arXiv subjects

Yixuan Zhang

Publications and source records attributed to Yixuan Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2023

Large Language Models Understand and Can be Enhanced by Emotional Stimuli

Emotional intelligence significantly impacts our daily behaviors and interactions. Although Large Language Models (LLMs) are increasingly viewed as a stride toward artificial general intelligence, exhibiting impressive performance in numerous tasks, it is still uncertain if LLMs can genuinely grasp psychological emotional stimuli. Understanding and responding to emotional cues gives humans a distinct advantage in problem-solving. In this paper, we take the first step towards exploring the ability of LLMs to understand emotional stimuli. To this end, we first conduct automatic experiments on 45 tasks using various LLMs, including Flan-T5-Large, Vicuna, Llama 2, BLOOM, ChatGPT, and GPT-4. Our tasks span deterministic and generative applications that represent comprehensive evaluation scenarios. Our automatic experiments show that LLMs have a grasp of emotional intelligence, and their performance can be improved with emotional prompts (which we call "EmotionPrompt" that combines the original prompt with emotional stimuli), e.g., 8.00% relative performance improvement in Instruction Induction and 115% in BIG-Bench. In addition to those deterministic tasks that can be automatically evaluated using existing metrics, we conducted a human study with 106 participants to assess the quality of generative tasks using both vanilla and emotional prompts. Our human study results demonstrate that EmotionPrompt significantly boosts the performance of generative tasks (10.9% average improvement in terms of performance, truthfulness, and responsibility metrics). We provide an in-depth discussion regarding why EmotionPrompt works for LLMs and the factors that may influence its performance. We posit that EmotionPrompt heralds a novel avenue for exploring interdisciplinary knowledge for human-LLMs interaction.

cs.CL↗

arXiv2023

Can Large Language Model Comprehend Ancient Chinese? A Preliminary Test on ACLUE

Large language models (LLMs) have showcased remarkable capabilities in understanding and generating language. However, their ability in comprehending ancient languages, particularly ancient Chinese, remains largely unexplored. To bridge this gap, we present ACLUE, an evaluation benchmark designed to assess the capability of language models in comprehending ancient Chinese. ACLUE consists of 15 tasks cover a range of skills, spanning phonetic, lexical, syntactic, semantic, inference and knowledge. Through the evaluation of eight state-of-the-art LLMs, we observed a noticeable disparity in their performance between modern Chinese and ancient Chinese. Among the assessed models, ChatGLM2 demonstrates the most remarkable performance, achieving an average score of 37.4%. We have made our code and data public available.

cs.CL↗

arXiv2023

Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes

In this study, we propose a novel deep spatio-temporal point process model, Deep Kernel Mixture Point Processes (DKMPP), that incorporates multimodal covariate information. DKMPP is an enhanced version of Deep Mixture Point Processes (DMPP), which uses a more flexible deep kernel to model complex relationships between events and covariate data, improving the model's expressiveness. To address the intractable training procedure of DKMPP due to the non-integrable deep kernel, we utilize an integration-free method based on score matching, and further improve efficiency by adopting a scalable denoising score matching method. Our experiments demonstrate that DKMPP and its corresponding score-based estimators outperform baseline models, showcasing the advantages of incorporating covariate information, utilizing a deep kernel, and employing score-based estimators.

cs.LG↗

arXiv2023

Advancing Acoustic Howling Suppression through Recursive Training of Neural Networks

In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process. This framework integrates a neural network (NN) module into the closed-loop system during training with signals generated recursively on the fly to closely mimic the streaming process of acoustic howling suppression (AHS). The proposed recursive training strategy bridges the gap between training and real-world inference scenarios, marking a departure from previous NN-based methods that typically approach AHS as either noise suppression or acoustic echo cancellation. Within this framework, we explore two methodologies: one exclusively relying on NN and the other combining NN with the traditional Kalman filter. Additionally, we propose strategies, including howling detection and initialization using pre-trained offline models, to bolster trainability and expedite the training process. Experimental results validate that this framework offers a substantial improvement over previous methodologies for acoustic howling suppression.

eess.AS↗

arXiv2023

Neural Network Augmented Kalman Filter for Robust Acoustic Howling Suppression

Acoustic howling suppression (AHS) is a critical challenge in audio communication systems. In this paper, we propose a novel approach that leverages the power of neural networks (NN) to enhance the performance of traditional Kalman filter algorithms for AHS. Specifically, our method involves the integration of NN modules into the Kalman filter, enabling refining reference signal, a key factor in effective adaptive filtering, and estimating covariance metrics for the filter which are crucial for adaptability in dynamic conditions, thereby obtaining improved AHS performance. As a result, the proposed method achieves improved AHS performance compared to both standalone NN and Kalman filter methods. Experimental evaluations validate the effectiveness of our approach.

eess.AS↗

arXiv2023

Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in real-world scenarios, hampering listening experiences. To address these challenges, we propose a novel approach that uses pre-trained generative methods to resynthesize clean, anechoic speech from degraded inputs. This study leverages pre-trained vocoder or codec models to synthesize high-quality speech while enhancing robustness in challenging scenarios. Generative methods effectively handle information loss in speech signals, resulting in regenerated speech that has improved fidelity and reduced artifacts. By harnessing the capabilities of pre-trained models, we achieve faithful reproduction of the original speech in adverse conditions. Experimental evaluations on both simulated datasets and realistic samples demonstrate the effectiveness and robustness of our proposed methods. Especially by leveraging codec, we achieve superior subjective scores for both simulated and realistic recordings. The generated speech exhibits enhanced audio quality, reduced background noise, and reverberation. Our findings highlight the potential of pre-trained generative techniques in speech processing, particularly in scenarios where traditional methods falter. Demos are available at https://whmrtm.github.io/SoundResynthesis.

eess.AS↗

arXiv2023

Hierarchical Optimization-Derived Learning

In recent years, by utilizing optimization techniques to formulate the propagation of deep model, a variety of so-called Optimization-Derived Learning (ODL) approaches have been proposed to address diverse learning and vision tasks. Although having achieved relatively satisfying practical performance, there still exist fundamental issues in existing ODL methods. In particular, current ODL methods tend to consider model construction and learning as two separate phases, and thus fail to formulate their underlying coupling and depending relationship. In this work, we first establish a new framework, named Hierarchical ODL (HODL), to simultaneously investigate the intrinsic behaviors of optimization-derived model construction and its corresponding learning process. Then we rigorously prove the joint convergence of these two sub-tasks, from the perspectives of both approximation quality and stationary analysis. To our best knowledge, this is the first theoretical guarantee for these two coupled ODL components: optimization and learning. We further demonstrate the flexibility of our framework by applying HODL to challenging learning tasks, which have not been properly addressed by existing ODL methods. Finally, we conduct extensive experiments on both synthetic data and real applications in vision and other learning tasks to verify the theoretical properties and practical performance of HODL in various application scenarios.

cs.LG↗

arXiv2023

Bayesian optimization with active learning of Ta-Nb-Hf-Zr-Ti system for spin transport properties

Designing materials with enhanced spin charge conversion, i.e., with high spin Hall conductivity (SHC) and low longitudinal electric conductivity (hence large spin Hall angle (SHA)), is a challenging task, especially in the presence of a vast chemical space for compositionally complex alloys (CCAs). In this work, focusing on the Ta-Nb-Hf-Zr-Ti system, we confirm that CCAs exhibit significant spin Hall conductivities and propose a multi-objective Bayesian optimization approach (MOBO) incorporated with active learning (AL) in order to screen for the optimal compositions with significant SHC and SHA. As a result, within less than 5 iterations we are able to target the TaZr-dominated systems displaying both high magnitudes of SHC (~-2.0 (10$^{-3}$ $Ω$ cm)$^{-1}$) and SHA (~0.03). The SHC is mainly ascribed to the extrinsic skew scattering mechanism. Our work provides an efficient route for identifying new materials with significant SHE, which can be straightforwardly generalized to optimize other properties in a vast chemical space.

cond-mat.mtrl-sci↗

arXiv2023

A new variant of the Erdős-Gyárfás problem on $K_{5}$

Motivated by an extremal problem on graph-codes that links coding theory and graph theory, Alon recently proposed a question aiming to find the smallest number $t$ such that there is an edge coloring of $K_{n}$ by $t$ colors with no copy of given graph $H$ in which every color appears an even number of times. When $H=K_{4}$, the question of whether $n^{o(1)}$ colors are enough, was initially emphasized by Alon. Through modifications to the coloring functions originally designed by Mubayi, and Conlon, Fox, Lee and Sudakov, the question of $K_{4}$ has already been addressed. Expanding on this line of inquiry, we further study this new variant of the generalized Ramsey problem and provide a conclusively affirmative answer to Alon's question concerning $K_{5}$.

math.CO↗

arXiv2023

Value-Function-based Sequential Minimization for Bi-level Optimization

Gradient-based Bi-Level Optimization (BLO) methods have been widely applied to handle modern learning tasks. However, most existing strategies are theoretically designed based on restrictive assumptions (e.g., convexity of the lower-level sub-problem), and computationally not applicable for high-dimensional tasks. Moreover, there are almost no gradient-based methods able to solve BLO in those challenging scenarios, such as BLO with functional constraints and pessimistic BLO. In this work, by reformulating BLO into approximated single-level problems, we provide a new algorithm, named Bi-level Value-Function-based Sequential Minimization (BVFSM), to address the above issues. Specifically, BVFSM constructs a series of value-function-based approximations, and thus avoids repeated calculations of recurrent gradient and Hessian inverse required by existing approaches, time-consuming especially for high-dimensional tasks. We also extend BVFSM to address BLO with additional functional constraints. More importantly, BVFSM can be used for the challenging pessimistic BLO, which has never been properly solved before. In theory, we prove the asymptotic convergence of BVFSM on these types of BLO, in which the restrictive lower-level convexity assumption is discarded. To our best knowledge, this is the first gradient-based algorithm that can solve different kinds of BLO (e.g., optimistic, pessimistic, and with constraints) with solid convergence guarantees. Extensive experiments verify the theoretical investigations and demonstrate our superiority on various real-world applications.

cs.LG↗

arXiv2023

Accelerated Screening of Ternary Chalcogenides for High-Performance Optoelectronic Materials

Chalcogenides, which refer to chalcogen anions, have attracted considerable attention in multiple fields of applications, such as optoelectronics, thermoelectrics, transparent contacts, and thin film transistors. In comparison to oxide counterparts, chalcogenides have demonstrated higher mobility and \textit{p}-type dopability, owing to larger orbital overlaps between metal-X covalent chemical bondings and higher-energy valence bands derived by p-orbitals. Despite the potential of chalcogenides, the number of successfully synthesized compounds remains relatively low compared to oxides, suggesting the presence of numerous unexplored chalcogenides with fascinating physical characteristics. In this study, we implemented a systematic high-throughput screening process combined with first-principles calculations on ternary chalcogenides using 34 crystal structure prototypes. We generated a computational material database containing over 400,000 compounds by exploiting the ion-substitution approach at different atomic sites with elements in the periodic table. The thermodynamic stabilities of the candidates were validated using the chalcogenides included in the Open Quantum Materials Database. Moreover, we trained a model based on Crystal Graph Convolutional Neural Networks to predict the thermodynamic stability of novel materials. Furthermore, we theoretically evaluated the electronic structures of the stable candidates using accurate hybrid functionals. A series of in-depth characteristics, including the carrier effective masses, electronic configuration, and photovoltaic conversion efficiency, was also investigated. Our work provides useful guidance for further experimental research in the synthesis and characterization of such chalcogenides as promising candidates, as well as charting the stability and optoelectronic performance of ternary chalcogenides.

cond-mat.mtrl-sci↗

arXiv2023

Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures

Autonomous materials discovery with desired properties is one of the ultimate goals for materials science, and the current studies have been focusing mostly on high-throughput screening based on density functional theory calculations and forward modelling of physical properties using machine learning. Applying the deep learning techniques, we have developed a generative model which can predict distinct stable crystal structures by optimizing the formation energy in the latent space. It is demonstrated that the optimization of physical properties can be integrated into the generative model as on-top screening or backwards propagator, both with their own advantages. Applying the generative models on the binary Bi-Se system reveals that distinct crystal structures can be obtained covering the whole composition range, and the phases on the convex hull can be reproduced after the generated structures are fully relaxed to the equilibrium. The method can be extended to multicomponent systems for multi-objective optimization, which paves the way to achieve the inverse design of materials with optimal properties.

physics.comp-ph↗

arXiv2023

What Do We Mean When We Talk about Trust in Social Media? A Systematic Review

Do people trust social media? If so, why, in what contexts, and how does that trust impact their lives? Researchers, companies, and journalists alike have increasingly investigated these questions, which are fundamental to understanding social media interactions and their implications for society. However, trust in social media is a complex concept, and there is conflicting evidence about the antecedents and implications of trusting social media content, users, and platforms. More problematic is that we lack basic agreement as to what trust means in the context of social media. Addressing these challenges, we conducted a systematic review to identify themes and challenges in this field. Through our analysis of 70 papers, we contribute a synthesis of how trust in social media is defined, conceptualized, and measured, a summary of trust antecedents in social media, an understanding of how trust in social media impacts behaviors and attitudes, and directions for future work.

cs.SI↗

arXiv2023

Autonomous atomic Hamiltonian construction and active sampling of x-ray absorption spectroscopy by adversarial Bayesian optimization

X-ray absorption spectroscopy (XAS) is a well-established method for in-depth characterization of the electronic structure due to its sensitivity to the local coordination and electronic states of the active ions. In practice hundreds of energy points should be sampled during the XAS measurement, most of which are redundant and do not contain important information. In addition, it is also a tedious procedure to estimate reasonable parameters in the atomic Hamiltonian for mechanistic understanding. We implemented an Adversarial Bayesian optimization (ABO) algorithm comprising two coupled BOs to automatically fit the multiplet model Hamiltonian and meanwhile to sample effectively based on active learning. Taking NiO as an example, for simulated spectra which can be well fitted by the atomic model, we found that less than 30 sampling points are enough to obtain the complete XAS with the corresponding crystal field or charge transfer model, which can be selected based on intuitive hypothesis learning. Further application on the experimental spectra, it revealed that less than 80 sampling points can already give reasonable XAS and reliable atomic model parameters. Our ABO algorithm has a great potential for future application in automated physics-driven XAS analysis and active learning sampling.

cond-mat.mtrl-sci↗

arXiv2023

Characterizing and Detecting WebAssembly Runtime Bugs

WebAssembly (abbreviated WASM) has emerged as a promising language of the Web and also been used for a wide spectrum of software applications such as mobile applications and desktop applications. These applications, named as WASM applications, commonly run in WASM runtimes. Bugs in WASM runtimes are frequently reported by developers and cause the crash of WASM applications. However, these bugs have not been well studied. To fill in the knowledge gap, we present a systematic study to characterize and detect bugs in WASM runtimes. We first harvest a dataset of 311 real-world bugs from hundreds of related posts on GitHub. Based on the collected high-quality bug reports, we distill 31 bug categories of WASM runtimes and summarize their common fix strategies. Furthermore, we develop a pattern-based bug detection framework to automatically detect bugs in WASM runtimes. We apply the detection framework to five popular WASM runtimes and successfully uncover 53 bugs that have never been reported previously, among which 14 have been confirmed and 6 have been fixed by runtime developers.

cs.SE↗

arXiv2022

Optimal Transportation for Electrical Impedance Tomography

This work establishes a framework for solving inverse boundary problems with the geodesic based quadratic Wasserstein distance ($W_{2}$). A general form of the Fréchet gradient is systematically derived by optimal transportation (OT) theory. In addition, a fast algorithm based on the new formulation of OT on $\mathbb{S}^{1}$ is developed to solve the corresponding optimal transport problem. The computational complexity of the algorithm is reduced to $O(N)$ from $O(N^{3})$ of the traditional method. Combining with the adjoint-state method, this framework provides a new computational approach for solving the challenging electrical impedance tomography (EIT) problem. Numerical examples are presented to illustrate the effectiveness of our method.

math.NA↗

arXiv2022

De-biased Representation Learning for Fairness with Unreliable Labels

Removing bias while keeping all task-relevant information is challenging for fair representation learning methods since they would yield random or degenerate representations w.r.t. labels when the sensitive attributes correlate with labels. Existing works proposed to inject the label information into the learning procedure to overcome such issues. However, the assumption that the observed labels are clean is not always met. In fact, label bias is acknowledged as the primary source inducing discrimination. In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage. This contradiction puts a question mark on the fairness of the learned representations. To circumvent this issue, we explore the following question: \emph{Can we learn fair representations predictable to latent ideal fair labels given only access to unreliable labels?} In this work, we propose a \textbf{D}e-\textbf{B}iased \textbf{R}epresentation Learning for \textbf{F}airness (DBRF) framework which disentangles the sensitive information from non-sensitive attributes whilst keeping the learned representations predictable to ideal fair labels rather than observed biased ones. We formulate the de-biased learning framework through information-theoretic concepts such as mutual information and information bottleneck. The core concept is that DBRF advocates not to use unreliable labels for supervision when sensitive information benefits the prediction of unreliable labels. Experiment results over both synthetic and real-world data demonstrate that DBRF effectively learns de-biased representations towards ideal labels.

cs.LG↗

arXiv2022

Visualization Design Practices in a Crisis: Behind the Scenes with COVID-19 Dashboard Creators

During the COVID-19 pandemic, a number of data visualizations were created to inform the public about the rapidly evolving crisis. Data dashboards, a form of information dissemination used during the pandemic, have facilitated this process by visualizing statistics regarding the number of COVID-19 cases over time. In this research, we conducted a qualitative interview study among dashboard creators from federal agencies, state health departments, mainstream news media outlets, and other organizations that created (often widely-used) COVID-19 dashboards to answer the following questions: how did visualization creators engage in COVID-19 dashboard design, and what tensions, conflicts, and challenges arose during this process? Our findings detail the trajectory of design practices -- from creation to expansion, maintenance, and termination -- that are shaped by the complex interplay between design goals, tools and technologies, labor, emerging crisis contexts, and public engagement. We particularly examined the tensions between designers and the general public involved in these processes. These conflicts, which often materialized due to a divergence between public demands and standing policies, centered around the type and amount of information to be visualized, how public perceptions shape and are shaped by visualization design, and the strategies utilized to deal with (potential) misinterpretations and misuse of visualizations. Our findings and lessons learned shed light on new ways of thinking in visualization design, focusing on the bundled activities that are invariably involved in human and nonhuman participation throughout the entire trajectory of design practice.

cs.HC↗