no code implementations • 13 Sep 2017 • Yaodong Yang, Lantao Yu, Yiwei Bai, Jun Wang, Wei-Nan Zhang, Ying Wen, Yong Yu
We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning.
no code implementations • 6 Nov 2018 • Yufei Wang, Zheyuan Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, Fei Fang
Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal logging and overfishing.
no code implementations • 21 Nov 2019 • Yuxuan Song, Lantao Yu, Zhangjie Cao, Zhiming Zhou, Jian Shen, Shuo Shao, Wei-Nan Zhang, Yong Yu
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available.
no code implementations • 12 Jul 2020 • Yuxuan Song, Ning Miao, Hao Zhou, Lantao Yu, Mingxuan Wang, Lei LI
Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios.
no code implementations • NeurIPS 2020 • Chenlin Meng, Lantao Yu, Yang song, Jiaming Song, Stefano Ermon
To increase flexibility, we propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariate log-conditionals (scores), which need not be normalized.
no code implementations • 20 Jan 2021 • Yuanhao Gong, Wenming Tang, Lebin Zhou, Lantao Yu, Guoping Qiu
Weighted Gaussian Curvature is an important measurement for images.
no code implementations • 20 Jan 2021 • Yuanhao Gong, Wenming Tang, Lebin Zhou, Lantao Yu, Guoping Qiu
The proposed filter can be adopted in a wide range of image processing applications.
no code implementations • 17 Mar 2021 • Lantao Yu, Dehong Liu, Hassan Mansour, Petros T. Boufounos
First, we estimate the blur kernel by computing the kernel coefficients with minimum total generalized variation that blur a downsampled version of the PAN image to approximate a linear combination of the LRMS image channels.
no code implementations • 10 Jul 2021 • Hongwei Wang, Lantao Yu, Zhangjie Cao, Stefano Ermon
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems.
no code implementations • 31 Jul 2021 • Lantao Yu, Kuida Liu, Michael T. Orchard
To overcome the challenge in the second part, we propose to use the aliasing-removed image to guide the initialization of the interpolated image and develop a progressive scheme to refine the interpolated image based on manifold models.
no code implementations • 29 Sep 2021 • Willie Neiswanger, Lantao Yu, Shengjia Zhao, Chenlin Meng, Stefano Ermon
For special cases of the loss and design space, we develop gradient-based methods to efficiently optimize our proposed family of acquisition functions, and demonstrate that the resulting BO procedure shows strong empirical performance on a diverse set of optimization tasks.
no code implementations • NeurIPS 2021 • Lantao Yu, Jiaming Song, Yang song, Stefano Ermon
Energy-based models (EBMs) offer flexible distribution parametrization.
no code implementations • 7 Dec 2021 • Lantao Yu, Yujia Jin, Stefano Ermon
Binary density ratio estimation (DRE), the problem of estimating the ratio $p_1/p_2$ given their empirical samples, provides the foundation for many state-of-the-art machine learning algorithms such as contrastive representation learning and covariate shift adaptation.
no code implementations • 4 Oct 2022 • Willie Neiswanger, Lantao Yu, Shengjia Zhao, Chenlin Meng, Stefano Ermon
Bayesian optimization (BO) is a popular method for efficiently inferring optima of an expensive black-box function via a sequence of queries.
no code implementations • 5 Mar 2023 • Lantao Yu, Tianhe Yu, Jiaming Song, Willie Neiswanger, Stefano Ermon
In this case, a well-known issue is the distribution shift between the learned policy and the behavior policy that collects the offline data.
no code implementations • 7 Nov 2023 • Xingzhe He, Zhiwen Cao, Nicholas Kolkin, Lantao Yu, Kun Wan, Helge Rhodin, Ratheesh Kalarot
This strategy enables the model to preserve fine details of the desired subjects, such as text and logos.
no code implementations • 26 Dec 2023 • Lu Ling, Yichen Sheng, Zhi Tu, Wentian Zhao, Cheng Xin, Kun Wan, Lantao Yu, Qianyu Guo, Zixun Yu, Yawen Lu, Xuanmao Li, Xingpeng Sun, Rohan Ashok, Aniruddha Mukherjee, Hao Kang, Xiangrui Kong, Gang Hua, Tianyi Zhang, Bedrich Benes, Aniket Bera
We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS).
no code implementations • 21 Mar 2024 • Yuanhao Gong, Lantao Yu, Guanghui Yue
The 3D Gaussian splatting method has drawn a lot of attention, thanks to its high performance in training and high quality of the rendered image.
1 code implementation • 3 Apr 2020 • Yuxuan Song, Minkai Xu, Lantao Yu, Hao Zhou, Shuo Shao, Yong Yu
In this paper, motivated by the inherent connections between neural joint source-channel coding and discrete representation learning, we propose a novel regularization method called Infomax Adversarial-Bit-Flip (IABF) to improve the stability and robustness of the neural joint source-channel coding scheme.
1 code implementation • 15 Feb 2019 • Zhiming Zhou, Jiadong Liang, Yuxuan Song, Lantao Yu, Hongwei Wang, Wei-Nan Zhang, Yong Yu, Zhihua Zhang
By contrast, Wasserstein GAN (WGAN), where the discriminative function is restricted to 1-Lipschitz, does not suffer from such a gradient uninformativeness problem.
1 code implementation • 2 Jul 2018 • Zhiming Zhou, Yuxuan Song, Lantao Yu, Hongwei Wang, Jiadong Liang, Wei-Nan Zhang, Zhihua Zhang, Yong Yu
In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs.
1 code implementation • ICML 2020 • Lantao Yu, Yang song, Jiaming Song, Stefano Ermon
Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.
1 code implementation • 27 Jun 2022 • Jiaming Song, Lantao Yu, Willie Neiswanger, Stefano Ermon
To extend BO to a broader class of models and utilities, we propose likelihood-free BO (LFBO), an approach based on likelihood-free inference.
1 code implementation • NeurIPS 2019 • Lantao Yu, Tianhe Yu, Chelsea Finn, Stefano Ermon
Critically, our model can infer rewards for new, structurally-similar tasks from a single demonstration.
Ranked #1 on MuJoCo Games on Sawyer Pusher
2 code implementations • ICLR 2019 • Sidi Lu, Lantao Yu, Siyuan Feng, Yaoming Zhu, Wei-Nan Zhang, Yong Yu
In this paper, we study the generative models of sequential discrete data.
1 code implementation • 30 Jul 2019 • Lantao Yu, Jiaming Song, Stefano Ermon
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification.
6 code implementations • NeurIPS 2020 • Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma
We also characterize the trade-off between the gain and risk of leaving the support of the batch data.
2 code implementations • 1 Oct 2020 • Yuandong Tian, Lantao Yu, Xinlei Chen, Surya Ganguli
We propose a novel theoretical framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks (e. g., SimCLR).
2 code implementations • ICLR 2022 • Minkai Xu, Lantao Yu, Yang song, Chence Shi, Stefano Ermon, Jian Tang
GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.
3 code implementations • 30 May 2017 • Jun Wang, Lantao Yu, Wei-Nan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, Dell Zhang
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair.
23 code implementations • 18 Sep 2016 • Lantao Yu, Wei-Nan Zhang, Jun Wang, Yong Yu
As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data.
Ranked #2 on Text Generation on Chinese Poems