arXiv subjects

Yuanfeng Wang

Publications and source records attributed to Yuanfeng Wang.

4 recordsLinked to original sources

arXiv2025

Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoising

Building on recent advances in Bayesian statistics and image denoising, we propose Noise2Score3D, a fully unsupervised framework for point cloud denoising. Noise2Score3D learns the score function of the underlying point cloud distribution directly from noisy data, eliminating the need for clean data during training. Using Tweedie's formula, our method performs denoising in a single step, avoiding the iterative processes used in existing unsupervised methods, thus improving both accuracy and efficiency. Additionally, we introduce Total Variation for Point Clouds as a denoising quality metric, which allows for the estimation of unknown noise parameters. Experimental results demonstrate that Noise2Score3D achieves state-of-the-art performance on standard benchmarks among unsupervised learning methods in Chamfer distance and point-to-mesh metrics. Noise2Score3D also demonstrates strong generalization ability beyond training datasets. Our method, by addressing the generalization issue and challenge of the absence of clean data in learning-based methods, paves the way for learning-based point cloud denoising methods in real-world applications.

cs.CV↗

arXiv2025

Training Cross-Morphology Embodied AI Agents: From Practical Challenges to Theoretical Foundations

While theory and practice are often seen as separate domains, this article shows that theoretical insight is essential for overcoming real-world engineering barriers. We begin with a practical challenge: training a cross-morphology embodied AI policy that generalizes across diverse robot morphologies. We formalize this as the Heterogeneous Embodied Agent Training (HEAT) problem and prove it reduces to a structured Partially Observable Markov Decision Process (POMDP) that is PSPACE-complete. This result explains why current reinforcement learning pipelines break down under morphological diversity, due to sequential training constraints, memory-policy coupling, and data incompatibility. We further explore Collective Adaptation, a distributed learning alternative inspired by biological systems. Though NEXP-complete in theory, it offers meaningful scalability and deployment benefits in practice. This work illustrates how computational theory can illuminate system design trade-offs and guide the development of more robust, scalable embodied AI. For practitioners and researchers to explore this problem, the implementation code of this work has been made publicly available at https://github.com/airs-admin/HEAT

cs.AI↗

arXiv2024

Learning Parameterized Quantum Circuits with Quantum Gradient

Parameterized quantum circuits (PQCs) are crucial for quantum machine learning and circuit synthesis, enabling the practical implementation of complex quantum tasks. However, PQC learning has been largely confined to classical optimization methods, which suffer from issues like gradient vanishing. In this work, we introduce a nested optimization model that leverages quantum gradient to enhance PQC learning for polynomial-type cost functions. Our approach utilizes quantum algorithms to identify and overcome a type of gradient vanishing-a persistent challenge in PQC learning-by effectively navigating the optimization landscape. We also mitigate potential barren plateaus of our model and manage the learning cost via restricting the optimization region. Numerically, we demonstrate the feasibility of the approach on two tasks: the Max-Cut problem and polynomial optimization. The method excels in generating circuits without gradient vanishing and effectively optimizes the cost function. From the perspective of quantum algorithms, our model improves quantum optimization for polynomial-type cost functions, addressing the challenge of exponential sample complexity growth.

quant-ph↗

arXiv2011

Efficient Latent Variable Graphical Model Selection via Split Bregman Method

We consider the problem of covariance matrix estimation in the presence of latent variables. Under suitable conditions, it is possible to learn the marginal covariance matrix of the observed variables via a tractable convex program, where the concentration matrix of the observed variables is decomposed into a sparse matrix (representing the graphical structure of the observed variables) and a low rank matrix (representing the marginalization effect of latent variables). We present an efficient first-order method based on split Bregman to solve the convex problem. The algorithm is guaranteed to converge under mild conditions. We show that our algorithm is significantly faster than the state-of-the-art algorithm on both artificial and real-world data. Applying the algorithm to a gene expression data involving thousands of genes, we show that most of the correlation between observed variables can be explained by only a few dozen latent factors.

stat.ML↗