no code implementations • ICML 2020 • Tianyi Zhou, Shengjie Wang, Jeff Bilmes
In this paper, we study the dynamics of neural net outputs in SSL and show that selecting and using first the unlabeled samples with more consistent outputs over the course of training (i. e., "time-consistency") can improve the final test accuracy and save computation.
no code implementations • 1 Mar 2024 • Shengjie Wang, Shaohuai Liu, Weirui Ye, Jiacheng You, Yang Gao
We have expanded the performance of EfficientZero to multiple domains, encompassing both continuous and discrete actions, as well as visual and low-dimensional inputs.
1 code implementation • 12 Dec 2023 • Haoming Liu, Yuanhe Guo, Shengjie Wang, Hongyi Wen
In this work, we study the combinations of diffusion models.
no code implementations • 13 Oct 2023 • Fengbo Lan, Shengjie Wang, Yunzhe Zhang, Haotian Xu, Oluwatosin Oseni, Yang Gao, Tao Zhang
Achieving human-like dexterous manipulation remains a crucial area of research in robotics.
no code implementations • 4 Oct 2023 • Weirui Ye, Yunsheng Zhang, Mengchen Wang, Shengjie Wang, Xianfan Gu, Pieter Abbeel, Yang Gao
Our method tolerates the unavoidable noise in embodied foundation models.
1 code implementation • 5 Jun 2023 • Alexander Bukharin, Tianyi Liu, Shengjie Wang, Simiao Zuo, Weihao Gao, Wen Yan, Tuo Zhao
To address this issue, we propose a multi-stage computational framework -- ASTEROID, which lowers the data cost of MLFFs by leveraging a combination of cheap inaccurate data and expensive accurate data.
1 code implementation • 4 May 2023 • Xiang Zheng, Xingjun Ma, Shengjie Wang, Xinyu Wang, Chao Shen, Cong Wang
Our experiments validate the effectiveness of the four types of adversarial intrinsic regularizers and the bias-reduction method in enhancing black-box adversarial policy learning across a variety of environments.
no code implementations • 27 Mar 2023 • Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Tao Zhang
Symmetric bi-manual manipulation is essential for various on-orbit operations due to its potent load capacity.
no code implementations • 28 Feb 2023 • Haotian Xu, Shengjie Wang, Zhaolei Wang, Yunzhe Zhang, Qing Zhuo, Yang Gao, Tao Zhang
In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety budget) with the aid of a new metric we propose.
no code implementations • 2 Jan 2023 • Shengjie Wang, Fengbo Lan, Xiang Zheng, Yuxue Cao, Oluwatosin Oseni, Haotian Xu, Tao Zhang, Yang Gao
In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization.
1 code implementation • 18 Nov 2022 • Liangwei Yang, Shengjie Wang, Yunzhe Tao, Jiankai Sun, Xiaolong Liu, Philip S. Yu, Taiqing Wang
Graph Neural Network (GNN) based recommender systems have been attracting more and more attention in recent years due to their excellent performance in accuracy.
1 code implementation • 3 Sep 2022 • Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Xinru Xie, Lei Liu
However, due to the increase in planning dimension and the intensification of system dynamics coupling, the motion planning of dual-arm free-floating space robots remains an open challenge.
1 code implementation • 6 Jul 2022 • Shengjie Wang, Yuxue Cao, Xiang Zheng, Tao Zhang
Module I realizes the multi-target trajectory planning for two end-effectors within a large target space.
1 code implementation • 17 Jun 2022 • Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Yiran Geng, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang
In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.
no code implementations • NeurIPS 2021 • Shengjie Wang, Tianyi Zhou, Chandrashekhar Lavania, Jeff A. Bilmes
Robust submodular partitioning promotes the diversity of every block in the partition.
no code implementations • 4 Mar 2021 • Evangelos Theodorou, Shengjie Wang, Yanfei Kang, Evangelos Spiliotis, Spyros Makridakis, Vassilios Assimakopoulos
The main objective of the M5 competition, which focused on forecasting the hierarchical unit sales of Walmart, was to evaluate the accuracy and uncertainty of forecasting methods in the field in order to identify best practices and highlight their practical implications.
no code implementations • ICLR 2021 • Tianyi Zhou, Shengjie Wang, Jeff Bilmes
Neural nets training can easily overfit to noisy labels and end with poor generalization performance.
no code implementations • NeurIPS 2020 • Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes
Compared to existing CL methods: (1) DIH is more stable over time than using only instantaneous hardness, which is noisy due to stochastic training and DNN's non-smoothness; (2) DIHCL is computationally inexpensive since it uses only a byproduct of back-propagation and thus does not require extra inference.
no code implementations • 25 Sep 2019 • Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes
The advantages of DIHCL, compared to other curriculum learning approaches, are: (1) DIHCL does not require additional inference steps over the data not selected by DIHCL in each epoch, (2) the dynamic instance hardness, compared to static instance hardness (e. g., instantaneous loss), is more stable as it integrates information over the entire training history up to the present time.
no code implementations • ICLR 2019 • Shengjie Wang, Tianyi Zhou, Jeff Bilmes
In particular, we study how to attribute a DNN's bias to its input features.
no code implementations • ICLR 2019 • Shengjie Wang, Tianyi Zhou, Jeff Bilmes
In this paper, we discuss three novel observations about dropout to better understand the generalization of DNNs with rectified linear unit (ReLU) activations: 1) dropout is a smoothing technique that encourages each local linear model of a DNN to be trained on data points from nearby regions; 2) a constant dropout rate can result in effective neural-deactivation rates that are significantly different for layers with different fractions of activated neurons; and 3) the rescaling factor of dropout causes an inconsistency to occur between the normalization during training and testing conditions when batch normalization is also used.
no code implementations • NeurIPS 2018 • Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes
We study a new method (``Diverse Ensemble Evolution (DivE$^2$)'') to train an ensemble of machine learning models that assigns data to models at each training epoch based on each model's current expertise and an intra- and inter-model diversity reward.
no code implementations • NeurIPS 2015 • Kai Wei, Rishabh K. Iyer, Shengjie Wang, Wenruo Bai, Jeff A. Bilmes
In the present paper, we bridge this gap, by proposing several new algorithms (including greedy, majorization-minimization, minorization-maximization, and relaxation algorithms) that not only scale to large datasets but that also achieve theoretical approximation guarantees comparable to the state-of-the-art.
no code implementations • 19 Nov 2015 • Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana, Gregor Urban, Shengjie Wang, Ozlem Aslan, Matthai Philipose, Matthew Richardson, Charles Sutton
We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • NeurIPS 2015 • Kai Wei, Rishabh Iyer, Shengjie Wang, Wenruo Bai, Jeff Bilmes
While the robust versions have been studied in the theory community, existing work has focused on tight approximation guarantees, and the resultant algorithms are not, in general, scalable to very large real-world applications.
no code implementations • 29 Oct 2014 • Shengjie Wang, John T. Halloran, Jeff A. Bilmes, William S. Noble
Liquid chromatography coupled with tandem mass spectrometry, also known as shotgun proteomics, is a widely-used high-throughput technology for identifying proteins in complex biological samples.