arXiv subjects

Xiang Ye

Publications and source records attributed to Xiang Ye.

9 recordsLinked to original sources

arXiv2026

A Bayesian regression framework for circular models with INLA

Regression models for circular variables are less developed, since the concept of building a linear predictor from linear combinations of covariates and various random effects, breaks the circular nature of the variable. In this paper, we introduce a new approach to rectify this issue, leading to well-defined regression models for circular responses when the data are concentrated. Our approach extends naturally to joint regression models where we can have several circular and non-circular responses, and allow us to handle a mix of linear covariates, circular covariates and various random effects. Our formulation aligns naturally with the integrated nested Laplace approximation (INLA), which provides fast and accurate Bayesian inference. We illustrate our approach through several simulated and real examples.

stat.ME↗

arXiv2025

MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation

We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven behaviors by leveraging personality signifiers such as Zodiac Signs and MBTI types, a Dialog Agent executing task-oriented persuasion strategies and an Optimization Agent evaluating and refining dialogue outcomes. We further validate its effectiveness through users' Chain-of-Attitude (CoA) modeling and dedicated LLMs' persuasion assessment. This approach enables low-cost generation of training data without human annotation, addressing key industry challenges such as lack of user data, cold-start evaluation difficulties, and prompt inefficiency. Applied to a real-world marketing scenario, MADS significantly improved the persuasion capacity of small LLMs, increasing the organic traffic conversion rate by 22.4% (from 1.83% to 2.24%) , demonstrating clear business value.

cs.CL↗

arXiv2025

Penalizing complexity priors for Bayesian inference of circular models

Advancements in computational power and methodologies have enabled research on massive datasets. However, tools for analyzing data with directional or periodic characteristics, such as wind directions and customers' arrival time in 24-hour clock, remain underdeveloped. While statisticians have proposed circular distributions for such analyses, significant challenges persist in constructing circular statistical models, particularly in the context of Bayesian methods. These challenges stem from limited theoretical development and a lack of historical studies on prior selection for circular distribution parameters. In this article, we propose a framework for selecting hyperpriors that contracts to a simpler model in circular scenarios, especially when there is insufficient information to guide prior selection. We introduce well-examined Penalized Complexity (PC) priors for the most widely used circular distributions. Comprehensive comparisons with existing hyperpriors in the literature are conducted through simulation studies and a practical case study. Finally, we discuss the contributions and implications of our work, providing a foundation for further advancements in constructing Bayesian circular statistical models.

stat.ME↗

arXiv2024

TALE-teller: Tendon-Actuated Linked Element Robotic Testbed for Investigating Tail Functions

Tails serve various functions in both robotics and biology, including expression, grasping, and defense. The vertebrate tails associated with these functions exhibit diverse patterns of vertebral lengths, but the precise mechanisms linking form to function have not yet been established. Vertebrate tails are complex musculoskeletal structures, making both direct experimentation and computational modeling challenging. This paper presents Tendon-Actuated Linked-Element (TALE), a modular robotic test bed to explore how tail morphology influences function. By varying 3D printed bones, silicone joints, and tendon configurations, TALE can match the morphology of extant, extinct, and even theoretical tails. We first characterized the stiffness of our joint design empirically and in simulation before testing the hypothesis that tails with different vertebral proportions curve differently. We then compared the maximum bending state of two common vertebrate proportions and one theoretical morphology. Uniform bending of joints with different vertebral proportions led to substantial differences in the location of the tail tip, suggesting a significant influence on overall tail function. Future studies can introduce more complex morphologies to establish the mechanisms of diverse tail functions. With this foundational knowledge, we will isolate the key features underlying tail function to inform the design for robotic tails. Images and videos can be found on TALE's project page: https://www.embirlab.com/tale.

cs.RO↗

arXiv2022

Canonical Mean Filter for Almost Zero-Shot Multi-Task classification

The support set is a key to providing conditional prior for fast adaption of the model in few-shot tasks. But the strict form of support set makes its construction actually difficult in practical application. Motivated by ANIL, we rethink the role of adaption in the feature extractor of CNAPs, which is a state-of-the-art representative few-shot method. To investigate the role, Almost Zero-Shot (AZS) task is designed by fixing the support set to replace the common scheme, which provides corresponding support sets for the different conditional prior of different tasks. The AZS experiment results infer that the adaptation works little in the feature extractor. However, CNAPs cannot be robust to randomly selected support sets and perform poorly on some datasets of Meta-Dataset because of its scattered mean embeddings responded by the simple mean operator. To enhance the robustness of CNAPs, Canonical Mean Filter (CMF) module is proposed to make the mean embeddings intensive and stable in feature space by mapping the support sets into a canonical form. CMFs make CNAPs robust to any fixed support sets even if they are random matrices. This attribution makes CNAPs be able to remove the mean encoder and the parameter adaptation network at the test stage, while CNAP-CMF on AZS tasks keeps the performance with one-shot tasks. It leads to a big parameter reduction. Precisely, 40.48\% parameters are dropped at the test stage. Also, CNAP-CMF outperforms CNAPs in one-shot tasks because it addresses inner-task unstable performance problems. Classification performance, visualized and clustering results verify that CMFs make CNAPs better and simpler.

cs.CV↗

arXiv2021

Towards Understanding the Effectiveness of Attention Mechanism

Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is popularly believed that its effectiveness stems from the visual attention explanation, advocating focusing on the important part of input data rather than ingesting the entire input. In this paper, we find that there is only a weak consistency between the attention weights of features and their importance. Instead, we verify the crucial role of feature map multiplication in attention mechanism and uncover a fundamental impact of feature map multiplication on the learned landscapes of CNNs: with the high order non-linearity brought by the feature map multiplication, it played a regularization role on CNNs, which made them learn smoother and more stable landscapes near real samples compared to vanilla CNNs. This smoothness and stability induce a more predictive and stable behavior in-between real samples, and make CNNs generate better. Moreover, motivated by the proposed effectiveness of feature map multiplication, we design feature map multiplication network (FMMNet) by simply replacing the feature map addition in ResNet with feature map multiplication. FMMNet outperforms ResNet on various datasets, and this indicates that feature map multiplication plays a vital role in improving the performance even without finely designed attention mechanism in existing methods.

cs.CV↗

arXiv2013

Conductance of Ferro- and Antiferro-magnetic single-atom contacts: A first-principles study

We present a first-principles study on the spin denpendent conductance of five single-atom magnetic junctions consisting of a magnetic tip and an adatom adsorbed on a magnetic surface, i.e., the Co-Co/Co(001) and Ni-X/Ni(001) (X=Fe, Co, Ni, Cu) junctions. When their spin configuration changes from ferromagnetism to anti-ferromagnetism, the spin-up conductance increases while the spin-down one decreases. For the junctions with a magnetic adatom, there is nearly no spin valve effect as the decreased spin-down conductance counteracts the increased spin-up one. For the junction with a nonmagnetic adatom (Ni-Cu/Ni(001)), a spin valve effect is obtained with a variation of 22% in the total conductance. In addition, the change in spin configuration enhances the spin filter effect for the Ni-Fe/Ni(001) junction but suppresses it for the other junctions.

cond-mat.mes-hall↗

arXiv2012

Conductance of single-atom magnetic junctions: A first-principles study

We present a first-principles investigation to show that the contact conductance of a half conductance quantum ($G_0/2$) found previously does not generally hold for single-atom magnetic junctions composed of a tip and an adatom dsorbed on a surface. The contact conductance of the Ni-Co/Co(111) junction is approximately $G_0/2$, while for the Co-Co/Co(111), Ni-Ni/Ni(111), and Ni-Ni/Ni(001) junctions the contact conductances are 0.80$G_0$, 1.55$G_0$, and 1.77$G_0$, respectively. The deviation from $G_0/2$ is mainly caused by the variation of the spin-down conductance largely determined by the minority $d$ orbitals, as the spin-up one changes little for different junctions.

cond-mat.mes-hall↗

arXiv2012

Pressure-induced structural transition of ZnO nanocrystals studied with molecular dynamics

We have studied the pressure-induced structural transition of ZnO nanocrystals using constant pressure molecular dynamics simulations for finite system. We have observed the transition from the fourfold coordination wurtzite to the sixfold coordination rocksalt structure, and the process of transition is strongly dependent on the morphology of the nanocrystals. It is found that the perfect faceted ZnO nanocrystals undergo wurtzite to rocksalt transition with a perfect fivefold h-MgO structure as the intermediate status. But for the faceted ones without perfect surface structure, as the number of the atoms removed from the (001) and (00-1) surface edge increases, the local morphology will become more similar to spherical. The nanocrystal will receive equal stress from every direction and it will be more difficult to compress the structure along only c axis as the perfect faceted ZnO nanocrystal. In this situation, only partial structure experiences intermediate fivefold coordination structure or even no intermediate fivefold coordination structure exists dependent on the surface disorder level.

cond-mat.mtrl-sci↗