Efficient Exploration Is Enough
本文研究在无外部奖励情况下，通过优先生成可泛化的经验来实现高效探索，理论上和实证上展示了该方法能自动产生复杂行为。
0 citationsRead paper
Selected work
Representative Papers
IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing
为解决无线感知中环境识别的领域迁移问题，提出结合IIns-VAE与最小最大风险分类器的IIns-VAE+框架，提升模型在不同场景下的适应性和鲁棒性。
0 citationsRead paper
A Deep Generative Model for Synthesizing Labeled Wireless Signals
为解决无线信号数据获取成本高、合成不真实的问题，提出一种基于深度学习的Inter-Instance Generative Adversarial Networks方法来生成带标签的无线信号。
0 citationsRead paper
Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening
研究通过跨数据集评估机器学习和深度学习的咳嗽模型在结核病筛查中的泛化能力，发现模型受数据采集设备影响大，泛化性能不佳。
0 citationsRead paper
SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
This work investigates the non-asymptotic characterization of posterior contraction rates and finite-sample Bernstein–von Mises (BvM) behavior in nonparametric Bayesian models. By interpreting the posterior distribution as the invariant measure of a Langevin stochastic partial differential equation (SPDE) on a separable Hilbert space, the study extends diffusion-based analytical frameworks to infinite-dimensional settings for the first time. This approach enables precise control over posterior moments and yields sharp non-asymptotic concentration rates in Hilbert norm, along with a quantitative Laplace approximation of the posterior. In the context of nonparametric linear Gaussian inverse problems, the theory elucidates how likelihood curvature and prior regularity jointly govern posterior contraction rates and finite-sample BvM phenomena.
0 citationsRead paper
Recent publications
Latest Papers
Efficient Exploration Is Enough
本文研究在无外部奖励情况下，通过优先生成可泛化的经验来实现高效探索，理论上和实证上展示了该方法能自动产生复杂行为。
0 citationsRead paper
IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing
为解决无线感知中环境识别的领域迁移问题，提出结合IIns-VAE与最小最大风险分类器的IIns-VAE+框架，提升模型在不同场景下的适应性和鲁棒性。
0 citationsRead paper
A Deep Generative Model for Synthesizing Labeled Wireless Signals
为解决无线信号数据获取成本高、合成不真实的问题，提出一种基于深度学习的Inter-Instance Generative Adversarial Networks方法来生成带标签的无线信号。
0 citationsRead paper
Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening
研究通过跨数据集评估机器学习和深度学习的咳嗽模型在结核病筛查中的泛化能力，发现模型受数据采集设备影响大，泛化性能不佳。
0 citationsRead paper
SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
This work investigates the non-asymptotic characterization of posterior contraction rates and finite-sample Bernstein–von Mises (BvM) behavior in nonparametric Bayesian models. By interpreting the posterior distribution as the invariant measure of a Langevin stochastic partial differential equation (SPDE) on a separable Hilbert space, the study extends diffusion-based analytical frameworks to infinite-dimensional settings for the first time. This approach enables precise control over posterior moments and yields sharp non-asymptotic concentration rates in Hilbert norm, along with a quantitative Laplace approximation of the posterior. In the context of nonparametric linear Gaussian inverse problems, the theory elucidates how likelihood curvature and prior regularity jointly govern posterior contraction rates and finite-sample BvM phenomena.
0 citationsRead paper