
Sceneaware Generative Network for Human Motion Synthesis
We revisit human motion synthesis, a task useful in various real world a...
read it

Leveraging Nonuniformity in Firstorder Nonconvex Optimization
Classical global convergence results for firstorder methods rely on uni...
read it

Unsupervised 3D Shape Completion through GAN Inversion
Most 3D shape completion approaches rely heavily on partialcomplete sha...
read it

Visually Informed Binaural Audio Generation without Binaural Audios
Stereophonic audio, especially binaural audio, plays an essential role i...
read it

On the Optimality of Batch Policy Optimization Algorithms
Batch policy optimization considers leveraging existing data for policy ...
read it

Nearly HorizonFree Offline Reinforcement Learning
We revisit offline reinforcement learning on episodic timehomogeneous t...
read it

OffPolicy Imitation Learning from Observations
Learning from Observations (LfO) is a practical reinforcement learning s...
read it

Towards Automatic Evaluation of Dialog Systems: A ModelFree OffPolicy Evaluation Approach
Reliable automatic evaluation of dialogue systems under an interactive e...
read it

Focal Frequency Loss for Generative Models
Despite the remarkable success of generative models in creating photorea...
read it

Offline Policy Selection under Uncertainty
The presence of uncertainty in policy evaluation significantly complicat...
read it

Learning Discrete Energybased Models via Auxiliaryvariable Local Exploration
Discrete structures play an important role in applications like program ...
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 ...
read it

Named Entity Recognition for Social Media Texts with Semantic Augmentation
Existing approaches for named entity recognition suffer from data sparsi...
read it

CoinDICE: OffPolicy Confidence Interval Estimation
We study highconfidence behavioragnostic offpolicy evaluation in rein...
read it

OffPolicy Evaluation via the Regularized Lagrangian
The recently proposed distribution correction estimation (DICE) family o...
read it

Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach
Structural equation models (SEMs) are widely used in sciences, ranging f...
read it

Unsupervised Landmark Learning from Unpaired Data
Recent attempts for unsupervised landmark learning leverage synthesized ...
read it

Scalable Deep Generative Modeling for Sparse Graphs
Learning graph generative models is a challenging task for deep learning...
read it

Video Representation Learning with Visual Tempo Consistency
Visual tempo, which describes how fast an action goes, has shown its pot...
read it

Novel Policy Seeking with Constrained Optimization
In this work, we address the problem of learning to seek novel policies ...
read it

Evolutionary Stochastic Policy Distillation
Solving the GoalConditioned Reward Sparse (GCRS) task is a challenging ...
read it

Temporal Pyramid Network for Action Recognition
Visual tempo characterizes the dynamics and the temporal scale of an act...
read it

SelfSupervised Scene Deocclusion
Natural scene understanding is a challenging task, particularly when enc...
read it

Learning Sparse Rewarded Tasks from SubOptimal Demonstrations
Modelfree deep reinforcement learning (RL) has demonstrated its superio...
read it

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Learning a good image prior is a longterm goal for image restoration an...
read it

EnergyBased Processes for Exchangeable Data
Recently there has been growing interest in modeling sets with exchangea...
read it

Batch Stationary Distribution Estimation
We consider the problem of approximating the stationary distribution of ...
read it

GenDICE: Generalized Offline Estimation of Stationary Values
An important problem that arises in reinforcement learning and Monte Car...
read it

Differentiable Topk Operator with Optimal Transport
The topk operation, i.e., finding the k largest or smallest elements fr...
read it

Real or Not Real, that is the Question
While generative adversarial networks (GAN) have been widely adopted in ...
read it

Reinforcement Learning via FenchelRockafellar Duality
We review basic concepts of convex duality, focusing on the very general...
read it

Retrosynthesis Prediction with Conditional Graph Logic Network
Retrosynthesis is one of the fundamental problems in organic chemistry. ...
read it

AlgaeDICE: Policy Gradient from Arbitrary Experience
In many realworld applications of reinforcement learning (RL), interact...
read it

Overcoming Catastrophic Forgetting by Generative Regularization
In this paper, we propose a new method to overcome catastrophic forgetti...
read it

EnergyInspired Models: Learning with SamplerInduced Distributions
Energybased models (EBMs) are powerful probabilistic models, but suffer...
read it

Recursive Visual Sound Separation Using MinusPlus Net
Sounds provide rich semantics, complementary to visual data, for many ta...
read it

DualDICE: BehaviorAgnostic Estimation of Discounted Stationary Distribution Corrections
In many realworld reinforcement learning applications, access to the en...
read it

Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification
We propose a new approach, called cooperative neural networks (CoNN), wh...
read it

Exponential Family Estimation via Adversarial Dynamics Embedding
We present an efficient algorithm for maximum likelihood estimation (MLE...
read it

Feature Intertwiner for Object Detection
A welltrained model should classify objects with a unanimous score for ...
read it

Learning to Plan via Neural ExplorationExploitation Trees
Samplingbased algorithms such as RRT and its variants are powerful tool...
read it

Bayesian Metanetwork Architecture Learning
For deep neural networks, the particular structure often plays a vital r...
read it

Kernel Exponential Family Estimation via Doubly Dual Embedding
We investigate penalized maximum loglikelihood estimation for exponenti...
read it

Learning to Defense by Learning to Attack
Adversarial training provides a principled approach for training robust ...
read it

A Neural Compositional Paradigm for Image Captioning
Mainstream captioning models often follow a sequential structure to gene...
read it

Neural Network Encapsulation
A capsule is a collection of neurons which represents different variants...
read it

Move Forward and Tell: A Progressive Generator of Video Descriptions
We present an efficient framework that can generate a coherent paragraph...
read it

Rethinking the Form of Latent States in Image Captioning
RNNs and their variants have been widely adopted for image captioning. I...
read it

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data
Learning nonlinear dynamics from diffusion data is a challenging problem...
read it

Learning towards Minimum Hyperspherical Energy
Neural networks are a powerful class of nonlinear functions that can be ...
read it
Bo Dai
is this you? claim profile
Research Assistant, Ph.D. Candidate at Georgia Institute of Technology