Bo Dai

is this you? claim profile

∙ 0 followers
Google ∙ Georgia Institute of Technology ∙ The Chinese University of Hong Kong

Research Assistant, Ph.D. Candidate at Georgia Institute of Technology

Featured Co-authors

Masashi Sugiyama
158 publications
Xiaogang Wang
137 publications
Raquel Urtasun
128 publications
Chen Change Loy
104 publications
Anima Anandkumar
101 publications
Wanli Ouyang
93 publications
Dahua Lin
85 publications
Le Song
82 publications
Csaba Szepesvari
81 publications
Wei Wei
76 publications
Ping Luo
73 publications

Focal Frequency Loss for Generative Models

Despite the remarkable success of generative models in creating photorea...
12/23/2020 ∙ by Liming Jiang, et al. ∙ 23 ∙ share

read it
Offline Policy Selection under Uncertainty

The presence of uncertainty in policy evaluation significantly complicat...
12/12/2020 ∙ by Mengjiao Yang, et al. ∙ 0 ∙ share

read it
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration

Discrete structures play an important role in applications like program ...
11/10/2020 ∙ by Hanjun Dai, et al. ∙ 14 ∙ share

read it
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs

Natural images are projections of 3D objects on a 2D image plane. While ...
11/02/2020 ∙ by Xingang Pan, et al. ∙ 31 ∙ share

read it
Named Entity Recognition for Social Media Texts with Semantic Augmentation

Existing approaches for named entity recognition suffer from data sparsi...
10/29/2020 ∙ by Yuyang Nie, et al. ∙ 0 ∙ share

read it
CoinDICE: Off-Policy Confidence Interval Estimation

We study high-confidence behavior-agnostic off-policy evaluation in rein...
10/22/2020 ∙ by Bo Dai, et al. ∙ 0 ∙ share

read it
Off-Policy Evaluation via the Regularized Lagrangian

The recently proposed distribution correction estimation (DICE) family o...
07/07/2020 ∙ by Mengjiao Yang, et al. ∙ 4 ∙ share

read it
Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach

Structural equation models (SEMs) are widely used in sciences, ranging f...
07/02/2020 ∙ by Luofeng Liao, et al. ∙ 13 ∙ share

read it
Unsupervised Landmark Learning from Unpaired Data

Recent attempts for unsupervised landmark learning leverage synthesized ...
06/29/2020 ∙ by Yinghao Xu, et al. ∙ 14 ∙ share

read it
Scalable Deep Generative Modeling for Sparse Graphs

Learning graph generative models is a challenging task for deep learning...
06/28/2020 ∙ by Hanjun Dai, et al. ∙ 8 ∙ share

read it
Video Representation Learning with Visual Tempo Consistency

Visual tempo, which describes how fast an action goes, has shown its pot...
06/28/2020 ∙ by Ceyuan Yang, et al. ∙ 3 ∙ share

read it
Novel Policy Seeking with Constrained Optimization

In this work, we address the problem of learning to seek novel policies ...
05/21/2020 ∙ by Hao Sun, et al. ∙ 6 ∙ share

read it
Evolutionary Stochastic Policy Distillation

Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging ...
04/27/2020 ∙ by Hao Sun, et al. ∙ 9 ∙ share

read it
Temporal Pyramid Network for Action Recognition

Visual tempo characterizes the dynamics and the temporal scale of an act...
04/07/2020 ∙ by Ceyuan Yang, et al. ∙ 21 ∙ share

read it
Self-Supervised Scene De-occlusion

Natural scene understanding is a challenging task, particularly when enc...
04/06/2020 ∙ by Xiaohang Zhan, et al. ∙ 37 ∙ share

read it
Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations

Model-free deep reinforcement learning (RL) has demonstrated its superio...
04/01/2020 ∙ by Zhuangdi Zhu, et al. ∙ 5 ∙ share

read it
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

Learning a good image prior is a long-term goal for image restoration an...
03/30/2020 ∙ by Xingang Pan, et al. ∙ 0 ∙ share

read it
Energy-Based Processes for Exchangeable Data

Recently there has been growing interest in modeling sets with exchangea...
03/17/2020 ∙ by Mengjiao Yang, et al. ∙ 0 ∙ share

read it
Batch Stationary Distribution Estimation

We consider the problem of approximating the stationary distribution of ...
03/02/2020 ∙ by Junfeng Wen, et al. ∙ 7 ∙ share

read it
GenDICE: Generalized Offline Estimation of Stationary Values

An important problem that arises in reinforcement learning and Monte Car...
02/21/2020 ∙ by Ruiyi Zhang, et al. ∙ 11 ∙ share

read it
Differentiable Top-k Operator with Optimal Transport

The top-k operation, i.e., finding the k largest or smallest elements fr...
02/16/2020 ∙ by Yujia Xie, et al. ∙ 6 ∙ share

read it
Real or Not Real, that is the Question

While generative adversarial networks (GAN) have been widely adopted in ...
02/12/2020 ∙ by Yuanbo Xiangli, et al. ∙ 15 ∙ share

read it
Reinforcement Learning via Fenchel-Rockafellar Duality

We review basic concepts of convex duality, focusing on the very general...
01/07/2020 ∙ by Ofir Nachum, et al. ∙ 0 ∙ share

read it
Retrosynthesis Prediction with Conditional Graph Logic Network

Retrosynthesis is one of the fundamental problems in organic chemistry. ...
01/06/2020 ∙ by Hanjun Dai, et al. ∙ 6 ∙ share

read it
AlgaeDICE: Policy Gradient from Arbitrary Experience

In many real-world applications of reinforcement learning (RL), interact...
12/04/2019 ∙ by Ofir Nachum, et al. ∙ 0 ∙ share

read it
Overcoming Catastrophic Forgetting by Generative Regularization

In this paper, we propose a new method to overcome catastrophic forgetti...
12/03/2019 ∙ by Patrick H. Chen, et al. ∙ 0 ∙ share

read it
Energy-Inspired Models: Learning with Sampler-Induced Distributions

Energy-based models (EBMs) are powerful probabilistic models, but suffer...
10/31/2019 ∙ by Dieterich Lawson, et al. ∙ 18 ∙ share

read it
Recursive Visual Sound Separation Using Minus-Plus Net

Sounds provide rich semantics, complementary to visual data, for many ta...
08/30/2019 ∙ by Xudong Xu, et al. ∙ 3 ∙ share

read it
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections

In many real-world reinforcement learning applications, access to the en...
06/10/2019 ∙ by Ofir Nachum, et al. ∙ 0 ∙ share

read it
Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification

We propose a new approach, called cooperative neural networks (CoNN), wh...
06/01/2019 ∙ by Harsh Shrivastava, et al. ∙ 0 ∙ share

read it
Exponential Family Estimation via Adversarial Dynamics Embedding

We present an efficient algorithm for maximum likelihood estimation (MLE...
04/27/2019 ∙ by Bo Dai, et al. ∙ 28 ∙ share

read it
Feature Intertwiner for Object Detection

A well-trained model should classify objects with a unanimous score for ...
03/28/2019 ∙ by Hongyang Li, et al. ∙ 0 ∙ share

read it
Learning to Plan via Neural Exploration-Exploitation Trees

Sampling-based algorithms such as RRT and its variants are powerful tool...
02/28/2019 ∙ by Binghong Chen, et al. ∙ 0 ∙ share

read it
Bayesian Meta-network Architecture Learning

For deep neural networks, the particular structure often plays a vital r...
12/22/2018 ∙ by Albert Shaw, et al. ∙ 0 ∙ share

read it
Kernel Exponential Family Estimation via Doubly Dual Embedding

We investigate penalized maximum log-likelihood estimation for exponenti...
11/06/2018 ∙ by Bo Dai, et al. ∙ 4 ∙ share

read it
Learning to Defense by Learning to Attack

Adversarial training provides a principled approach for training robust ...
11/03/2018 ∙ by Zhehui Chen, et al. ∙ 0 ∙ share

read it
A Neural Compositional Paradigm for Image Captioning

Mainstream captioning models often follow a sequential structure to gene...
10/23/2018 ∙ by Bo Dai, et al. ∙ 0 ∙ share

read it
Neural Network Encapsulation

A capsule is a collection of neurons which represents different variants...
08/11/2018 ∙ by Hongyang Li, et al. ∙ 0 ∙ share

read it
Move Forward and Tell: A Progressive Generator of Video Descriptions

We present an efficient framework that can generate a coherent paragraph...
07/26/2018 ∙ by Yilei Xiong, et al. ∙ 2 ∙ share

read it
Rethinking the Form of Latent States in Image Captioning

RNNs and their variants have been widely adopted for image captioning. I...
07/26/2018 ∙ by Bo Dai, et al. ∙ 10 ∙ share

read it
Learning Deep Hidden Nonlinear Dynamics from Aggregate Data

Learning nonlinear dynamics from diffusion data is a challenging problem...
07/22/2018 ∙ by Yisen Wang, et al. ∙ 0 ∙ share

read it
Learning towards Minimum Hyperspherical Energy

Neural networks are a powerful class of nonlinear functions that can be ...
05/23/2018 ∙ by Weiyang Liu, et al. ∙ 0 ∙ share

read it
Decoupled Networks

Inner product-based convolution has been a central component of convolut...
04/22/2018 ∙ by Weiyang Liu, et al. ∙ 0 ∙ share

read it
Syntax-Directed Variational Autoencoder for Structured Data

Deep generative models have been enjoying success in modeling continuous...
02/24/2018 ∙ by Hanjun Dai, et al. ∙ 0 ∙ share

read it
Smoothed Dual Embedding Control

We revisit the Bellman optimality equation with Nesterov's smoothing tec...
12/29/2017 ∙ by Bo Dai, et al. ∙ 0 ∙ share

read it
Boosting the Actor with Dual Critic

This paper proposes a new actor-critic-style algorithm called Dual Actor...
12/29/2017 ∙ by Bo Dai, et al. ∙ 0 ∙ share

read it
Deep Hyperspherical Learning

Convolution as inner product has been the founding basis of convolutiona...
11/08/2017 ∙ by Weiyang Liu, et al. ∙ 0 ∙ share

read it
Towards Black-box Iterative Machine Teaching

In this paper, we make an important step towards the black-box machine t...
10/21/2017 ∙ by Weiyang Liu, et al. ∙ 0 ∙ share

read it
Contrastive Learning for Image Captioning

Image captioning, a popular topic in computer vision, has achieved subst...
10/06/2017 ∙ by Bo Dai, et al. ∙ 0 ∙ share

read it
Iterative Machine Teaching

In this paper, we consider the problem of machine teaching, the inverse ...
05/30/2017 ∙ by Weiyang Liu, et al. ∙ 0 ∙ share

read it