arXiv subjects

Xin Sun

Publications and source records attributed to Xin Sun.

At least 127 records · Page 7Linked to original sources

arXiv2024

SLE Loop Measure and Liouville Quantum Gravity

As recently shown by Holden and two of the authors, the conformal welding of two Liouville quantum gravity (LQG) disks produces a canonical variant of SLE curve whose law is called the SLE loop measure. In this paper, we demonstrate how LQG can be used to study the SLE loop measure. Firstly, we show that for $κ\in (8/3,8)$, the loop intensity measure of the conformal loop ensemble agrees with the SLE loop measure as defined by Zhan (2021). The former was initially considered by Kemppainen and Werner (2016) for $κ\in (8/3,4]$, and the latter was constructed for $κ\in (0,8)$. Secondly, we establish a duality for the SLE loop measure between $κ$ and $16/κ$. Thirdly, we obtain the exact formula for the moment of the electrical thickness for the shape (probability) measure of the SLE loop, which in the regime $κ\in (8/3,8)$ was conjectured by Kenyon and Wilson (2004). This relies on the exact formulae for the reflection coefficient and the one-point disk correlation function in Liouville conformal field theory. Finally, we compute several multiplicative constants associated with the SLE loop measure, which are not only of intrinsic interest but also used in our companion paper relating the conformal loop ensemble to the imaginary DOZZ formulae.

math.PR↗

arXiv2024

Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies

Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI). However, the inherent lack of transparency in LLM outputs presents significant challenges given the sensitive nature of psychotherapy. Applying MI strategies, a set of MI skills, to generate more controllable therapeutic-adherent conversations with explainability provides a possible solution. In this work, we explore the alignment of LLMs with MI strategies by first prompting the LLMs to predict the appropriate strategies as reasoning and then utilizing these strategies to guide the subsequent dialogue generation. We seek to investigate whether such alignment leads to more controllable and explainable generations. Multiple experiments including automatic and human evaluations are conducted to validate the effectiveness of MI strategies in aligning psychotherapy dialogue generation. Our findings demonstrate the potential of LLMs in producing strategically aligned dialogues and suggest directions for practical applications in psychotherapeutic settings.

cs.CL↗

arXiv2024

SLE partition functions via conformal welding of random surfaces

SLE curves describe the scaling limit of interfaces from many 2D lattice models. Heuristically speaking, the SLE partition function is the continuum counterpart of the partition function of the corresponding discrete model. It is well known that conformally welding of Liouville quantum gravity (LQG) surfaces gives SLE curves as the interfaces. In this paper, we demonstrate in several settings how the SLE partition function arises from conformal welding of LQG surfaces. The common theme is that we conformally weld a collection of canonical LQG surfaces which produces a topological configuration with more than one conformal structure. Conditioning on the conformal moduli, the surface after welding is described by Liouville conformal field theory (LCFT), and the density of the random moduli contains the SLE partition function for the interfaces as a multiplicative factor. The settings we treat includes the multiple SLE for $κ\in (0,4)$, the flow lines of imaginary geometry on the disk with boundary marked points, and the boundary Green function. These results demonstrate an alternative approach to construct and study the SLE partition function, which complements the traditional method based on stochastic calculus and differential equation.

math.PR↗

arXiv2024

Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction

Molecular property prediction (MPP) is integral to drug discovery and material science, but often faces the challenge of data scarcity in real-world scenarios. Addressing this, few-shot molecular property prediction (FSMPP) has been developed. Unlike other few-shot tasks, FSMPP typically employs a pre-trained molecular encoder and a context-aware classifier, benefiting from molecular pre-training and molecular context information. Despite these advancements, existing methods struggle with the ineffective fine-tuning of pre-trained encoders. We attribute this issue to the imbalance between the abundance of tunable parameters and the scarcity of labeled molecules, and the lack of contextual perceptiveness in the encoders. To overcome this hurdle, we propose a parameter-efficient in-context tuning method, named Pin-Tuning. Specifically, we propose a lightweight adapter for pre-trained message passing layers (MP-Adapter) and Bayesian weight consolidation for pre-trained atom/bond embedding layers (Emb-BWC), to achieve parameter-efficient tuning while preventing over-fitting and catastrophic forgetting. Additionally, we enhance the MP-Adapters with contextual perceptiveness. This innovation allows for in-context tuning of the pre-trained encoder, thereby improving its adaptability for specific FSMPP tasks. When evaluated on public datasets, our method demonstrates superior tuning with fewer trainable parameters, improving few-shot predictive performance.

cs.LG↗

arXiv2024

LRM-Zero: Training Large Reconstruction Models with Synthesized Data

We present LRM-Zero, a Large Reconstruction Model (LRM) trained entirely on synthesized 3D data, achieving high-quality sparse-view 3D reconstruction. The core of LRM-Zero is our procedural 3D dataset, Zeroverse, which is automatically synthesized from simple primitive shapes with random texturing and augmentations (e.g., height fields, boolean differences, and wireframes). Unlike previous 3D datasets (e.g., Objaverse) which are often captured or crafted by humans to approximate real 3D data, Zeroverse completely ignores realistic global semantics but is rich in complex geometric and texture details that are locally similar to or even more intricate than real objects. We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse. We also analyze several critical design choices of Zeroverse that contribute to LRM-Zero's capability and training stability. Our work demonstrates that 3D reconstruction, one of the core tasks in 3D vision, can potentially be addressed without the semantics of real-world objects. The Zeroverse's procedural synthesis code and interactive visualization are available at: https://desaixie.github.io/lrm-zero/.

cs.CV↗

arXiv2024

RNA: Relightable Neural Assets

High-fidelity 3D assets with materials composed of fibers (including hair), complex layered material shaders, or fine scattering geometry are ubiquitous in high-end realistic rendering applications. Rendering such models is computationally expensive due to heavy shaders and long scattering paths. Moreover, implementing the shading and scattering models is non-trivial and has to be done not only in the 3D content authoring software (which is necessarily complex), but also in all downstream rendering solutions. For example, web and mobile viewers for complex 3D assets are desirable, but frequently cannot support the full shading complexity allowed by the authoring application. Our goal is to design a neural representation for 3D assets with complex shading that supports full relightability and full integration into existing renderers. We provide an end-to-end shading solution at the first intersection of a ray with the underlying geometry. All shading and scattering is precomputed and included in the neural asset; no multiple scattering paths need to be traced, and no complex shading models need to be implemented to render our assets, beyond a single neural architecture. We combine an MLP decoder with a feature grid. Shading consists of querying a feature vector, followed by an MLP evaluation producing the final reflectance value. Our method provides high-fidelity shading, close to the ground-truth Monte Carlo estimate even at close-up views. We believe our neural assets could be used in practical renderers, providing significant speed-ups and simplifying renderer implementations.

cs.GR↗

arXiv2024

Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology

This paper addresses the persistent challenge in Keyword Spotting (KWS), a fundamental component in speech technology, regarding the acquisition of substantial labeled data for training. Given the difficulty in obtaining large quantities of positive samples and the laborious process of collecting new target samples when the keyword changes, we introduce a novel approach combining unsupervised contrastive learning and a unique augmentation-based technique. Our method allows the neural network to train on unlabeled data sets, potentially improving performance in downstream tasks with limited labeled data sets. We also propose that similar high-level feature representations should be employed for speech utterances with the same keyword despite variations in speed or volume. To achieve this, we present a speech augmentation-based unsupervised learning method that utilizes the similarity between the bottleneck layer feature and the audio reconstructing information for auxiliary training. Furthermore, we propose a compressed convolutional architecture to address potential redundancy and non-informative information in KWS tasks, enabling the model to simultaneously learn local features and focus on long-term information. This method achieves strong performance on the Google Speech Commands V2 Dataset. Inspired by recent advancements in sign spotting and spoken term detection, our method underlines the potential of our contrastive learning approach in KWS and the advantages of Query-by-Example Spoken Term Detection strategies. The presented CAB-KWS provide new perspectives in the field of KWS, demonstrating effective ways to reduce data collection efforts and increase the system's robustness.

cs.SD↗

arXiv2024

Quantum triangles and imaginary geometry flow lines

We define a three-parameter family of random surfaces in Liouville quantum gravity (LQG) which can be viewed as the quantum version of triangles. These quantum triangles are natural in two senses. First, by our definition they produce the boundary three-point correlation functions of Liouville conformal field theory on the disk. Second, it turns out that the laws of the triangles bounded by flow lines in imaginary geometry coupled with LQG are given by these quantum triangles. In this paper we demonstrate the second point for boundary flow lines on a quantum disk. Our method has the potential to prove general conformal welding results with quantum triangles glued in an arbitrary way. Quantum triangles play a basic role in understanding the integrability of SLE and LQG via conformal welding. In this paper, we deduce integrability results for chordal SLE with three force points, using the conformal welding of a quantum triangle and a two-pointed quantum disk. In a subsequent work we will explore their applications to the mating-of-trees framework of LQG, including the exact evaluation of the expected proportion of inversions in skew Brownian permutons.

math.PR↗

arXiv2024

Boundary touching probability and nested-path exponent for non-simple CLE

The conformal loop ensemble (CLE) has two phases: for $κ\in (8/3, 4]$, the loops are simple and do not touch each other or the boundary; for $κ\in (4,8)$, the loops are non-simple and may touch each other and the boundary. For $κ\in(4,8)$, we derive the probability that the loop surrounding a given point touches the domain boundary. We also obtain the law of the conformal radius of this loop seen from the given point conditioned on the loop touching the boundary or not, refining a result of Schramm-Sheffield-Wilson (2009). As an application, we exactly evaluate the CLE counterpart of the nested-path exponent for the Fortuin-Kasteleyn (FK) random cluster model recently introduced by Song-Tan-Zhang-Jacobsen-Nienhuis-Deng (2022). This exponent describes the asymptotic behavior of the number of nested open paths in the open cluster containing the origin when the cluster is large. For Bernoulli percolation, which corresponds to $κ=6$, the exponent was derived recently in Song-Jacobsen-Nienhuis-Sportiello-Deng (2023) by a color switching argument. For $κ\neq 6$, and in particular for the FK-Ising case, our formula appears to be new. Our derivation begins with Sheffield's construction of CLE from which the quantities of interest can be expressed by radial SLE. We solve the radial SLE problem using the coupling between SLE and Liouville quantum gravity, along with the exact solvability of Liouville conformal field theory.

math.PR↗

arXiv2024

OpenVoice: Versatile Instant Voice Cloning

We introduce OpenVoice, a versatile voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages. OpenVoice represents a significant advancement in addressing the following open challenges in the field: 1) Flexible Voice Style Control. OpenVoice enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone color of the reference speaker. The voice styles are not directly copied from and constrained by the style of the reference speaker. Previous approaches lacked the ability to flexibly manipulate voice styles after cloning. 2) Zero-Shot Cross-Lingual Voice Cloning. OpenVoice achieves zero-shot cross-lingual voice cloning for languages not included in the massive-speaker training set. Unlike previous approaches, which typically require extensive massive-speaker multi-lingual (MSML) dataset for all languages, OpenVoice can clone voices into a new language without any massive-speaker training data for that language. OpenVoice is also computationally efficient, costing tens of times less than commercially available APIs that offer even inferior performance. To foster further research in the field, we have made the source code and trained model publicly accessible. We also provide qualitative results in our demo website. OpenVoice has been used by more than 2M users worldwide as the voice engine of MyShell.ai

cs.SD↗

arXiv2024

HSDreport: Heart Sound Diagnosis with Echocardiography Reports

Heart sound auscultation holds significant importance in the diagnosis of congenital heart disease. However, existing methods for Heart Sound Diagnosis (HSD) tasks are predominantly limited to a few fixed categories, framing the HSD task as a rigid classification problem that does not fully align with medical practice and offers only limited information to physicians. Besides, such methods do not utilize echocardiography reports, the gold standard in the diagnosis of related diseases. To tackle this challenge, we introduce HSDreport, a new benchmark for HSD, which mandates the direct utilization of heart sounds obtained from auscultation to predict echocardiography reports. This benchmark aims to merge the convenience of auscultation with the comprehensive nature of echocardiography reports. First, we collect a new dataset for this benchmark, comprising 2,275 heart sound samples along with their corresponding reports. Subsequently, we develop a knowledge-aware query-based transformer to handle this task. The intent is to leverage the capabilities of medically pre-trained models and the internal knowledge of large language models (LLMs) to address the task's inherent complexity and variability, thereby enhancing the robustness and scientific validity of the method. Furthermore, our experimental results indicate that our method significantly outperforms traditional HSD approaches and existing multimodal LLMs in detecting key abnormalities in heart sounds.

cs.SD↗

arXiv2024

DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization

This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between source and target data distributions. Traditional graph learning algorithms, based on the assumption of uniform distribution between training and test data, falter in real-world scenarios where this assumption fails, resulting in suboptimal performance. A principal factor contributing to this suboptimal performance is the inherent simplicity bias of neural networks trained through Stochastic Gradient Descent (SGD), which prefer simpler features over more complex yet equally or more predictive ones. This bias leads to a reliance on spurious correlations, adversely affecting OOD performance in various tasks such as image recognition, natural language understanding, and graph classification. Current methodologies, including subgraph-mixup and information bottleneck approaches, have achieved partial success but struggle to overcome simplicity bias, often reinforcing spurious correlations. To tackle this, we propose DIVE, training a collection of models to focus on all label-predictive subgraphs by encouraging the models to foster divergence on the subgraph mask, which circumvents the limitation of a model solely focusing on the subgraph corresponding to simple structural patterns. Specifically, we employs a regularizer to punish overlap in extracted subgraphs across models, thereby encouraging different models to concentrate on distinct structural patterns. Model selection for robust OOD performance is achieved through validation accuracy. Tested across four datasets from GOOD benchmark and one dataset from DrugOOD benchmark, our approach demonstrates significant improvement over existing methods, effectively addressing the simplicity bias and enhancing generalization in graph machine learning.

cs.LG↗

arXiv2024

Toward Ubiquitous 3D Object Digitization: A Wearable Computing Framework for Non-Invasive Physical Property Acquisition

Accurately digitizing physical objects is central to many applications, including virtual/augmented reality, industrial design, and e-commerce. Prior research has demonstrated efficient and faithful reconstruction of objects' geometric shapes and visual appearances, which suffice for digitally representing rigid objects. In comparison, physical properties, such as elasticity and pressure, are also indispensable to the behavioral fidelity of digitized deformable objects. However, existing approaches to acquiring these quantities either rely on invasive specimen collection or expensive/bulky laboratory setups, making them inapplicable to consumer-level usage. To fill this gap, we propose a wearable and non-invasive computing framework that allows users to conveniently estimate the material elasticity and internal pressure of deformable objects through finger touches. This is achieved by modeling their local surfaces as pressurized elastic shells and analytically deriving the two physical properties from finger-induced wrinkling patterns. Together with photogrammetry-reconstructed geometry and textures, the two estimated physical properties enable us to faithfully replicate the motion and deformation behaviors of several deformable objects. For the pressure estimation, our model achieves a relative error of 3.5%. In the interaction experiments, the virtual-physical deformation discrepancy measures less than 10.1%. Generalization to objects of irregular shape further demonstrates the potential of our approach in practical applications. We envision this work to provide insights for and motivate research toward democratizing the ubiquitous and pervasive digitization of our physical surroundings in daily, industrial, and scientific scenarios.

cs.GR↗

arXiv2024

MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models

Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce "MedBench", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure, with physical separations for question and ground truth. Third, MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer remembering. Applying MedBench to popular general and medical LLMs, we observe unbiased, reproducible evaluation results largely aligning with medical professionals' perspectives. This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs. MedBench is publicly accessible at https://medbench.opencompass.org.cn.

cs.CL↗

arXiv2024

On the Relative Completeness of Satisfaction-based Probabilistic Hoare Logic With While Loop

Probabilistic Hoare logic (PHL) is an extension of Hoare logic and is specifically useful in verifying randomized programs. It allows researchers to formally reason about the behavior of programs with stochastic elements, ensuring the desired probabilistic properties are upheld. The relative completeness of satisfaction-based PHL has been an open problem ever since the birth of the first PHL in 1979. More specifically, no satisfaction-based PHL with While-loop has been proven to be relatively complete yet. This paper solves this problem by establishing a new PHL with While-loop and prove its relative completeness. The programming language concerned in our PHL is expressively equivalent to the existing PHL systems but brings a lot of convenience in showing completeness. The weakest preterm for While-loop command reveals how it changes the probabilistic properties of computer states, considering both execution branches that halt and infinite runs. We prove the relative completeness of our PHL in two steps. We first establish a semantics and proof system of Hoare triples with probabilistic programs and deterministic assertions. Then, by utilizing the weakest precondition of deterministic assertions, we construct the weakest preterm calculus of probabilistic expressions. The relative completeness of our PHL is then obtained as a consequence of the weakest preterm calculus.

cs.LO↗

arXiv2024

On the Relative Completeness of Satisfaction-based Quantum Hoare Logic

Quantum Hoare logic (QHL) is a formal verification tool specifically designed to ensure the correctness of quantum programs. There has been an ongoing challenge to achieve a relatively complete satisfaction-based QHL with while-loop since its inception in 2006. This paper presents a solution by proposing the first relatively complete satisfaction-based QHL with while-loop. The completeness is proved in two steps. First, we establish a semantics and proof system of Hoare triples with quantum programs and deterministic assertions. Then, by utilizing the weakest precondition of deterministic assertion, we construct the weakest preterm calculus of probabilistic expressions. The relative completeness of QHL is then obtained as a consequence of the weakest preterm calculus. Using our QHL, we formally verify the correctness of Deutsch's algorithm and quantum teleportation.

cs.LO↗

arXiv2024

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

Multi-view diffusion models, obtained by applying Supervised Finetuning (SFT) to text-to-image diffusion models, have driven recent breakthroughs in text-to-3D research. However, due to the limited size and quality of existing 3D datasets, they still suffer from multi-view inconsistencies and Neural Radiance Field (NeRF) reconstruction artifacts. We argue that multi-view diffusion models can benefit from further Reinforcement Learning Finetuning (RLFT), which allows models to learn from the data generated by themselves and improve beyond their dataset limitations during SFT. To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models. To measure the MRC metric on a set of multi-view images, we compare them with their corresponding NeRF renderings at the same camera viewpoints. The resulting model, which we denote as Carve3DM, demonstrates superior multi-view consistency and NeRF reconstruction quality than existing models. Our results suggest that pairing SFT with Carve3D's RLFT is essential for developing multi-view-consistent diffusion models, mirroring the standard Large Language Model (LLM) alignment pipeline. Our code, training and testing data, and video results are available at: https://desaixie.github.io/carve-3d.

cs.CV↗

arXiv2024

Derivation of all structure constants for boundary Liouville CFT

We prove that the probabilistic definition of the most general boundary three-point and bulk-boundary structure constants in Liouville conformal field theory (LCFT) agree respectively with the formula proposed by Ponsot-Techsner (2002) and by Hosomichi (2001). These formulas also respectively describe the fusion kernel and modular kernel of the Virasoro conformal blocks, which are important functions in various contexts of mathematical physics. As an intermediate step, we obtain the formula for the boundary reflection coefficient of LCFT proposed by Fateev-Zamolodchikov-Zamolodchikov (2000). Our proof relies on the boundary Belavin-Polyakov-Zamolodchikov differential equation recently proved by the first named author, and inputs from the coupling theory of Liouville quantum gravity (LQG) and Schramm Loewner evolution. Our results supply all the structure constants needed to perform the conformal bootstrap for boundary LCFT. They also yield exact descriptions for the joint law of the area and boundary lengths of basic LQG surfaces, including quantum triangles and two-pointed quantum disks.

math.PR↗