arXiv subjects

Xin Sun

Publications and source records attributed to Xin Sun.

At least 145 records · Page 8Linked to original sources

arXiv2024

Trusting the Search: Unraveling Human Trust in Health Information from Google and ChatGPT

People increasingly rely on online sources for health information seeking due to their convenience and timeliness, traditionally using search engines like Google as the primary search agent. Recently, the emergence of generative Artificial Intelligence (AI) has made Large Language Model (LLM) powered conversational agents such as ChatGPT a viable alternative for health information search. However, while trust is crucial for adopting the online health advice, the factors influencing people's trust judgments in health information provided by LLM-powered conversational agents remain unclear. To address this, we conducted a mixed-methods, within-subjects lab study (N=21) to explore how interactions with different agents (ChatGPT vs. Google) across three health search tasks influence participants' trust judgments of the search results as well as the search agents themselves. Our key findings showed that: (a) participants' trust levels in ChatGPT were significantly higher than Google in the context of health information seeking; (b) there is a significant correlation between trust in health-related information and trust in the search agent, however only for Google; (c) the type of search tasks did not affect participants' perceived trust; and (d) participants' prior knowledge, the style of information presentation, and the interactive manner of using search agents were key determinants of trust in the health-related information. Our study taps into differences in trust perceptions when using traditional search engines compared to LLM-powered conversational agents. We highlight the potential role LLMs play in health-related information-seeking contexts, where they excel as stepping stones for further search. We contribute key factors and considerations for ensuring effective and reliable personal health information seeking in the age of generative AI.

cs.HC↗

arXiv2024

OpenMEDLab: An Open-source Platform for Multi-modality Foundation Models in Medicine

The emerging trend of advancing generalist artificial intelligence, such as GPTv4 and Gemini, has reshaped the landscape of research (academia and industry) in machine learning and many other research areas. However, domain-specific applications of such foundation models (e.g., in medicine) remain untouched or often at their very early stages. It will require an individual set of transfer learning and model adaptation techniques by further expanding and injecting these models with domain knowledge and data. The development of such technologies could be largely accelerated if the bundle of data, algorithms, and pre-trained foundation models were gathered together and open-sourced in an organized manner. In this work, we present OpenMEDLab, an open-source platform for multi-modality foundation models. It encapsulates not only solutions of pioneering attempts in prompting and fine-tuning large language and vision models for frontline clinical and bioinformatic applications but also building domain-specific foundation models with large-scale multi-modal medical data. Importantly, it opens access to a group of pre-trained foundation models for various medical image modalities, clinical text, protein engineering, etc. Inspiring and competitive results are also demonstrated for each collected approach and model in a variety of benchmarks for downstream tasks. We welcome researchers in the field of medical artificial intelligence to continuously contribute cutting-edge methods and models to OpenMEDLab, which can be accessed via https://github.com/openmedlab.

cs.CV↗

arXiv2024

Can a Funny Chatbot Make a Difference? Infusing Humor into Conversational Agent for Behavioral Intervention

Regular physical activity is crucial for reducing the risk of non-communicable disease (NCD). With NCDs on the rise globally, there is an urgent need for effective health interventions, with chatbots emerging as a viable and cost-effective option because of limited healthcare accessibility. Although health professionals often utilize behavior change techniques (BCTs) to boost physical activity levels and enhance client engagement and motivation by affiliative humor, the efficacy of humor in chatbot-delivered interventions is not well-understood. This study conducted a randomized controlled trial to examine the impact of the generative humorous communication style in a 10-day chatbot-delivered intervention for physical activity. It further investigated if user engagement and motivation act as mediators between the communication style and changes in physical activity levels. 66 participants engaged with the chatbots across three groups (humorous, non-humorous, and no-intervention) and responded to daily ecological momentary assessment questionnaires assessing engagement, motivation, and physical activity levels. Multilevel time series analyses revealed that an affiliative humorous communication style positively impacted physical activity levels over time, with user engagement acting as a mediator in this relationship, whereas motivation did not. These findings clarify the role of humorous communication style in chatbot-delivered physical activity interventions, offering valuable insights for future development of intelligent conversational agents incorporating humor.

cs.HC↗

arXiv2024

Probabilistic conformal blocks for Liouville CFT on the torus

Virasoro conformal blocks are a family of important functions defined as power series via the Virasoro algebra. They are a fundamental input to the conformal bootstrap program for 2D conformal field theory (CFT) and are closely related to four dimensional supersymmetric gauge theory through the Alday-Gaiotto-Tachikawa correspondence. The present work provides a probabilistic construction of the 1-point toric Virasoro conformal block for central change greater than 25. More precisely, we construct an analytic function using a probabilistic tool called Gaussian multiplicative chaos (GMC) and prove that its power series expansion coincides with the 1-point toric Virasoro conformal block. The range $(25,\infty)$ of central charges corresponds to Liouville CFT, an important CFT originating from 2D quantum gravity and bosonic string theory. Our work reveals a new integrable structure underlying GMC and opens the door to the study of non-perturbative properties of Virasoro conformal blocks such as their analytic continuation and modular symmetry. Our proof combines an analysis of GMC with tools from CFT such as Belavin-Polyakov-Zamolodchikov differential equations, operator product expansions, and Dotsenko-Fateev type integrals.

math.PR↗

arXiv2024

Backbone exponent for two-dimensional percolation

We derive an exact expression for the celebrated backbone exponent for Bernoulli percolation in dimension two at criticality. It turns out to be a root of an elementary function. Contrary to previously known arm exponents for this model, which are all rational, it has a transcendental value. Our derivation relies on the connection to the SLE$_κ$ bubble measure, the coupling between SLE and Liouville quantum gravity, and the integrability of Liouville conformal field theory. Along the way, we derive a formula not only for $κ=6$ (corresponding to percolation), but for all $κ\in (4,8)$.

math.PR↗

arXiv2023

Bootstrap, Markov Chain Monte Carlo, and LP/SDP Hierarchy for the Lattice Ising Model

Bootstrap is an idea that imposing consistency conditions on a physical system may lead to rigorous and nontrivial statements about its physical observables. In this work, we discuss the bootstrap problem for the invariant measure of the stochastic Ising model defined as a Markov chain where probability bounds and invariance equations are imposed. It is described by a linear programming (LP) hierarchy whose asymptotic convergence is shown by explicitly constructing the invariant measure from the convergent sequence of moments. We also discuss the relation between the LP hierarchy for the invariant measure and a recently introduced semidefinite programming (SDP) hierarchy for the Gibbs measure of the statistical Ising model based on reflection positivity and spin-flip equations.

hep-th↗

arXiv2023

GSLB: The Graph Structure Learning Benchmark

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://github.com/GSL-Benchmark/GSLB.

cs.LG↗

arXiv2023

Impact of COVID-19 Lockdown Measures on Chinese Startups and Local Government Public Finance: Challenges and Policy Implications

This paper aims to assess the impact of COVID-19 on the public finance of Chinese local governments, with a particular focus on the effect of lockdown measures on startups during the pandemic. The outbreak has placed significant fiscal pressure on local governments, as containment measures have led to declines in revenue and increased expenses related to public health and social welfare. In tandem, startups have faced substantial challenges, including reduced funding and profitability, due to the negative impact of lockdown measures on entrepreneurship. Moreover, the pandemic has generated short- and long-term economic shocks, affecting both employment and economic recovery. To address these challenges, policymakers must balance health concerns with economic development. In this regard, the government should consider implementing more preferential policies that focus on startups to ensure their survival and growth. Such policies may include financial assistance, tax incentives, and regulatory flexibility to foster innovation and entrepreneurship. By and large, the COVID-19 pandemic has had a profound impact on both the public finance of Chinese local governments and the startup ecosystem. Addressing the challenges faced by local governments and startups will require a comprehensive approach that balances health and economic considerations and includes targeted policies to support entrepreneurship and innovation.

econ.GN↗

arXiv2023

Accurate Airway Tree Segmentation in CT Scans via Anatomy-aware Multi-class Segmentation and Topology-guided Iterative Learning

Intrathoracic airway segmentation in computed tomography (CT) is a prerequisite for various respiratory disease analyses such as chronic obstructive pulmonary disease (COPD), asthma and lung cancer. Unlike other organs with simpler shapes or topology, the airway's complex tree structure imposes an unbearable burden to generate the "ground truth" label (up to 7 or 3 hours of manual or semi-automatic annotation on each case). Most of the existing airway datasets are incompletely labeled/annotated, thus limiting the completeness of computer-segmented airway. In this paper, we propose a new anatomy-aware multi-class airway segmentation method enhanced by topology-guided iterative self-learning. Based on the natural airway anatomy, we formulate a simple yet highly effective anatomy-aware multi-class segmentation task to intuitively handle the severe intra-class imbalance of the airway. To solve the incomplete labeling issue, we propose a tailored self-iterative learning scheme to segment toward the complete airway tree. For generating pseudo-labels to achieve higher sensitivity , we introduce a novel breakage attention map and design a topology-guided pseudo-label refinement method by iteratively connecting breaking branches commonly existed from initial pseudo-labels. Extensive experiments have been conducted on four datasets including two public challenges. The proposed method ranked 1st in both EXACT'09 challenge using average score and ATM'22 challenge on weighted average score. In a public BAS dataset and a private lung cancer dataset, our method significantly improves previous leading approaches by extracting at least (absolute) 7.5% more detected tree length and 4.0% more tree branches, while maintaining similar precision.

eess.IV↗

arXiv2023

MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine

METHODS: First, a set of evaluation criteria is designed based on a comprehensive literature review. Second, existing candidate criteria are optimized for using a Delphi method by five experts in medicine and engineering. Third, three clinical experts design a set of medical datasets to interact with LLMs. Finally, benchmarking experiments are conducted on the datasets. The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts. RESULTS: The obtained evaluation criteria cover medical professional capabilities, social comprehensive capabilities, contextual capabilities, and computational robustness, with sixteen detailed indicators. The medical datasets include twenty-seven medical dialogues and seven case reports in Chinese. Three chatbots are evaluated, ChatGPT by OpenAI, ERNIE Bot by Baidu Inc., and Doctor PuJiang (Dr. PJ) by Shanghai Artificial Intelligence Laboratory. Experimental results show that Dr. PJ outperforms ChatGPT and ERNIE Bot in both multiple-turn medical dialogue and case report scenarios.

cs.CL↗

arXiv2023

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

Lighting effects such as shadows or reflections are key in making synthetic images realistic and visually appealing. To generate such effects, traditional computer graphics uses a physically-based renderer along with 3D geometry. To compensate for the lack of geometry in 2D Image compositing, recent deep learning-based approaches introduced a pixel height representation to generate soft shadows and reflections. However, the lack of geometry limits the quality of the generated soft shadows and constrain reflections to pure specular ones. We introduce PixHt-Lab, a system leveraging an explicit mapping from pixel height representation to 3D space. Using this mapping, PixHt-Lab reconstructs both the cutout and background geometry and renders realistic, diverse, lighting effects for image compositing. Given a surface with physically-based materials, we can render reflections with varying glossiness. To generate more realistic soft shadows, we further propose to use 3D-aware buffer channels to guide a neural renderer. Both quantitative and qualitative evaluations demonstrate that PixHt-Lab significantly improves soft shadow generation.

cs.CV↗

arXiv2023

You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos

Moment retrieval in videos is a challenging task that aims to retrieve the most relevant video moment in an untrimmed video given a sentence description. Previous methods tend to perform self-modal learning and cross-modal interaction in a coarse manner, which neglect fine-grained clues contained in video content, query context, and their alignment. To this end, we propose a novel Multi-Granularity Perception Network (MGPN) that perceives intra-modality and inter-modality information at a multi-granularity level. Specifically, we formulate moment retrieval as a multi-choice reading comprehension task and integrate human reading strategies into our framework. A coarse-grained feature encoder and a co-attention mechanism are utilized to obtain a preliminary perception of intra-modality and inter-modality information. Then a fine-grained feature encoder and a conditioned interaction module are introduced to enhance the initial perception inspired by how humans address reading comprehension problems. Moreover, to alleviate the huge computation burden of some existing methods, we further design an efficient choice comparison module and reduce the hidden size with imperceptible quality loss. Extensive experiments on Charades-STA, TACoS, and ActivityNet Captions datasets demonstrate that our solution outperforms existing state-of-the-art methods. Codes are available at github.com/Huntersxsx/MGPN.

cs.CV↗

arXiv2023

Mating of trees for random planar maps and Liouville quantum gravity: a survey

We survey the theory and applications of mating-of-trees bijections for random planar maps and their continuum analog: the mating-of-trees theorem of Duplantier, Miller, and Sheffield (2014). The latter theorem gives an encoding of a Liouville quantum gravity (LQG) surface decorated by a Schramm-Loewner evolution (SLE) curve in terms of a pair of correlated linear Brownian motions. We assume minimal familiarity with the theory of SLE and LQG. Mating-of-trees theory enables one to reduce problems about SLE and LQG to problems about Brownian motion and leads to deep rigorous connections between random planar maps and LQG. Applications discussed in this article include scaling limit results for various functionals of decorated random planar maps, estimates for graph distances and random walk on (not necessarily uniform) random planar maps, computations of the Hausdorff dimensions of sets associated with SLE, scaling limit results for random planar maps conformally embedded in the plane, and special symmetries for $\sqrt{8/3}$-LQG which allow one to prove its equivalence with the Brownian map.

math.PR↗

arXiv2023

The SLE loop via conformal welding of quantum disks

We prove that the SLE$_κ$ loop measure arises naturally from the conformal welding of two $γ$-Liouville quantum gravity (LQG) disks for $γ^2 = κ\in (0,4)$. The proof relies on our companion work on conformal welding of LQG disks and uses as an essential tool the concept of uniform embedding of LQG surfaces. Combining our result with work of Gwynne and Miller, we get that random quadrangulations decorated by a self-avoiding polygon converge in the scaling limit to the LQG sphere decorated by the SLE$_{8/3}$ loop. Our result is also a key input to recent work of the first and third coauthors on the integrability of the conformal loop ensemble.

math.PR↗

arXiv2023

Baxter permuton and Liouville quantum gravity

The Baxter permuton is a random probability measure on the unit square which describes the scaling limit of uniform Baxter permutations. We find an explict formula for the expectation of the Baxter permuton, i.e.\ the density of its intensity measure. This answers a question of Dokos and Pak (2014). We also prove that all pattern densities of the Baxter permuton are strictly positive, distinguishing it from other permutons arising as scaling limits of pattern-avoiding permutations. Our proofs rely on a recent connection between the Baxter permuton and Liouville quantum gravity (LQG) coupled with the Schramm-Loewner evolution (SLE). The method works equally well for a two-parameter generalization of the Baxter permuton recently introduced by the first author, except that the density is not as explicit. This new family of permutons, called \emph{skew Brownian permuton}, describes the scaling limit of a number of random constrained permutations. We finally observe that in the LQG/SLE framework, the expected proportion of inversions in a skew Brownian permuton equals $\frac{π-2θ}{2π}$ where $θ$ is the so-called imaginary geometry angle between a certain pair of SLE curves.

math.PR↗

arXiv2022

FZZ formula of boundary Liouville CFT via conformal welding

Liouville Conformal Field Theory (LCFT) on the disk describes the conformal factor of the quantum disk, which is the natural random surface in Liouville quantum gravity with disk topology. Fateev, Zamolodchikov and Zamolodchikov (2000) proposed an explicit expression, the so-called the FZZ formula, for the one-point bulk structure constant for LCFT on the disk. In this paper we give a proof of the FZZ formula in the probabilistic framework of LCFT, which represents the first step towards rigorously solving boundary LCFT using conformal bootstrap. In contrast to previous works, our proof is based on conformal welding of quantum disks and the mating-of-trees theory for Liouville quantum gravity. As a byproduct of our proof, we also obtain the exact value of the variance for the Brownian motion in the mating-of-trees theory. Our paper is an essential part of an ongoing program proving integrability results for Schramm-Loewner evolutions, LCFT, and in the mating-of-trees theory.

math.PR↗

arXiv2022

Schnyder woods, SLE(16), and Liouville quantum gravity

In 1990, Schnyder used a 3-spanning-tree decomposition of a simple triangulation, now known as the Schnyder wood, to give a fundamental grid-embedding algorithm for planar maps. In the framework of mating of trees, a uniformly sampled Schnyder-wood-decorated triangulation can produce a triple of random walks. We show that these three walks converge in the scaling limit to three Brownian motions produced in the mating-of-trees framework by Liouville quantum gravity (LQG) with parameter $1$, decorated with a triple of SLE$_{16}$'s curves. These three SLE$_{16}$'s curves are coupled such that the angle difference between them is $2π/3$ in imaginary geometry. Our convergence result provides a description of the continuum limit of Schnyder's embedding algorithm via LQG and SLE.

math.PR↗

arXiv2022

A Repulsive Force Unit for Garment Collision Handling in Neural Networks

Despite recent success, deep learning-based methods for predicting 3D garment deformation under body motion suffer from interpenetration problems between the garment and the body. To address this problem, we propose a novel collision handling neural network layer called Repulsive Force Unit (ReFU). Based on the signed distance function (SDF) of the underlying body and the current garment vertex positions, ReFU predicts the per-vertex offsets that push any interpenetrating vertex to a collision-free configuration while preserving the fine geometric details. We show that ReFU is differentiable with trainable parameters and can be integrated into different network backbones that predict 3D garment deformations. Our experiments show that ReFU significantly reduces the number of collisions between the body and the garment and better preserves geometric details compared to prior methods based on collision loss or post-processing optimization.

cs.GR↗