Honglak Lee

verfied profile

∙ 0 followers
Google ∙ University of Michigan

Senior Vice President and Chief Scientist of LG AI Research; Associate Professor of CSE University of Michigan

Featured Co-authors

Sergey Levine
267 publications
Bo Li
251 publications
Pieter Abbeel
180 publications
Rui Zhang
163 publications
Yi Zhang
140 publications
Ming-Hsuan Yang
115 publications
Bernt Schiele
108 publications
Quoc V. Le
92 publications
Pushmeet Kohli
89 publications
Abhinav Gupta
76 publications
Jinwoo Shin
69 publications

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on ...
07/13/2021 ∙ by Sungryull Sohn, et al. ∙ 10 ∙ share

read it
Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning

Learning to reach goal states and learning diverse skills through mutual...
06/02/2021 ∙ by Jongwook Choi, et al. ∙ 9 ∙ share

read it
Pathdreamer: A World Model for Indoor Navigation

People navigating in unfamiliar buildings take advantage of myriad visua...
05/18/2021 ∙ by Jing Yu Koh, et al. ∙ 12 ∙ share

read it
Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction

Learning to predict the long-term future of video frames is notoriously ...
04/14/2021 ∙ by Wonkwang Lee, et al. ∙ 1 ∙ share

read it
Adversarial Environment Generation for Learning to Navigate the Web

Learning to autonomously navigate the web is a difficult sequential deci...
03/02/2021 ∙ by Izzeddin Gür, et al. ∙ 14 ∙ share

read it
State Entropy Maximization with Random Encoders for Efficient Exploration

Recent exploration methods have proven to be a recipe for improving samp...
02/18/2021 ∙ by Younggyo Seo, et al. ∙ 13 ∙ share

read it
Cross-Modal Contrastive Learning for Text-to-Image Generation

The output of text-to-image synthesis systems should be coherent, clear,...
01/12/2021 ∙ by Han Zhang, et al. ∙ 16 ∙ share

read it
Evolving Reinforcement Learning Algorithms

We propose a method for meta-learning reinforcement learning algorithms ...
01/08/2021 ∙ by John D. Co-Reyes, et al. ∙ 28 ∙ share

read it
Few-shot Sequence Learning with Transformers

Few-shot algorithms aim at learning new tasks provided only a handful of...
12/17/2020 ∙ by Lajanugen Logeswaran, et al. ∙ 9 ∙ share

read it
Text-to-Image Generation Grounded by Fine-Grained User Attention

Localized Narratives is a dataset with detailed natural language descrip...
11/07/2020 ∙ by Jing Yu Koh, et al. ∙ 5 ∙ share

read it
What's in a Loss Function for Image Classification?

It is common to use the softmax cross-entropy loss to train neural netwo...
10/30/2020 ∙ by Simon Kornblith, et al. ∙ 31 ∙ share

read it
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in First-person Simulated 3D Environments

First-person object-interaction tasks in high-fidelity, 3D, simulated en...
10/28/2020 ∙ by Wilka Carvalho, et al. ∙ 10 ∙ share

read it
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning

Sample efficiency has been one of the major challenges for deep reinforc...
10/23/2020 ∙ by Guangxiang Zhu, et al. ∙ 5 ∙ share

read it
i-Mix: A Strategy for Regularizing Contrastive Representation Learning

Contrastive representation learning has shown to be an effective way of ...
10/17/2020 ∙ by Kibok Lee, et al. ∙ 4 ∙ share

read it
Text as Neural Operator: Image Manipulation by Text Instruction

In this paper, we study a new task that allows users to edit an input im...
08/11/2020 ∙ by Tianhao Zhang, et al. ∙ 7 ∙ share

read it
Predictive Information Accelerates Learning in RL

The Predictive Information is the mutual information between the past an...
07/24/2020 ∙ by Kuang-Huei Lee, et al. ∙ 21 ∙ share

read it
An Ode to an ODE

We present a new paradigm for Neural ODE algorithms, calledODEtoODE, whe...
06/19/2020 ∙ by Krzysztof Choromanski, et al. ∙ 18 ∙ share

read it
CompressNet: Generative Compression at Extremely Low Bitrates

Compressing images at extremely low bitrates (< 0.1 bpp) has always been...
06/14/2020 ∙ by Suraj Kiran Raman, et al. ∙ 11 ∙ share

read it
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

Model-based reinforcement learning (RL) enjoys several benefits, such as...
05/14/2020 ∙ by Kimin Lee, et al. ∙ 7 ∙ share

read it
Time Dependence in Non-Autonomous Neural ODEs

Neural Ordinary Differential Equations (ODEs) are elegant reinterpretati...
05/05/2020 ∙ by Jared Quincy Davis, et al. ∙ 7 ∙ share

read it
Improved Consistency Regularization for GANs

Recent work has increased the performance of Generative Adversarial Netw...
02/11/2020 ∙ by Zhengli Zhao, et al. ∙ 38 ∙ share

read it
BRPO: Batch Residual Policy Optimization

In batch reinforcement learning (RL), one often constrains a learned pol...
02/08/2020 ∙ by Sungryull Sohn, et al. ∙ 11 ∙ share

read it
High-Fidelity Synthesis with Disentangled Representation

Learning disentangled representation of data without supervision is an i...
01/13/2020 ∙ by Wonkwang Lee, et al. ∙ 0 ∙ share

read it
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies

We propose and address a novel few-shot RL problem, where a task is char...
01/01/2020 ∙ by Sungryull Sohn, et al. ∙ 15 ∙ share

read it
Efficient Adversarial Training with Transferable Adversarial Examples

Adversarial training is an effective defense method to protect classific...
12/27/2019 ∙ by Haizhong Zheng, et al. ∙ 12 ∙ share

read it
How Should an Agent Practice?

We present a method for learning intrinsic reward functions to drive the...
12/15/2019 ∙ by Janarthanan Rajendran, et al. ∙ 17 ∙ share

read it
High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks

Predicting future video frames is extremely challenging, as there are ma...
11/05/2019 ∙ by Ruben Villegas, et al. ∙ 37 ∙ share

read it
Consistency Regularization for Generative Adversarial Networks

Generative Adversarial Networks (GANs) are known to be difficult to trai...
10/26/2019 ∙ by Han Zhang, et al. ∙ 28 ∙ share

read it
A Simple Randomization Technique for Generalization in Deep Reinforcement Learning

Deep reinforcement learning (RL) agents often fail to generalize to unse...
10/11/2019 ∙ by Kimin Lee, et al. ∙ 24 ∙ share

read it
IEG: Robust Neural Network Training to Tackle Severe Label Noise

Collecting large-scale data with clean labels for supervised training of...
10/01/2019 ∙ by Zizhao Zhang, et al. ∙ 10 ∙ share

read it
Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?

Hierarchical reinforcement learning has demonstrated significant success...
09/23/2019 ∙ by Ofir Nachum, et al. ∙ 14 ∙ share

read it
Efficient Exploration with Self-Imitation Learning via Trajectory-Conditioned Policy

This paper proposes a method for learning a trajectory-conditioned polic...
07/24/2019 ∙ by Yijie Guo, et al. ∙ 1 ∙ share

read it
Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networks

Training a deep network policy for robot manipulation is notoriously cos...
06/21/2019 ∙ by Xinchen Yan, et al. ∙ 3 ∙ share

read it
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing

Deep neural networks (DNNs) have achieved great success in various appli...
06/19/2019 ∙ by Haonan Qiu, et al. ∙ 7 ∙ share

read it
Unsupervised Learning of Object Structure and Dynamics from Videos

Extracting and predicting object structure and dynamics from videos with...
06/19/2019 ∙ by Matthias Minderer, et al. ∙ 4 ∙ share

read it
Zero-Shot Entity Linking by Reading Entity Descriptions

We present the zero-shot entity linking task, where mentions must be lin...
06/18/2019 ∙ by Lajanugen Logeswaran, et al. ∙ 0 ∙ share

read it
Similarity of Neural Network Representations Revisited

Recent work has sought to understand the behavior of neural networks by ...
05/01/2019 ∙ by Simon Kornblith, et al. ∙ 20 ∙ share

read it
Incremental Learning with Unlabeled Data in the Wild

Deep neural networks are known to suffer from catastrophic forgetting in...
03/29/2019 ∙ by Kibok Lee, et al. ∙ 13 ∙ share

read it
Robust Inference via Generative Classifiers for Handling Noisy Labels

Large-scale datasets may contain significant proportions of noisy (incor...
01/31/2019 ∙ by Kimin Lee, et al. ∙ 7 ∙ share

read it
Diversity-Sensitive Conditional Generative Adversarial Networks

We propose a simple yet highly effective method that addresses the mode-...
01/25/2019 ∙ by Dingdong Yang, et al. ∙ 16 ∙ share

read it
Generative Adversarial Self-Imitation Learning

This paper explores a simple regularizer for reinforcement learning by p...
12/03/2018 ∙ by Yijie Guo, et al. ∙ 0 ∙ share

read it
Learning Latent Dynamics for Planning from Pixels

Planning has been very successful for control tasks with known environme...
11/12/2018 ∙ by Danijar Hafner, et al. ∙ 6 ∙ share

read it
Contingency-Aware Exploration in Reinforcement Learning

This paper investigates whether learning contingency-awareness and contr...
11/05/2018 ∙ by Jongwook Choi, et al. ∙ 8 ∙ share

read it
Content preserving text generation with attribute controls

In this work, we address the problem of modifying textual attributes of ...
11/03/2018 ∙ by Lajanugen Logeswaran, et al. ∙ 0 ∙ share

read it
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning

We study the problem of representation learning in goal-conditioned hier...
10/02/2018 ∙ by Ofir Nachum, et al. ∙ 12 ∙ share

read it
Learning Hierarchical Semantic Image Manipulation through Structured Representations

Understanding, reasoning, and manipulating semantic concepts of images h...
08/22/2018 ∙ by Seunghoon Hong, et al. ∙ 2 ∙ share

read it
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

Long-term human motion can be represented as a series of motion modes---...
08/14/2018 ∙ by Xinchen Yan, et al. ∙ 2 ∙ share

read it
Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

We introduce a new RL problem where the agent is required to execute a g...
07/19/2018 ∙ by Sungryull Sohn, et al. ∙ 0 ∙ share

read it
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Detecting test samples drawn sufficiently far away from the training dis...
07/10/2018 ∙ by Kimin Lee, et al. ∙ 3 ∙ share

read it
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

Integrating model-free and model-based approaches in reinforcement learn...
07/04/2018 ∙ by Jacob Buckman, et al. ∙ 6 ∙ share

read it