math.PR↗

arXiv2024

A Survey on Long Video Generation: Challenges, Methods, and Prospects

Video generation is a rapidly advancing research area, garnering significant attention due to its broad range of applications. One critical aspect of this field is the generation of long-duration videos, which presents unique challenges and opportunities. This paper presents the first survey of recent advancements in long video generation and summarises them into two key paradigms: divide and conquer temporal autoregressive. We delve into the common models employed in each paradigm, including aspects of network design and conditioning techniques. Furthermore, we offer a comprehensive overview and classification of the datasets and evaluation metrics which are crucial for advancing long video generation research. Concluding with a summary of existing studies, we also discuss the emerging challenges and future directions in this dynamic field. We hope that this survey will serve as an essential reference for researchers and practitioners in the realm of long video generation.

cs.CV↗

arXiv2024

SAI3D: Segment Any Instance in 3D Scenes

Advancements in 3D instance segmentation have traditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories. Recent efforts have sought to harness vision-language models like CLIP for open-set semantic reasoning, yet these methods struggle to distinguish between objects of the same categories and rely on specific prompts that are not universally applicable. In this paper, we introduce SAI3D, a novel zero-shot 3D instance segmentation approach that synergistically leverages geometric priors and semantic cues derived from Segment Anything Model (SAM). Our method partitions a 3D scene into geometric primitives, which are then progressively merged into 3D instance segmentations that are consistent with the multi-view SAM masks. Moreover, we design a hierarchical region-growing algorithm with a dynamic thresholding mechanism, which largely improves the robustness of finegrained 3D scene parsing.Empirical evaluations on ScanNet, Matterport3D and the more challenging ScanNet++ datasets demonstrate the superiority of our approach. Notably, SAI3D outperforms existing open-vocabulary baselines and even surpasses fully-supervised methods in class-agnostic segmentation on ScanNet++. Our project page is at https://yd-yin.github.io/SAI3D.

cs.CV↗

arXiv2024

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e.g., joint location), and may suffer from local information loss and low generalization ability. To alleviate these, we propose to leverage text description generated from large language models (LLM) that contain high-level human knowledge, to guide feature learning, in a global-local-global way. Particularly, during training, we design $2$ prompts to gain global and local text descriptions of each action from an LLM. We first utilize the global text description to guide the skeleton encoder focus on informative joints (i.e.,global-to-local). Then we build non-local interaction between local text and joint features, to form the final global representation (i.e., local-to-global). To mitigate the asymmetry issue between the training and inference phases, we further design a dual-branch architecture that allows the model to perform novel class inference without any text input, also making the additional inference cost neglectable compared with the base skeleton encoder. Extensive experiments on three different benchmarks show that CrossGLG consistently outperforms the existing SOTA methods with large margins, and the inference cost (model size) is only $2.8$\% than the previous SOTA. CrossGLG can also serve as a plug-and-play module that can substantially enhance the performance of different SOTA skeleton encoders with a neglectable cost during inference. The source code will be released soon.

cs.CV↗

arXiv2024

A Survey of Lottery Ticket Hypothesis

The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i.e., winning tickets) that can achieve even better performance than the original model when trained in isolation. While LTH has been proved both empirically and theoretically in many works, there still are some open issues, such as efficiency and scalability, to be addressed. Also, the lack of open-source frameworks and consensual experimental setting poses a challenge to future research on LTH. We, for the first time, examine previous research and studies on LTH from different perspectives. We also discuss issues in existing works and list potential directions for further exploration. This survey aims to provide an in-depth look at the state of LTH and develop a duly maintained platform to conduct experiments and compare with the most updated baselines.

cs.LG↗

arXiv2024

Dual Knowledge Distillation for Efficient Sound Event Detection

Sound event detection (SED) is essential for recognizing specific sounds and their temporal locations within acoustic signals. This becomes challenging particularly for on-device applications, where computational resources are limited. To address this issue, we introduce a novel framework referred to as dual knowledge distillation for developing efficient SED systems in this work. Our proposed dual knowledge distillation commences with temporal-averaging knowledge distillation (TAKD), utilizing a mean student model derived from the temporal averaging of the student model's parameters. This allows the student model to indirectly learn from a pre-trained teacher model, ensuring a stable knowledge distillation. Subsequently, we introduce embedding-enhanced feature distillation (EEFD), which involves incorporating an embedding distillation layer within the student model to bolster contextual learning. On DCASE 2023 Task 4A public evaluation dataset, our proposed SED system with dual knowledge distillation having merely one-third of the baseline model's parameters, demonstrates superior performance in terms of PSDS1 and PSDS2. This highlights the importance of proposed dual knowledge distillation for compact SED systems, which can be ideal for edge devices.

cs.SD↗

arXiv2024

Global Impact and Balancing Act: Deciphering the Effect of Fluorination on B1s Binding Energies in Fluorinated $h$-BN Nanosheets

X-ray photoelectron spectroscopy (XPS) is an important characterization tool in the pursuit of controllable fluorination of two-dimensional hexagonal boron nitride ($h$-BN). However, there is a lack of clear spectral interpretation and seemingly conflicting measurements exist. To discern the structure-spectroscopy relation, we performed a comprehensive first-principles study on the boron 1s edge XPS of fluorinated $h$-BN (F-BN) nanosheets. By gradually introducing 1--6 fluorine atoms into different boron or nitrogen sites, we created various F-BN structures with doping ratios ranging from 1-6\%. Our calculations reveal that fluorines landed at boron or nitrogen sites exert competitive effects on the B1s binding energies (BEs), leading to red or blue shifts in different measurements. Our calculations affirmed the hypothesis that fluorination affects 1s BEs of all borons in the $π$-conjugated system, undermining the transferability from $h$-BN to F-BN. Additionally, we observe that BE generally increases with higher fluorine concentration when both borons and nitrogens are non-exclusively fluorinated. These findings provide critical insights into how fluorination affects boron's 1s BEs, contributing to a better understanding of fluorination functionalization processes in $h$-BN and its potential applications in materials science.

cond-mat.mtrl-sci↗

arXiv2023

End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context

In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye in an end-to-end learning way, which has not been well concerned yet. The main advantage of MCGaze is that the tasks of clue localization of head, face, and eye can be solved jointly for gaze estimation in a one-step way, with joint optimization to seek optimal performance. During this, spatial-temporal context exchange happens among the clues on the head, face, and eye. Accordingly, the final gazes obtained by fusing features from various queries can be aware of global clues from heads and faces, and local clues from eyes simultaneously, which essentially leverages performance. Meanwhile, the one-step running way also ensures high running efficiency. Experiments on the challenging Gaze360 dataset verify the superiority of our proposition. The source code will be released at https://github.com/zgchen33/MCGaze.

cs.CV↗

arXiv2023

Implications of Nano-Hertz Gravitational Waves on Electroweak Phase Transition in the Singlet Dark Matter Model

Inspired by the recent evidences of nano-Hertz stochastic gravitational waves observed by the pulsar timing array collaborations, we explore their implied supercooled electroweak phase transition in the singlet extension of the Standard Model. Our findings reveal that by adjusting the model parameter at per milli level, the corresponding percolation temperature can be continuously lowered to 1 GeV. With such a low percolation temperature, the singlet dark matter may freeze out before the electroweak phase transition, and, consequently, the entropy generated during the transition can significantly affect the dark matter relic density. It alleviates the tension between the requirement of a strong electroweak phase transition and the constraints imposed by dark matter direct detection, and can be tested in future experiments.

hep-ph↗