Search

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., Comment: Accepted by NeurIPS 2024

Phytoplankton are a crucial component of aquatic ecosystems, and effective monitoring of them can provide valuable insights into ocean environments and ecosystem changes. Traditional phytoplankton monitoring methods are often complex and lack timely analysis. Therefore, deep learning algorithms offer a promising approach for automated phytoplankton monitoring. However, the lack of large-scale, high-quality training samples has become a major bottleneck in advancing phytoplankton tracking. In this paper, we propose a challenging benchmark dataset, Multiple Phytoplankton Tracking (MPT), which covers diverse background information and variations in motion during observation. The dataset includes 27 species of phytoplankton and zooplankton, 14 different backgrounds to simulate diverse and complex underwater environments, and a total of 140 videos. To enable accurate real-time observation of phytoplankton, we introduce a multi-object tracking method, Deviation-Corrected Multi-Scale Feature Fusion Tracker(DSFT), which addresses issues such as focus shifts during tracking and the loss of small target information when computing frame-to-frame similarity. Specifically, we introduce an additional feature extractor to predict the residuals of the standard feature extractor's output, and compute multi-scale frame-to-frame similarity based on features from different layers of the extractor. Extensive experiments on the MPT have demonstrated the validity of the dataset and the superiority of DSFT in tracking phytoplankton, providing an effective solution for phytoplankton monitoring.

The conformal loop ensemble (CLE) is a conformally invariant random collection of loops. In the non-simple regime $\kappa'\in (4,8)$, it describes the scaling limit of the critical Fortuin-Kasteleyn (FK) percolations. CLE percolations were introduced by Miller-Sheffield-Werner (2017). The CLE$_{\kappa'}$ percolations describe the scaling limit of a natural variant of the FK percolation called the fuzzy Potts model, which has an additional percolation parameter $r$. Based on CLE percolations and assuming that the convergence of the FK percolation to CLE, K{\"o}hler-Schindler and Lehmkuehler (2022) derived all the arm exponents for the fuzzy Potts model except the bulk one-arm exponent. In this paper, we exactly solve this exponent, which prescribes the dimension of the clusters in CLE$_{\kappa'}$ percolations. As a special case, the bichromatic one-arm exponent for the critical 3-state Potts model should be $4/135$. To the best of our knowledge, this natural exponent was not predicted in physics. Our derivation relies on the iterative construction of CLE percolations from the boundary conformal loop ensemble (BCLE), and the coupling between Liouville quantum gravity and SLE curves. The source of the exact solvability comes from the structure constants of boundary Liouville conformal field theory. A key technical step is to prove a conformal welding result for the target-invariant radial SLE curves. As intermediate steps in our derivation, we obtain several exact results for BCLE in both the simple and non-simple regimes, which extend results of Ang-Sun-Yu-Zhuang (2024) on the touching probability of non-simple CLE. This also provides an alternative derivation of the relation between the BCLE parameter $\rho$ and the additional percolation parameter $r$ in CLE percolations, which was originally due to Miller-Sheffield-Werner (2021, 2022)., Comment: 49 pages, 13 figures

We report the recent derivation of the backbone exponent for 2D percolation. In contrast to previously known exactly solved percolation exponents, the backbone exponent is a transcendental number, which is a root of an elementary equation. We also report an exact formula for the probability that there are two disjoint paths of the same color crossing an annulus. The backbone exponent captures the leading asymptotic, while the other roots of the elementary equation capture the asymptotic of the remaining terms. This suggests that the backbone exponent is part of a conformal field theory (CFT) whose bulk spectrum contains this set of roots. Our approach is based on the coupling between SLE curves and Liouville quantum gravity (LQG), and the integrability of Liouville CFT that governs the LQG surfaces., Comment: 5 pages, 3 figures

We derive exact formulae for three basic annulus crossing events for the critical planar Bernoulli percolation in the continuum limit. The first is for the probability that there is an open path connecting the two boundaries of an annulus of inner radius $r$ and outer radius $R$. The second is for the probability that there are both open and closed paths connecting the two annulus boundaries. These two results were predicted by Cardy based on non-rigorous Coulomb gas arguments. Our third result gives the probability that there are two disjoint open paths connecting the two boundaries. Its leading asymptotic as $r/R\to 0$ is captured by the so-called backbone exponent, a transcendental number recently determined by Nolin, Qian and two of the authors. This exponent is the unique real root to the equation $\frac{\sqrt{36 x +3}}{4} + \sin (\frac{2 \pi \sqrt{12 x +1}}{3} ) =0$, other than $-\frac{1}{12}$ and $\frac{1}{4}$. Besides these three real roots, this equation has countably many complex roots. Our third result shows that these roots appear exactly as exponents of the subleading terms in the crossing formula. This suggests that the backbone exponent is part of a conformal field theory (CFT) whose bulk spectrum contains this set of roots. Expanding the same crossing probability as $r/R\to 1$, we obtain a series with logarithmic corrections at every order, suggesting that the backbone exponent is related to a logarithmic boundary CFT. Our proofs are based on the coupling between SLE curves and Liouville quantum gravity (LQG). The key is to encode the annulus crossing probabilities by the random moduli of certain LQG surfaces with annular topology, whose law can be extracted from the dependence of the LQG annuli partition function on their boundary lengths., Comment: 42 pages, 7 figures

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 $\kappa\in (8/3,8)$, 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 $\kappa\in (8/3,4]$, and the latter was constructed for $\kappa\in (0,8)$. Secondly, we establish a duality for the SLE loop measure between $\kappa$ and $16/\kappa$. 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 $\kappa\in (8/3,8)$ 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., Comment: Results in the simple-loop regime except for the evaluation of certain constants were originally contained in arXiv:2107.01788 by the first and the third authors. Results in the non-simple regime are new. 80 pages, 10 figures

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., Comment: This paper has been accepted by the ICPR2024

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.

Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, especially in Motivational Interviewing (MI). However, how to employ strategies, a set of motivational interviewing (MI) skills, to generate therapeutic-adherent conversations with explainability is underexplored. We propose an approach called strategy-aware dialogue generation with Chain-of-Strategy (CoS) planning, which first predicts MI strategies as reasoning and utilizes these strategies to guide the subsequent dialogue generation. It brings the potential for controllable and explainable generation in psychotherapy by aligning the generated MI dialogues with therapeutic strategies. Extensive experiments including automatic and human evaluations are conducted to validate the effectiveness of the MI strategy. Our findings demonstrate the potential of LLMs in producing strategically aligned dialogues and suggest directions for practical applications in psychotherapeutic settings.

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.

We present Perm, a learned parametric model of human 3D hair designed to facilitate various hair-related applications. Unlike previous work that jointly models the global hair shape and local strand details, we propose to disentangle them using a PCA-based strand representation in the frequency domain, thereby allowing more precise editing and output control. Specifically, we leverage our strand representation to fit and decompose hair geometry textures into low- to high-frequency hair structures. These decomposed textures are later parameterized with different generative models, emulating common stages in the hair modeling process. We conduct extensive experiments to validate the architecture design of \textsc{Perm}, and finally deploy the trained model as a generic prior to solve task-agnostic problems, further showcasing its flexibility and superiority in tasks such as 3D hair parameterization, hairstyle interpolation, single-view hair reconstruction, and hair-conditioned image generation. Our code, data, and supplemental can be found at our project page: https://cs.yale.edu/homes/che/projects/perm/, Comment: Project page: https://cs.yale.edu/homes/che/projects/perm/

Ellipsometry is used to indirectly measure the optical properties and thickness of thin films. However, solving the inverse problem of ellipsometry is time-consuming since it involves human expertise to apply the data fitting techniques. Many studies use traditional machine learning-based methods to model the complex mathematical fitting process. In our work, we approach this problem from a deep learning perspective. First, we introduce a large-scale benchmark dataset to facilitate deep learning methods. The proposed dataset encompasses 98 types of thin film materials and 4 types of substrate materials, including metals, alloys, compounds, and polymers, among others. Additionally, we propose a deep learning framework that leverages residual connections and self-attention mechanisms to learn the massive data points. We also introduce a reconstruction loss to address the common challenge of multiple solutions in thin film thickness prediction. Compared to traditional machine learning methods, our framework achieves state-of-the-art (SOTA) performance on our proposed dataset. The dataset and code will be available upon acceptance.

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., Comment: 10 pages, 6 figures

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., Comment: 25 pages.4 figures

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., Comment: 13 pages. arXiv admin note: text overlap with arXiv:2405.01940

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/., Comment: 23 pages, 8 figures. Our code and interactive visualization are available at: https://desaixie.github.io/lrm-zero/. v2: NeurIPS 2024 Camera Ready version

Manufacturing complexities and uncertainties have impeded the transition from material prototypes to commercial batteries, making prototype verification critical to quality assessment. A fundamental challenge involves deciphering intertwined chemical processes to characterize degradation patterns and their quantitative relationship with battery performance. Here we show that a physics-informed machine learning approach can quantify and visualize temporally resolved losses concerning thermodynamics and kinetics only using electric signals. Our method enables non-destructive degradation pattern characterization, expediting temperature-adaptable predictions of entire lifetime trajectories, rather than end-of-life points. The verification speed is 25 times faster yet maintaining 95.1% accuracy across temperatures. Such advances facilitate more sustainable management of defective prototypes before massive production, establishing a 19.76 billion USD scrap material recycling market by 2060 in China. By incorporating stepwise charge acceptance as a measure of the initial manufacturing variability of normally identical batteries, we can immediately identify long-term degradation variations. We attribute the predictive power to interpreting machine learning insights using material-agnostic featurization taxonomy for degradation pattern decoupling. Our findings offer new possibilities for dynamic system analysis, such as battery prototype degradation, demonstrating that complex pattern evolutions can be accurately predicted in a non-destructive and data-driven fashion by integrating physics-informed machine learning.

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., Comment: 35 pages

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., Comment: 24 pages

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.

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., Comment: Technical Report. Visit https://github.com/openmedlab for more details

The conformal loop ensemble (CLE) has two phases: for $\kappa \in (8/3, 4]$, the loops are simple and do not touch each other or the boundary; for $\kappa \in (4,8)$, the loops are non-simple and may touch each other and the boundary. For $\kappa\in(4,8)$, 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 $\kappa=6$, the exponent was derived recently in Song-Jacobsen-Nienhuis-Sportiello-Deng (2023) by a color switching argument. For $\kappa\neq 6$, 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., Comment: 42 pages, 14 figures; revised according to referee report. Accepted for publication in AOP

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., Comment: 22 pages, 16 figures. Our code, training and testing data, and video results are available at: https://desaixie.github.io/carve-3d. This paper has been accepted to CVPR 2024. v2: incorporated changes from the CVPR 2024 camera-ready version

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., Comment: Added Fig. 10 and Section 6.5 - new comparison

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, Comment: Technical Report